#680 by GitHub stars
dzhng/skills
Reusable AI agent skills for software factories: explore ideas, write specs, implement, review, and run autonomous research. Works with Claude Code, Codex, and other skill-compatible agents.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/authoring/audit-agents/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/authoring/eval-skills/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/authoring/write-skills/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/audit-decisions/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/audit-performance/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/audit-tests/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/auto-research/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/claude/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/close-spec/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/code-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/codex/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/eli5/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/explore-unknowns/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/handoff-spec/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/implement-spec/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/implement-spec-with-codex/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/implement-spec-with-goal/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/marketing-pages/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/port-features/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0867285d3f26
No earlier version was observed for comparison.
skills/engineering/ratchet-files/SKILL.md
Week of Nov 2, 2026 · +52 / −14 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
- 3 description: Ratchet source file size so every file stays small enough for an agent to read whole: find every file over a token budget, split oversized files by concept, and set up the pre-commit ratchet that stops them from growing. Use when a commit is blocked because a file is over the size budget, when asked to find or split oversized/long/god files, when a file you need to change is too large to read in one pass, or when asked to add a file-size limit or hook to a repository.
+ 3 description: >-
+ 4 Ratchet source file size so every file stays small enough for an agent to read
+ 5 whole: find every file over a token budget, split oversized files by concept,
+ 6 and set up the pre-commit ratchet that stops them from growing. Use when a
+ 7 commit is blocked because a file is over the size budget, when asked to find
+ 8 or split oversized/long/god files, when a file you need to change is too large
+ 9 to read in one pass, or when asked to add a file-size limit or hook to a
+ 10 repository or repair commit-hook coverage across worktrees.
- 75 adds, and make sure `.gitignore` covers `node_modules/`.
+ 82 adds, and make sure `.gitignore` covers `node_modules/`. Choose dependency
+ 83 versions compatible with the repository's supported runtime; the check
+ 84 script's minimum Node version does not establish the runner's minimum.
- 88 With no runner, add husky with lint-staged as dev dependencies, run
- 89 `npx husky init`, replace the whole of `.husky/pre-commit` (it starts as
- 90 `npm test`) with `npx lint-staged` or the package manager's equivalent, and
- 91 add the lint-staged entry above. Husky installs the hook on each clone's
- 92 package install.
+ 97 Inspect `git config --show-origin --get core.hooksPath` and the existing
+ 98 hooks first. The config is normally shared while a relative path resolves
+ 99 per checkout, so Husky's `.husky/_` exists only where the package install
+ 100 ran and every other worktree commits unchecked. Keep an existing runner
+ 101 only if it installs into linked worktrees too.
+ 102
+ 103 Otherwise add lint-staged as an exact dev dependency and call
+ 104 [`scripts/install-git-hooks.mjs`](scripts/install-git-hooks.mjs) from the
+ 105 root package's `prepare` script, after any existing prepare work. Use this
+ 106 skill's copy if the skill is committed in the repository, else commit an
+ 107 unchanged copy beside the repository's tool scripts; never point at a
+ 108 global skill path. It installs one hook in the shared hooks directory that
+ 109 runs the committing checkout's own lint-staged, refuses a checkout without
+ 110 dependencies with its lockfile's install command, and leaves custom hooks
+ 111 alone. Each committing worktree needs its own install; never share another
+ 112 checkout's dependencies or build output to provide them. If its logic must
+ 113 change, extend `node --test scripts/install-git-hooks.test.mjs` from this
+ 114 skill to cover it.
+ 115
+ 116 When replacing a repository-owned runner such as Husky, move its other
+ 117 checks into lint-staged and remove its setup and dependency so no
+ 118 installer competes; never unset a user's own hooks path. Installing an
+ 119 older branch can still re-enable the old runner until a current branch
+ 120 installs again. Inspect any conflict the installer reports before going on.
- 97 - **Docs.** Document the budget, the opt-out pragma, and that a clone needs a
- 98 package install for the hook, where the repository documents its other
- 99 hooks; failing that, in a section of its README, creating one if needed.
+ 125 - **Docs.** Document the budget, the opt-out pragma, how package installation
+ 126 enables hooks across worktrees, that each committing checkout needs
+ 127 dependencies, and any replaced runner an older branch can re-enable,
+ 128 where the repository documents its other hooks; failing that, in a
+ 129 section of its README, creating one if needed.
- 103 Done when the setup commit passed the hook, and the installed hook refuses
- 104 `git commit` both of a staged new source file over the budget (a `.js` file
- 105 of more than four bytes per token of budget) and of a line added to a file the audit
- 106 listed, printing the split rules. Unstage and discard both probes afterwards.
+ 133 Verify with real `git commit` attempts in disposable repository fixtures,
+ 134 using the committed installer, runner configuration, and size-check script.
+ 135 Install once, then create a linked worktree without rerunning installation
+ 136 there. Make its dependencies available and prove its own staged oversized
+ 137 new file is refused with the split rules while an under-budget commit
+ 138 succeeds and the main checkout stays unchanged. Also prove an existing
+ 139 oversized file cannot grow, a checkout without dependencies refuses with
+ 140 setup instructions, repeated installation from a linked worktree works, and
+ 141 custom hooks survive installation. Remove the fixtures afterwards.
+ 142
+ 143 Done when these commit checks pass in both checkout types and the setup
+ 144 commit passed the new hook without bypassing it.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/refactor-clean/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/retro/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/write-docs/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/write-spec/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/engineering/write-tests/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/graphics/cinematic-shot/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/graphics/isometric-motion/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/graphics/launch-video/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/graphics/renderer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/graphics/xiaohei-illustrations/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/visual/compare-screenshots/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/visual/design-with-images/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/visual/preview-shots/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
skills/visual/screenshot-critique/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
dc8bdd9dbaaf → 0867285d3f26
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → dc8bdd9dbaaf
No earlier version was observed for comparison.
1.4kGitHub stars
14stars in 7 days
35skills in this repository
30commits in 30 days
Heat
6.4- Star growth, last 7 daysAhead of 84% of tracked repositories
- Star growth, last 24 hoursAhead of 84% of tracked repositories
- Rank movement, last 7 daysAhead of 29% of tracked repositories
- Commits, last 30 daysAhead of 87% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- audit-agents
skills/authoring/audit-agents - eval-skills
skills/authoring/eval-skills - write-skills
skills/authoring/write-skills - audit-decisions
skills/engineering/audit-decisions - audit-performance
skills/engineering/audit-performance - audit-tests
skills/engineering/audit-tests - auto-research
skills/engineering/auto-research - claude
skills/engineering/claude - close-spec
skills/engineering/close-spec - code-review
skills/engineering/code-review - codex
skills/engineering/codex - eli5
skills/engineering/eli5 - explore-unknowns
skills/engineering/explore-unknowns - handoff-spec
skills/engineering/handoff-spec - implement-spec
skills/engineering/implement-spec - implement-spec-with-codex
skills/engineering/implement-spec-with-codex - implement-spec-with-goal
skills/engineering/implement-spec-with-goal - marketing-pages
skills/engineering/marketing-pages - port-features
skills/engineering/port-features - ratchet-files
skills/engineering/ratchet-files - refactor-clean
skills/engineering/refactor-clean - retro
skills/engineering/retro - review
skills/engineering/review - write-docs
skills/engineering/write-docs - write-spec
skills/engineering/write-spec - write-tests
skills/engineering/write-tests - cinematic-shot
skills/graphics/cinematic-shot - isometric-motion
skills/graphics/isometric-motion - launch-video
skills/graphics/launch-video - renderer
skills/graphics/renderer - xiaohei-illustrations
skills/graphics/xiaohei-illustrations - compare-screenshots
skills/visual/compare-screenshots - design-with-images
skills/visual/design-with-images - preview-shots
skills/visual/preview-shots - screenshot-critique
skills/visual/screenshot-critique
How it works
audit-agents
When your agent uses it
Audit or rewrite AGENTS.md so it holds only lasting principles. Run it only when the user asks for it by name; never invoke it on your own.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
760 tokensWhen the skill is activated
Reference documents
1,132 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Tests for a line
- Shape
Files
SKILL.mdcore3,393 bytesassets/example-agents.mddoc5,364 bytes
Read SKILL.md
# Audit Agents
AGENTS.md is read by everyone who will ever work on the project. Picture the next thousand contributors over the next hundred years: a line belongs only if it is still true, and still changes what they do, after every file, tool and dependency has been replaced.
## Workflow
1. Read the AGENTS.md and the root readme. This is a document audit: run no builds and no tests.
2. Give every line one verdict, using the tests below.
- **Keep**: a principle that passes every test.
- **Rephrase**: a lasting lesson worded in today's mechanics, or too vague to act on.
- **Move**: a detail someone needs. Name the owner it belongs to: a readme, a manifest, a skill or a spec.
- **Delete**: repetition, history, or a line that changes nothing.
3. Check the shape against the example below.
4. Report the findings, highest impact first. Quote each line, give its verdict and the replacement text, and group repeats. Report no finding you can't quote.eval-skills
When your agent uses it
Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each example input, grade the artifact against the expected outcome, and let the gaps drive the edits. Use when the user wants to test/eval/improve/harden a skill, says "this skill keeps producing X / keeps missing Y", or hands a skill plus example input→expected-output pairs. Pairs with [write-skills](../write-skills/SKILL.md) (the authoring principles every fix obeys).
What it loads into context
Frontmatter
118 tokensAlways available to the agent
SKILL.md
1,810 tokensWhen the skill is activated
Reference documents
2,473 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Inputs you need — refuse without them
- Workflow
- Output
- Rules
Files
SKILL.mdcore7,671 bytes../write-skills/SKILL.mddoc10,877 bytes
Read SKILL.md
# Eval Skills
Treat a skill like a function under test. Feed it example inputs in a clean
room, check the artifacts against what good looks like, and let the failures
drive the edits. The eval is only honest if the run is **blind**: the agent
executing the skill must carry none of this conversation's context and must
never see the expected output. Leak either and you are teaching to the test.
## Inputs you need — refuse without them
Confirm all three before spawning anything. If any is missing or
unresolvable, stop and tell the user *exactly which one* and what a good
version looks like. Do not invent cases, guess intent, or eval against a
fuzzy wish.write-skills
When your agent uses it
Create or revise agent skills. Use when adding a new skill file, renaming a skill, simplifying an existing skill, improving trigger descriptions, or deciding what belongs in a skill versus references, scripts, assets, or ordinary docs.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
2,473 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- First Principles
- Leading Words
- Invocation
- Description
- Information Hierarchy
- When to Split
- Failure Modes
- Shape
- Edit Pass
- Done
Files
SKILL.mdcore10,877 bytesSKILL.mdcore10,877 bytesSKILL.mdcore10,877 bytes
Read SKILL.md
# Write Skills
A skill is not documentation. It is compressed operational memory for an
agent that already knows how to code and reason. Its job is
**predictability** — the agent taking the same *process* every run, not
producing the same output. Put only the context that changes what the agent
will do.
## First Principles
1. **Trigger from the description.** The frontmatter `description` is the
only part read before the skill loads. Say what the skill does and the
concrete situations that should trigger it. Do not hide trigger rules in
the body.audit-decisions
When your agent uses it
Audit the decisions an implementing agent made, not its diff — a pure audit that traces the session's history into a decisions ledger, changes no code, and never blocks an unsupervised run. Working code still embeds architecture the user never chose; surface it because future work inherits it. Use when the user wants to review the decisions the AI made on their behalf, before merging or committing AI-implemented work, when integrating a delegated subagent's pass, or when a fix "works" but might be a point fix.
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
2,329 tokensWhen the skill is activated
Reference documents
687 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- The Decisions Ledger
- Rules
- Done
Files
SKILL.mdcore10,232 bytes../eli5/SKILL.mddoc3,242 bytes
Read SKILL.md
# Audit Decisions
Given a good decision, an agent implements it faithfully; wherever the task is
underspecified, it makes the decision itself — silently, and the diff won't
flag it. Reviewing thousands of changed lines doesn't scale, and it inspects
the execution, which was probably fine. The audit that scales is of the
**decisions**: surface every one the implementer made on its own, judge
that list, and record the verdicts.
This is about architecture more than bugs. An implementation can work
perfectly and still rest on decisions the user never made — a data shape, a
storage location, a dependency, an API contract, a tradeoff of memory for
speed — and every one of them is load-bearing for future work. The user needs
to know them not because they're wrong, but because they now own them.audit-performance
When your agent uses it
Audit and prioritize performance work through bounded-work and forward-progress checks. Use when asked to find performance issues, investigate freezes/500s/OOMs, review retries or polling for no-progress loops, rank a performance backlog, or implement the next simple performance fixes.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
1,050 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Priority Policy
- Guardrails
- Done
Files
SKILL.mdcore5,252 bytes
Read SKILL.md
# Audit Performance
Find work that grows without a useful bound or repeats without progress. Produce an evidence-backed
ledger or report, then prefer the smallest fix that preserves recovery.
## Workflow
1. **Trace hot paths.** Find recurring syncs, polls, streams, retries, queues, scheduled jobs,
filesystem walks, and request-time reads. Follow each through its production caller; ignore
test-only paths.
2. **Compute the amplification.** State the trigger and worst-case work in concrete units: rows,
queries, pages, entries, bytes, jobs, retries, or full-file rewrites. Distinguish a bounded large
constant from work that grows with history, tenants, paths, or outage duration.
3. **Check forward progress.** For every retry, fixed-prefix batch, cutoff, or transitional poll,audit-tests
When your agent uses it
Audit whether tests earn their maintenance cost and which suite owns each contract. Use when pruning redundant tests, investigating implementation coupling or test-only production hooks, reviewing the value of proposed coverage, or auditing an entire subsystem. Use write-tests to implement the resulting test changes.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
1,837 tokensWhen the skill is activated
Reference documents
2,738 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Evidence record
- False confidence
- What earns retention
- Whole-subsystem sweeps
- Done
Files
SKILL.mdcore9,423 bytesSKILL.mdcore9,423 bytes../review/SKILL.mddoc1,892 bytes../write-tests/SKILL.mddoc10,174 bytes
Read SKILL.md
# Audit Tests
Audit **independent proof**: what bug would escape if this test disappeared?
The result is a map of contracts to their surviving tests, with evidence for
what to keep, repair, combine, or remove. Fewer tests is not the objective;
less maintenance for the same or better confidence is.
[write-tests](../write-tests/SKILL.md) owns how to write and falsify a test.
This skill owns whether that test adds proof and where that proof belongs.
[review](../review/SKILL.md) owns closing out the resulting changes.
## Workflow
1. **Bound the audit.** Read the repository and scoped instructions, then pickauto-research
When your agent uses it
Run fast, progressive experiments to map tunable parameters and their effects. Use when optimizing code, prompts, configurations, or other artifacts against a goal or benchmark, or when a long research run needs a planned hypothesis queue, focused trials, and durable findings.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
2,123 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Durable research record
- Evidence discipline
- Stopping
Files
SKILL.mdcore10,825 bytes
Read SKILL.md
# Auto Research
Optimize **learning per unit of time**. Start with one fast, revealing task,
plan competing hypotheses, test them separately, combine verified winners, then
expand coverage. The durable result is a **parameter-effect map** plus the best
verified artifact. An experiment is a checkpoint, not a stopping point.
## Workflow
1. **Recover the research state.** Read the objective, user feedback, project
instructions, and existing research records. Reconcile the handoff with actual
artifacts and running jobs; collect a pending attempt before launching another.
Identify the best verified artifact (the incumbent), active task, regression
set, hypothesis queue, and remaining budget. Reuse existing record locations.claude
When your agent uses it
Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude, or asks to delegate a well-scoped task to Claude. Supports selecting `--model` and thinking/effort level with defaults of the current `opus` alias and `high`.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
1,498 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Defaults
- Prompting Claude
- Consultation
- Implementation — explicit ask only
- Liveness
- Rules
Files
SKILL.mdcore6,468 bytesSKILL.mdcore6,468 bytes
Read SKILL.md
# Claude
Claude Code is an independent agent on PATH (`claude`), sharing this working
tree and already authenticated. Use it as a second opinion or delegated worker,
not as ground truth: verify its claims, own any changes, and keep its task
contract narrow.
## Defaults
Use `claude -p --model opus --effort high` unless the user or task calls for a
different model or thinking level. Keep `opus` as an alias so Claude Code
resolves the current Opus release; do not pin a dated model ID in this skill.
- **Model:** prefer aliases such as `opus`, `sonnet`, or `fable`, which followclose-spec
When your agent uses it
When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).
What it loads into context
Frontmatter
133 tokensAlways available to the agent
SKILL.md
1,512 tokensWhen the skill is activated
Reference documents
4,534 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Smell Test
- Done
Files
SKILL.mdcore6,512 bytesSKILL.mdcore6,512 bytesSKILL.mdcore6,512 bytes../review/SKILL.mddoc1,892 bytes../write-spec/SKILL.mddoc18,672 bytes
Read SKILL.md
# Close Spec
A spec is a **build plan** while you're building and a **rationale record**
once you've shipped. Closing flips it from one to the other. The plan was a
ladder of slices and predictions; the record is the layer of meaning the code
can't hold — why this exists, what it must never break, what you tried that
failed. The code is the single source of truth for *how*; the closed spec is
the source of truth for *why*, and a map into the code.
Do not summarize the implementation. Anyone can read the code. If a paragraph
restates what a function does, cut it and point at the function instead.
## Workflow
code-review
When your agent uses it
Review changed code for naming, stale references, unnecessary complexity, and comment quality. Use after completing implementation work, before committing, or when the user asks to review or audit code.
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
4,948 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Names must reflect current reality
- 2. No stale references
- 3. Simplify detection and guard logic
- 4. Comments document WHY, not WHAT HAPPENED
- 5. Separate install-time from runtime
- 6. No intermediary artifacts
- 7. Tighten guarantees after changes
- 8. When changes are tangled, start clean
- 9. Tests must verify actual values, not just collection sizes
- 10. No thin wrappers or re-export-only modules
- 11. Extract only around real ownership boundaries
- 12. Decouple tests from implementation — drive the system end-to-end
- 13. A failing check can be a toolchain defect, not a code defect
- 14. Identity comes from auth, never from the caller
- 15. Public API actions are thin auth + dispatch, not inlined business logic
- 16. Public endpoints ship at minimum scope
- 17. Reuse existing types — derive, don't redeclare
- 18. Filter at the index, never `take()` + post-filter
- 19. Never `.collect()` — bound the read with `.take(N)`
- 20. Don't remap rows just to rename or default fields
- 21. Internal APIs carry no version or compat machinery
- 22. Things that must agree need one owner
- 23. Don't hoist a single-use value into a named const unless it earns the name
- 24. Batch loops isolate per-item failures — one bad item never starves the rest
- 25. Renaming what users see means sweeping what tests see
- 26. Leave the code better than you found it — a tidy diff is not worth an untidy repo
- Your task
Files
SKILL.mdcore22,327 bytesSKILL.mdcore22,327 bytesSKILL.mdcore22,327 bytes
Read SKILL.md
# Code Review
Review the diff or specified files against these principles.
## 1. Names must reflect current reality
- Variable and function names should describe what they ARE, not what they used to be.
- If the underlying mechanism changed (e.g. FUSE → NFS), all related names must update.
- Ask: would a new reader be confused by this name?
## 2. No stale references
- After refactoring, grep for references to the old approach — dead detection logic, abandoned feature flags, comments mentioning removed code.
- If something was tried and reverted, remove ALL traces. The codebase should look like the current approach was always the plan.codex
When your agent uses it
Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second opinion after completing a substantive change, before presenting it as done or committing; (2) delegate a well-defined implementation task via `codex exec`, ONLY when the user explicitly asks for Codex to do it. Also covers how to prompt Codex.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
2,459 tokensWhen the skill is activated
Reference documents
2,242 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- If `codex` is not installed
- Prompting Codex
- Review — proactive
- Implementation — explicit ask only
- Exec liveness — a hang looks like work
- Rules
Files
SKILL.mdcore10,197 bytesSKILL.mdcore10,197 bytes../../visual/screenshot-critique/SKILL.mddoc10,096 bytes
Read SKILL.md
# Codex
Codex is an independent agent on PATH (`codex` — invoke as `command codex` if
a shell alias shadows it), sharing this working tree and already authenticated. It is a second opinion, not ground truth: verify what it
reports, own what it changes. It reads the same skills your repo carries.
Leave Codex's model at its CLI default unless the user asks for a specific
one. The default follows the current Codex release; do not pin a dated model
ID in this skill. If an explicit override is needed, verify it is current and
pass the requested model with `-m <model>`.
## If `codex` is not installed
When `codex` is missing from PATH, offer to install it — **ask the user foreli5
When your agent uses it
Explain a technical spec or proposed change in plain language: what problem it solves, how the solution works, and every schema change.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
687 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The Register
- Workflow
- Output
- Rules
Files
SKILL.mdcore3,242 bytes
Read SKILL.md
# ELI5
Turn the referenced spec or change into an accurate mental model for a technical
reader who does not live in the code. Plain language, full precision: simplify
the telling, never the claims.
## The Register
Other skills point here when their output must be readable by someone who
didn't live the work. The reader is technical — pseudocode and precise claims
land fine — but they have read none of the code and none of the session's
messages: no diff, no transcript, no labels the work invented along the way.
Writing ELI5 means:
explore-unknowns
When your agent uses it
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the codebase or domain is unfamiliar, the user will "know it when they see it", a reference implementation must be understood before porting, mid-build deviations from the plan need capturing, or a finished change needs buy-in or verified understanding before merge. Pairs with [write-spec](../write-spec/SKILL.md) — walk the quadrants to burn off fog before slicing, and feed the finished map into the spec.
What it loads into context
Frontmatter
165 tokensAlways available to the agent
SKILL.md
1,490 tokensWhen the skill is activated
Reference documents
6,355 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The Quadrant Walk
- Preference Checkpoint — Offer to Answer on Their Behalf
- Rules
Files
SKILL.mdcore6,845 bytesreferences/after-the-walk.mddoc1,007 bytesreferences/stage-1-known-knowns.mddoc1,513 bytesreferences/stage-2-known-unknowns.mddoc2,194 bytesreferences/stage-3-unknown-knowns.mddoc2,001 bytesreferences/stage-4-unknown-unknowns.mddoc1,846 bytesreferences/stage-5-hand-over-the-map.mddoc1,635 bytes../write-spec/SKILL.mddoc18,672 bytes
Read SKILL.md
# Explore Unknowns
The map is not the territory. The prompt, the plan, and the context window are
the map; the codebase, the domain, and the user's actual intent are the
territory. The gap between them is the unknowns — and an unknown found before
code is written costs minutes, while the same unknown found three PRs later
costs the three PRs.
This skill is a guided conversation: the **quadrant walk**. Together with the
user you fill in a four-quadrant map of the task, one quadrant per stage, and
the user walks away holding the completed map. The map is the deliverable;
implementation is a different task that starts only after the map is handed
over.
handoff-spec
When your agent uses it
Hand a spec that is mid-implementation to another machine or another agent.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
319 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,393 bytes
Read SKILL.md
# Handoff Spec
I'm moving this spec's work to another machine or another agent. The next
session starts **cold**: it has the repository and nothing else. It has none
of this conversation, none of this machine's files and none of your memory.
Leave the spec so that session can carry on as if it had been here.
Collect what this session knows and the spec doesn't yet say, from the
discussion and from the work itself, and put it in the spec:
- what is done, what is half-done and exactly where it stopped, and what is
next;
- what I decided or corrected along the way, and how I want the work done;
- calls you made where I was silent, and anything still waiting on me;implement-spec
When your agent uses it
Implement an existing spec through committed passes. Use for long or multi-pass specs that need maintenance checkpoints to periodically clean code, handoffs, priorities, and plan bloat before drift accumulates.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
3,547 tokensWhen the skill is activated
Reference documents
10,596 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Preserve the winner
- Rules
- Done
Files
../audit-decisions/SKILL.mddoc10,232 bytes../close-spec/SKILL.mddoc6,512 bytesSKILL.mdcore15,880 bytes../refactor-clean/SKILL.mddoc12,505 bytes../review/SKILL.mddoc1,892 bytes../write-docs/SKILL.mddoc3,739 bytes../../visual/preview-shots/SKILL.mddoc2,046 bytes../../visual/screenshot-critique/SKILL.mddoc10,096 bytes
Read SKILL.md
# Implement Spec
Build the active spec to completion, one reviewable pass at a time. The spec is
the implementation plan; user constraints and accepted experimental evidence
remain binding when the architecture changes.
A pass (usually one slice) is a **commit checkpoint, not a stopping point.** The
job is the whole spec — every slice, every global TODO — not the first green
commit. Finishing a pass means starting the next one, not handing back to the
user. Only stop when the spec is fully implemented (or a genuine blocker needs a
decision only the user can make).
**Work in parallel wherever the graph allows.** Do not walk the ladder one slice
at a time when slices are independent. Read the spec's dependency graph as aimplement-spec-with-codex
When your agent uses it
Run [implement-spec](../implement-spec/SKILL.md) with Codex doing the implementation passes while you orchestrate, integrate, and review. Use when the user asks to implement a spec with Codex, or to run implement-spec with Codex as the implementer.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
494 tokensWhen the skill is activated
Reference documents
6,006 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Role split
- Rules
Files
../codex/SKILL.mddoc10,197 bytesSKILL.mdcore2,181 bytes../implement-spec/SKILL.mddoc15,880 bytes
Read SKILL.md
# Implement Spec with Codex
Run [implement-spec](../implement-spec/SKILL.md) exactly — same loop, same
gates, same maintenance checkpoints — but Codex writes the code. Invoking this
skill IS the explicit ask that authorizes `codex exec` delegation under the
[codex](../codex/SKILL.md) skill.
## Role split
- **Codex implements — whenever possible.** Default every implementation pass
to a `codex exec`, sliced sharp and prompted per the codex skill (prompt
blocks, sandbox choice, exec liveness). Run independent slices as concurrent
execs in separate worktrees, exactly where implement-spec would fan out
subagents.implement-spec-with-goal
When your agent uses it
Implement a spec using the harness's goal feature.
What it loads into context
Frontmatter
26 tokensAlways available to the agent
SKILL.md
64 tokensWhen the skill is activated
Reference documents
3,547 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore293 bytes../implement-spec/SKILL.mddoc15,880 bytes
Read SKILL.md
# Implement Spec with Goal
Use the harness's goal feature to implement the provided spec to completion.
Read and follow [implement-spec](../implement-spec/SKILL.md).marketing-pages
When your agent uses it
Best-practice rulebook for a marketing site's pages, organized by page class — campaign landers, product pages, programmatic SEO trees, editorial. Use when writing or updating a landing/marketing page, wiring a campaign lander to an attribution identifier, changing site-wide nav/footer links, touching sitemap/robots/agent-readable surfaces, or auditing a public site's indexing, reachability, and conversion setup.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,402 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Page classes
- Campaign lander rules
- Indexed page rules
- SEO rules
- Visual coverage rules
- Audit sweeps
Files
SKILL.mdcore6,299 bytesSKILL.mdcore6,299 bytesSKILL.mdcore6,299 bytes
Read SKILL.md
# Marketing Pages
A rulebook, not a workflow: every rule below is simultaneously a constraint to
build against and a check to audit against. Classify the page first — every
public page belongs to exactly one **page class**, and the class decides its
indexing, linking, chrome, and wiring.
## Page classes
| Class | Indexing | Reachability | Chrome |
|---|---|---|---|
| **Campaign lander** | `noindex, follow`; never in a sitemap | never linked from nav/footer | minimal: logo + ONE CTA, legal-only footer, no site nav |
| **Product page** | indexed | nav Product section and/or footer | full chrome |
| **SEO tree page** (programmatic: per-persona, per-industry, per-competitor) | indexed | footer link grid + hub pages | full chrome |port-features
When your agent uses it
Port a feature from an existing repository by copying its actual code and editing the copy, so its bug fixes and behavioral nuances survive. Use when asked to copy or port an existing feature (especially an exact copy), when moving one into a different framework or host, or when a previous reimplementation missed upstream behavior.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
383 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,785 bytesSKILL.mdcore1,785 bytes
Read SKILL.md
# Port Features
Upstream code is the spec. Every guard, ordering, timeout, and odd branch in it
may be a bug fix someone already paid for. A rewrite from your understanding of
the feature drops the ones you didn't notice.
1. **Start from the code.** Get a local checkout of upstream with its history,
pin the exact commit, and read the feature's real files, not a screenshot,
summary, or fetched snippet. Follow imports and callers until you know which
files make up the feature.
2. **Read the history.** Read path-scoped `git log`, following renames, for
those files, and read the fixes. Before changing or dropping anything that
looks unnecessary, find out from history why it is there.
3. **Copy, then edit.** Copy the exact files, with their tests, into theratchet-files
When your agent uses it
Ratchet source file size so every file stays small enough for an agent to read whole: find every file over a token budget, split oversized files by concept, and set up the pre-commit ratchet that stops them from growing. Use when a commit is blocked because a file is over the size budget, when asked to find or split oversized/long/god files, when a file you need to change is too large to read in one pass, or when asked to add a file-size limit or hook to a repository or repair commit-hook coverage across worktrees.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
1,906 tokensWhen the skill is activated
Reference documents
2,717 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Splitting
- Setting up the ratchet
Scripts executed separately
scripts/check-file-size.mjsscripts/install-git-hooks.mjsscripts/install-git-hooks.test.mjs
Files
SKILL.mdcore8,112 bytesSKILL.mdcore8,112 bytesSKILL.mdcore8,112 bytesSKILL.mdcore8,112 bytesscripts/check-file-size.mjsruns8,920 bytesscripts/install-git-hooks.mjsruns2,058 bytesscripts/install-git-hooks.test.mjsruns6,801 bytes../refactor-clean/SKILL.mddoc12,505 bytes
Read SKILL.md
# Ratchet Files
A source file is over budget when it is past what an agent can read in one
pass (8,000 tokens, counted as bytes / 4, unless the repository sets
another). [`scripts/check-file-size.mjs`](scripts/check-file-size.mjs) owns
what counts as source, the budget, the ratchet, and the split rules; run it
with `--help` before anything else.
## Splitting
1. Run the script with `--all` from the repository root, passing the
repository's `--max-tokens` if its hook sets one. Its list is the backlog.
2. Pick the files to split: the one blocking the work in front of you, or
with no blocker, the largest ones a change is about to touch.refactor-clean
When your agent uses it
Refactor cleanly instead of layering sediment. Use for rename requests, stale or misleading names, legacy leftovers, changed scope, or when a change reveals duplicated concepts, local adapters, obsolete owners, redundant inputs or guards, compatibility wrappers, parallel abstractions, an over-large module that has accreted many responsibilities, or "just tack this on" pressure in any code area.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
2,717 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Rules
Files
SKILL.mdcore12,505 bytes
Read SKILL.md
# Clean Refactoring
Replace the old shape with the simpler shape the codebase would want if it were
designed today. Refactoring is not adding a compatibility layer beside the problem;
it is moving ownership until every concept has exactly one clear home. That cuts
both ways: merging N duplicated owners into one, and splitting one over-loaded
module into the several owners it was hiding.
## Workflow
1. Sweep names in every touched path, even when no structural refactor is needed.
Ask whether each name describes the concept's current scope. Rename misleading
files, symbols, imported bindings and shared exports immediately; update every
consumer, test, doc and agent instruction in the same pass. Keep scenario namesretro
When your agent uses it
Conduct a retrospective on a coding session.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
966 tokensWhen the skill is activated
Reference documents
2,473 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Steps
- Reference
Files
../../authoring/write-skills/SKILL.mddoc10,877 bytesLICENSEasset1,068 bytesSKILL.mdcore4,405 bytesagents/openai.yamlasset146 bytes
Read SKILL.md
The user has asked for a **retrospective**. You are suggesting improvements to the coding agent's **environment** to improve future runs.
## Steps
1. Read [write-skills](../../authoring/write-skills/SKILL.md) for the writing style guide.
2. Read the primary sources for the session the user specifies. This may mean searching through session logs on this machine. If the user doesn't specify a session, default to the current one.
3. Look for candidates for improvement in these categories.
- **Navigation**: how easy was it for the agent to find the right files? Are there hidden dependencies between files? Would a **navigation pointer** make it easier? _Use when_ the session took a long time to find a piece of information.
- **Automated checks**: are there automated checks that could catch errors the agent made? Linting, typing, tests, filesystem linters? Read the repo's own check command first (its `package.json`/build-tool `lint`/`check` scripts, its CI workflow), so a check that already exists but sits unwired or silently broken is the finding, not a reinvention. A repo with no **guardrail** (no pre-commit hook and no CI job running its lint/typecheck/test command) is itself a finding: an un-linted repo is a standing missed opportunity, not a neutral default. _Use when_ the agent made a mistake an automated check could have caught, or the repo has no guardrail at all.
- **Coding standards**: should the **reviewer agent** be given a new rule to enforce? Should an existing rule be removed or clarified? Classify the violation first: a **mechanical** one (a fixed syntactic pattern, a banned API, an import shape, a file-location rule) gets a deterministic check, full stop: a custom rule in the repo's own linter, a new pre-commit hook, or a new CI job, whichever the repo's language and existing guardrail make cheapest. Default to building the check over writing the rule. Reserve `CODING_STANDARDS.md` for genuine **judgement calls** (cross-file consistency, "matches the surrounding style," anything no guardrail could ever substitute for). _Use when_ the reviewer agent failed to catch a mistake.
- **Global AGENTS.md**: are there any steering instructions that should be moved to coding standards (or automated checks) instead? _Use when_ the AGENTS.md file is particularly large - in the repo OR the user's global scope.review
When your agent uses it
Closeout pass on a finished substantive change — sequence refactor-clean (shape), code-review (diff), and write-docs (docs) so all three run, in the order where each feeds the next. Use after implementing a slice or feature and before calling it done or committing; when the user asks for a final review, a cleanup-and-document pass, or to "review everything." For a diff-only audit, reach code-review directly.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
454 tokensWhen the skill is activated
Reference documents
8,543 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Rules
Files
../code-review/SKILL.mddoc22,327 bytes../refactor-clean/SKILL.mddoc12,505 bytesSKILL.mdcore1,892 bytes../write-docs/SKILL.mddoc3,739 bytes
Read SKILL.md
# Review
A finished change earns "done" only after three lenses pass: its **shape**, its
**diff**, and its **docs**. Each has a specialist skill. This skill owns only
what they can't — the order they run in, the loop between them, and one verdict.
## Workflow
1. **Scope.** Fix the diff under review and confirm it's substantive; skip the
whole pass for trivial edits.
2. **Shape — [refactor-clean](../refactor-clean/SKILL.md).** Run it first, while
restructuring is cheap and before you audit a diff that's about to move.
3. **Diff — [code-review](../code-review/SKILL.md).** Audit the settled shape. A
finding that forces a structural change sends you back to step 2, not onward.write-docs
When your agent uses it
Write and edit project docs (README/markdown) as a glossary of principles, not a mirror of the code. Use when creating or revising a README; when a doc enumerates exact scenes, scenarios, helpers, class ids, file lists, or command/flag matrices the code already holds; when trimming narrative or changelog out of a doc; or when deduplicating overlapping docs and wiring a root doc to its sub-docs.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
878 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Keep vs shed
- Point, don't transcribe
- One home per fact
- Link the tree, downward
- Edit pass
Files
SKILL.mdcore3,739 bytesSKILL.mdcore3,739 bytes
Read SKILL.md
# Write Docs
A doc is a **glossary**: it names the moving parts, says why each exists, and
carries the principles a reader can't derive by grepping. The code is the source
of truth for *what exists right now* — the doc must never race it. Before writing
any line, ask the one question that governs this skill: **could the reader get
this faster and more reliably by reading the code?** If yes, point them at the
code instead of copying it in.
## Keep vs shed
Keep — a reader cannot grep their way to these:
- The WHY: why a thing exists, the principle behind a split, the taxonomy filewrite-spec
When your agent uses it
Break large features into independently verifiable, human-reviewable slices under a feature directory in specs/. Use for risky or multi-step feature work that needs upfront questioning, API seams, browser-playable checkpoints, HTML visualizations, screenshot gates, staged implementation plans, recursive fog-of-war reslicing, or proactive research into reference implementations/best practices before slicing. Pairs with your project's verification harness and screenshot gates (the browser checkpoints), [refactor-clean](../refactor-clean/SKILL.md) (review the materialized spec so the plan describes one-owner architecture, not the feature bolted on), [screenshot-critique](../../visual/screenshot-critique/SKILL.md) and [compare-screenshots](../../visual/compare-screenshots/SKILL.md) (the visual gates), and a code-review pass (audit each slice before it lands).
What it loads into context
Frontmatter
183 tokensAlways available to the agent
SKILL.md
4,080 tokensWhen the skill is activated
Reference documents
11,666 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- First Principles
- Workflow
- From research to implementation
- Plan Folder
- Slice File Contract
- README Handoff Prompt
- Done
Files
../audit-decisions/SKILL.mddoc10,232 bytes../close-spec/SKILL.mddoc6,512 bytes../refactor-clean/SKILL.mddoc12,505 bytesSKILL.mdcore18,672 bytesSKILL.mdcore18,672 bytes../../visual/compare-screenshots/SKILL.mddoc10,672 bytes../../visual/preview-shots/SKILL.mddoc2,046 bytes../../visual/screenshot-critique/SKILL.mddoc10,096 bytes
Read SKILL.md
# Write Spec
Turn a large feature into a ladder of small contracts. Each rung should be
understandable to the human, testable by an agent, and useful before the
whole feature is done.
## First Principles
1. **Grill before planning.** Ask one question at a time until you know the
desired outcome, non-goals, review surface, sacred contracts, missing
assets, and first useful playable checkpoint. Give your recommended
answer with each question so the user can accept, reject, or edit it.
Inspect the repo instead of asking questions the code can answer.
Close the interview by asking whether the plan must carry backwardwrite-tests
When your agent uses it
Write tests that pin real behavior instead of implementation details, config values, or lucky samples. Use when adding tests for new behavior, writing a regression test, fixing a brittle or flaky test, reviewing a test diff, or when a test breaks after a refactor or config change that didn't change behavior.
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
2,284 tokensWhen the skill is activated
Reference documents
1,837 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow: tracer bullets, not a batch
- What to assert
- Seams and mocks
- Control variables and probes
- Tests run on someone's live machine
- Prove the test can fail
- When a test goes red after a change
- Review checklist
Files
../audit-tests/SKILL.mddoc9,423 bytesSKILL.mdcore10,174 bytes
Read SKILL.md
# Write Tests
A good test fails **only** when real behavior breaks, and passes through every
refactor or config change that preserves it. Most bad tests fail the opposite
way: red on harmless changes, green while the real path is broken. Every rule
below serves that one goal.
Default to end-to-end or system-level tests for regression coverage; use a unit test only for specific, complex business logic when fast feedback will materially speed development.
For deciding whether coverage adds independent proof, where it belongs, or
which existing tests can go, use [audit-tests](../audit-tests/SKILL.md).
## Workflow: tracer bullets, not a batch
cinematic-shot
When your agent uses it
Shoot software UI like a film. A sequence of hero shots, each a steep, oblique, extreme close-up of the interface floating in black, with a razor-thin focal plane, a slow motivated camera drift, and UI that acts on its own, hard-cut on the action, ending on one line of copy and a still logo. Use when asked for a launch video, product film, feature trailer, teaser, promo clip, hero shot, or any "cinematic" footage of an app or UI. This skill covers camera, framing, light, and edit. It is stack-agnostic.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
3,609 tokensWhen the skill is activated
Reference documents
7,223 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The taste
- 1. Find the story before the shots
- 2. Write the shot list
- 3. Light and grade: a black void
- 4. Motion inside the shot
- 5. Ending: copy, then a still logo
- 6. Sound
- Don't
- 7. Verify like a DP
Files
SKILL.mdcore14,547 bytesreferences/landing-page-promo.mddoc7,116 bytesreferences/look.mddoc12,641 bytesreferences/shot-list-example.mddoc5,006 bytes
Read SKILL.md
# Cinematic shot
You are the director and the DP, not the motion designer. The film is a sequence of **hero shots**. Each one looks at a real piece of the product's UI from a steep, low angle, so close that the focal plane covers only a line or two of text and everything else melts into black. The camera drifts slowly toward where the next thing will happen. The UI does the work by itself: things get typed, streamed, selected, and written while we watch. Nothing explains itself with captions.
This skill is about camera, framing, light, and the edit. Build the film with any rendering stack. Whatever you choose, make every frame a pure function of time, so the film renders deterministically and can take motion blur.
Read [references/look.md](references/look.md) for exact camera, depth-of-field, light, reveal, and type recipes. Read [references/shot-list-example.md](references/shot-list-example.md) for a full example of the shot grammar.
For a ~15 second promo video made in code from a landing page (a continuous 3D fly-over of the page ending on a title card with the brand, logo mark, a two-part closing line, and an optional track), follow [references/landing-page-promo.md](references/landing-page-promo.md).
## The taste
A black void. The product floats in it like a dark slab, tilted away from the camera, lit by a soft pool that follows whatever matters and lets everything else fall into black. The camera is low and close, looking *along* the UI rather than at it, so lines of text run diagonally across the frame and shrink into the distance. The focal plane is a thin band: one control, one line of typing, one row of a list is sharp, and the rest is soft bokeh. The camera never stops drifting and never moves fast. Shots are long enough to watch something happen. The only colour is the product's own. Restraint everywhere else.
isometric-motion
When your agent uses it
Build animations and interactive elements (explainers, figures, hero visuals, step-through walkthroughs) in the crafted isometric "Anatomy" style, with many small precise solid parts, four-tone shading, correct painter's order, a framed card with title, hint and live readout, and calm eased motion. Works for physical machines and for abstract concepts (e.g. how an LLM picks its next token), as SVG/HTML or React/Next.js, with optional in-perspective WebGL shaders. Use this whenever someone wants an isometric animation, interactive element, explanatory diagram or figure for docs, a blog post, a landing page or an article, a "Linear-style" or "premium" technical drawing, or an SVG that shows how a system, algorithm or component works, even if they never say "isometric".
What it loads into context
Frontmatter
179 tokensAlways available to the agent
SKILL.md
8,341 tokensWhen the skill is activated
Reference documents
81,120 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The one idea that matters
- Workflow
- Setup
- Craft rules (short form)
- WebGL inside the drawing
- 3D: figures that turn (beta)
- References
Scripts executed separately
examples/arcade-cabinet/build.mjsexamples/arcade-cabinet/live.jsexamples/arcade-cabinet/parts.mjsexamples/arcade-cabinet/screen.mjsexamples/desk-computer/build.mjsexamples/dial-indicator/build.mjsexamples/next-token/build.mjsexamples/next-token/model.mjsexamples/raptor-engine/build.mjsexamples/raptor-engine/live.jsexamples/ripple-tank/build.mjsexamples/ripple-tank/live.jsexamples/ripple-tank/model.mjsexamples/spot-plate/art.tsxexamples/spot-plate/drops.tsexamples/spot-plate/fan.tsexamples/spot-plate/figure.tsxexamples/spot-plate/geometry.tsexamples/spot-plate/live.tsxexamples/spot-plate/rig.tsexamples/test-rig/art.tsxexamples/test-rig/figure.tsxexamples/test-rig/geometry.tsexamples/test-rig/live.tsxexamples/test-rig/pose.tsexamples/test-rig/rig.tsexamples/test-rig/view.tsexamples/turning-dial/build.mjsexamples/turning-dial/live.jsexamples/turning-dial/stress.mjskit/audit.mjskit/canvas-painter.mjskit/gl-shared.mjskit/gl.mjskit/iso-kit.mjskit/iso-kit.tskit/lathe.mjskit/react/draw.tsxkit/react/live.tsxkit/tube.mjskit/turn-audit.mjskit/turn-build.mjskit/turn-fixed.mjskit/turn.mjsscripts/audit-affine-bounds.test.mjsscripts/audit-cache.test.mjsscripts/audit-clearance-envelope.test.mjsscripts/audit-empty-clipping.test.mjsscripts/audit-order-convergence.test.mjsscripts/audit-path-origin.test.mjsscripts/audit-profile.test.mjsscripts/audit-projection.test.mjsscripts/audit-slide-clearance.test.mjsscripts/audit-svg-attributes.test.mjsscripts/audit-taper.test.mjsscripts/capture-current-geometry.test.mjsscripts/capture-selector.test.mjsscripts/capture.mjsscripts/capture.test.mjsscripts/chrome-port.mjsscripts/chrome-startup.test.mjsscripts/drive-actions.test.mjsscripts/drive-async-until.test.mjsscripts/drive-turn-controller.test.mjsscripts/drive.mjsscripts/drive.test.mjsscripts/enter-key.test.mjsscripts/fidelity-cut.test.mjsscripts/fidelity-tube-coverage.test.mjsscripts/fingerprint.mjsscripts/inline-kit.mjsscripts/line-ends.mjsscripts/lines-arcs.test.mjsscripts/lines-bezier.test.mjsscripts/lines-round.test.mjsscripts/lines-rounded-rect.test.mjsscripts/lines.mjsscripts/lines.test.mjsscripts/navigation.test.mjsscripts/orbit-sampling.test.mjsscripts/react-dots-opacity.test.mjsscripts/react-readout-first-write.test.mjsscripts/react-readout-target.test.mjsscripts/react-solid-seamless.test.mjsscripts/react-visibility-target.test.mjsscripts/turn-bench.mjsscripts/turn-check.mjsscripts/turn-fidelity.mjsscripts/turn-group-reference.test.mjsscripts/turn-split-owner.test.mjs
Files
LICENSEasset1,061 bytesSKILL.mdcore33,605 bytesSKILL.mdcore33,605 bytesSKILL.mdcore33,605 bytesSKILL.mdcore33,605 bytesSKILL.mdcore33,605 bytesSKILL.mdcore33,605 bytesexamples/arcade-cabinet/arcade-cabinet-light.htmlasset1,007,953 bytesexamples/arcade-cabinet/arcade-cabinet.cssasset3,221 bytesexamples/arcade-cabinet/arcade-cabinet.htmlasset1,007,952 bytesexamples/arcade-cabinet/build.mjsruns51,493 bytesexamples/arcade-cabinet/live.jsruns21,286 bytesexamples/arcade-cabinet/parts.mjsruns4,296 bytesexamples/arcade-cabinet/screen.mjsruns6,701 bytesexamples/desk-computer/build.mjsruns23,023 bytesexamples/desk-computer/desk-computer-light.htmlasset237,394 bytesexamples/desk-computer/desk-computer.htmlasset237,393 bytesexamples/dial-indicator/build.mjsruns14,973 bytesexamples/dial-indicator/dial-indicator-light.htmlasset136,489 bytesexamples/dial-indicator/dial-indicator.htmlasset136,488 bytesexamples/next-token/build.mjsruns36,308 bytesexamples/next-token/model.mjsruns1,783 bytesexamples/next-token/next-token-light.htmlasset231,699 bytesexamples/next-token/next-token.htmlasset231,698 bytesexamples/raptor-engine/build.mjsruns70,705 bytesexamples/raptor-engine/live.jsruns30,752 bytesexamples/raptor-engine/raptor-engine-light.htmlasset1,610,583 bytesexamples/raptor-engine/raptor-engine.htmlasset1,610,582 bytesexamples/raptor-engine/raptor.cssasset6,792 bytesexamples/ripple-tank/build.mjsruns32,062 bytesexamples/ripple-tank/live.jsruns21,720 bytesexamples/ripple-tank/model.mjsruns5,004 bytesexamples/ripple-tank/ripple-tank-light.htmlasset505,478 bytesexamples/ripple-tank/ripple-tank.htmlasset505,477 bytesexamples/ripple-tank/ripple.cssasset1,675 bytesexamples/spot-plate/art.tsxruns4,491 bytesexamples/spot-plate/drops.tsruns19,131 bytesexamples/spot-plate/fan.tsruns2,715 bytesexamples/spot-plate/figure.tsxruns1,078 bytesexamples/spot-plate/geometry.tsruns10,962 bytesexamples/spot-plate/live.tsxruns11,718 bytesexamples/spot-plate/rig.tsruns8,160 bytesexamples/spot-plate/spot-plate.cssasset1,518 bytesexamples/test-rig/art.tsxruns7,372 bytesexamples/test-rig/figure.tsxruns850 bytesexamples/test-rig/geometry.tsruns13,085 bytesexamples/test-rig/live.tsxruns17,463 bytesexamples/test-rig/pose.tsruns3,894 bytesexamples/test-rig/rig.tsruns5,604 bytesexamples/test-rig/stretch.cssasset1,210 bytesexamples/test-rig/view.tsruns3,116 bytesexamples/turning-dial/build.mjsruns32,098 bytesexamples/turning-dial/dial.cssasset509 bytesexamples/turning-dial/live.jsruns12,523 bytesexamples/turning-dial/stress.mjsruns19,414 bytesexamples/turning-dial/turning-dial-light.htmlasset673,894 bytesexamples/turning-dial/turning-dial-verify-light.htmlasset701,752 bytesexamples/turning-dial/turning-dial.htmlasset673,893 bytesexamples/turning-dial/turning-stress-light.htmlasset1,228,774 byteskit/audit.mjsruns92,696 byteskit/canvas-painter.mjsruns27,535 byteskit/gl-shared.mjsruns8,863 byteskit/gl.mjsruns8,763 byteskit/iso-kit.mjsruns35,175 byteskit/iso-kit.tsruns38,631 byteskit/iso.cssasset7,698 byteskit/lathe.mjsruns48,028 byteskit/react/draw.tsxruns6,602 byteskit/react/live.tsxruns4,359 byteskit/tube.mjsruns14,230 byteskit/turn-audit.mjsruns57,157 byteskit/turn-build.mjsruns65,265 byteskit/turn-fixed.mjsruns147,055 byteskit/turn.mjsruns139,815 bytesreferences/3d.mddoc44,644 bytesreferences/craft.mddoc50,299 bytesreferences/kit.mddoc67,873 bytesreferences/motion.mddoc22,611 bytesreferences/react.mddoc3,614 bytesreferences/verify.mddoc43,574 bytesreferences/walkthrough.mddoc5,276 bytesreferences/webgl.mddoc61,104 bytesscripts/audit-affine-bounds.test.mjsruns4,175 bytesscripts/audit-cache.test.mjsruns1,603 bytesscripts/audit-clearance-envelope.test.mjsruns2,407 bytesscripts/audit-empty-clipping.test.mjsruns3,936 bytesscripts/audit-order-convergence.test.mjsruns2,875 bytesscripts/audit-path-origin.test.mjsruns1,594 bytesscripts/audit-profile.test.mjsruns2,171 bytesscripts/audit-projection.test.mjsruns1,934 bytesscripts/audit-slide-clearance.test.mjsruns2,875 bytesscripts/audit-svg-attributes.test.mjsruns3,484 bytesscripts/audit-taper.test.mjsruns1,267 bytesscripts/capture-current-geometry.test.mjsruns5,109 bytesscripts/capture-selector.test.mjsruns7,665 bytesscripts/capture.mjsruns13,283 bytesscripts/capture.test.mjsruns2,023 bytesscripts/chrome-port.mjsruns1,083 bytesscripts/chrome-startup.test.mjsruns1,838 bytesscripts/drive-actions.test.mjsruns1,822 bytesscripts/drive-async-until.test.mjsruns2,743 bytesscripts/drive-turn-controller.test.mjsruns2,702 bytesscripts/drive.mjsruns22,086 bytesscripts/drive.test.mjsruns3,690 bytesscripts/enter-key.test.mjsruns2,560 bytesscripts/fidelity-cut.test.mjsruns3,702 bytesscripts/fidelity-tube-coverage.test.mjsruns3,223 bytesscripts/fingerprint.mjsruns1,241 bytesscripts/inline-kit.mjsruns648 bytesscripts/line-ends.mjsruns15,143 bytesscripts/lines-arcs.test.mjsruns2,059 bytesscripts/lines-bezier.test.mjsruns1,769 bytesscripts/lines-round.test.mjsruns2,458 bytesscripts/lines-rounded-rect.test.mjsruns2,527 bytesscripts/lines.mjsruns1,700 bytesscripts/lines.test.mjsruns1,537 bytesscripts/navigation.test.mjsruns2,255 bytesscripts/orbit-sampling.test.mjsruns2,810 bytesscripts/react-dots-opacity.test.mjsruns2,817 bytesscripts/react-readout-first-write.test.mjsruns3,846 bytesscripts/react-readout-target.test.mjsruns4,657 bytesscripts/react-solid-seamless.test.mjsruns2,752 bytesscripts/react-visibility-target.test.mjsruns3,844 bytesscripts/turn-bench.mjsruns3,863 bytesscripts/turn-check.mjsruns37,440 bytesscripts/turn-fidelity.mjsruns20,164 bytesscripts/turn-group-reference.test.mjsruns2,174 bytesscripts/turn-split-owner.test.mjsruns3,411 bytes
Read SKILL.md
# Isometric Motion
> Copied from [wheresryan22/anatomy](https://github.com/wheresryan22/anatomy) (MIT, see `LICENSE`) and repurposed for animations and interactive elements in the same style.
This skill makes figures like a small instrument on a bench: a heavy base on feet, rails with tick rulers, a carriage on bushings, knurled knobs, coil springs, a dial gauge whose needle moves, screws as tiny dots. The reader understands the idea because they recognise the machine. Every number the figure shows comes from the same model that moves its parts.
Nine complete examples ship with the skill. Open the closest one before you start. Each framework-free example is built with `node examples/<name>/build.mjs`, which writes a standalone HTML page next to the script; add `--light` for the light theme.
- `examples/dial-indicator/` is the smallest: a dial gauge on a stand, about 300 lines in all.
- `examples/desk-computer/` is framework-free SVG: a desk computer with a keyboard you can type on. The typed line appears on a CRT screen drawn in the plane of the case front, and the picture collapses to a line and a dot when you switch it off. It has about 85 solids and 850 paths.
- `examples/arcade-cabinet/` is an upright arcade cabinet with its side panel off, a Hero of about 240 solids and 15 cables. A quarter flies into the slot, rolls down the coin chute at the speed a rolling disc reaches on a 30° slope, trips the coin-switch wire and drops into the cash box; the switch's pulse runs chunk by chunk along its cable to the board, and the CRT warms up, self-tests and runs an attract mode drawn in the plane of the tilted monitor. The stick tilts and closes a microswitch under the panel. It shows how to place a camera so a cutaway's mechanism stays in view, a concave board drawn as a prism along any axis, moving parts rebuilt in the page from the same module the build uses, and live coins and a wire drawn in reserved slots of the settled order. `node build.mjs --audit` proves the geometry.
- `examples/raptor-engine/` is a rocket engine hanging in a test stand. Its round parts come from `kit/lathe.mjs` and its pipes and harness from `kit/tube.mjs`. It comes apart into 11 assemblies with staggered springs and per-frame depth re-sorting. Every part records its true shape, and `node build.mjs --audit` (`kit/audit.mjs`) proves, at rest, apart and in every replayed frame of the explode, that nothing passes through anything, that every end sits on a real mount, that no bend pinches, folds or lands on another line, that no curved profile's slope wobbles, and that every overlap is drawn in depth order. A WebGL plume, shock, splash and steam render between the back and front SVG. It is the reference for dense pipework, smooth shading and fades.
- `examples/ripple-tank/` is a school ripple tank on tall legs over a paper screen, seen from 44° up. Two WebGL layers (lamp light, shadows and caustics on the paper, and the water's reflections and glass) are registered to the isometric planes and driven by a pure dispersion and optics model (`model.mjs`); a frequency change travels out from the dippers through a history texture.
- `examples/next-token/` is the abstract-concept example: how an LLM picks its next token, drawn as a sampler on a bench. The prompt is written on a terminal screen in the plane of its front, the five candidate words are on keycaps, chip stacks on a ruled board are as tall as each word's probability, a knurled temperature knob reshapes them, and a carriage stops at a seeded random u on a strip where the probabilities lie end to end. The model (`model.mjs`: softmax, inverse-CDF pick, a seedable generator) drives every number.launch-video
When your agent uses it
Make a showreel-grade motion-graphics launch video, with music, that introduces a CLI, library, or product from its repo. Use when asked for a launch, promo, sizzle, or showreel video, an animated intro for a project, or a video to post on X/social.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
1,574 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Marketing, not a white paper
- Show, don't tell
- The showreel question
- Rules
Files
SKILL.mdcore6,702 bytesSKILL.mdcore6,702 bytesSKILL.mdcore6,702 bytes
Read SKILL.md
# Launch Video
The bar is a **showreel**: the piece a motion designer puts on their résumé to
prove how good they are — dynamic, ambitious, scored to music, a real
professional production and never a demo or prototype. Go all out. The repo
supplies the story; the craft is yours. Nothing here is a template: if the
piece could be re-skinned for any other project, it has failed.
## Workflow
1. **Find the story.** Read the README, docs, benchmarks, and brand art. Done
when you can state, each with a source: what it is in one line, how it works
underneath (the audience is technical), and the proof worth landing. Flag
any claim the repo cannot back instead of inventing its meaning.renderer
When your agent uses it
Architecture rules for GPU rendering with TypeGPU/WebGPU. Use when adding or changing render passes, shaders, frame orchestration, GPU resources, culling, terrain, shadows, or visual performance work.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
411 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,902 bytes
Read SKILL.md
# GPU renderer
The renderer is TypeGPU over WebGPU. It draws plain frame inputs the
application hands it and never reaches into simulation or app state. These are
the flaws that sink a 3D experience; check a change against each before
writing it.
- **Fixed-view cost never grows with world size.** For a fixed camera and
render size, submitted geometry, shadow casters, and per-frame lists are
bounded by what the view can see or cast into, and screen-space work by
pixels. Store the world map-wide; select from it spatially. Frustum clipping
does not make vertices free. Compare equal local content and finite view
distance: admitting more world changes the workload.
- **Detail follows projected size.** Correct culling can still admit thousandsxiaohei-illustrations
When your agent uses it
Generate Ian-style Xiaohei illustrations for articles, posts, blogs, Notion documents, workflows, methods, processes, structures, states, metaphors, and opinions. Use when the user asks for weird, hand-drawn, Xiaohei, article, editorial, body illustrations, illustration ideas, shot lists, title removal, image edits, or image regeneration. By default, all image text and annotations are English, even when the source article is Chinese; only use another language when the user explicitly asks.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
1,086 tokensWhen the skill is activated
Reference documents
2,954 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Default language rule
- Read these references as needed
- Workflow
- Output style
Files
SKILL.mdcore5,133 bytesSKILL.mdcore5,133 bytesassets/examples/01-two-breakpoints.pngasset641,601 bytesassets/examples/02-minimum-loop.pngasset749,006 bytesassets/examples/03-sort-by-purpose.pngasset622,981 bytesassets/examples/04-one-fish-many-uses.pngasset832,527 bytesassets/examples/05-handoff-path.pngasset617,082 bytesassets/examples/06-three-sources.pngasset790,208 bytesassets/examples/07-three-content-jobs.pngasset691,437 bytesassets/examples/08-handoff-copy-toolbox.pngasset667,790 bytesassets/examples/09-common-pits-no-title.pngasset720,892 bytesassets/examples/10-information-well.pngasset826,870 bytesassets/examples/11-idea-press.pngasset690,616 bytesassets/examples/12-content-fermentation.pngasset676,927 bytesassets/examples/13-system-bearing.pngasset683,241 bytesassets/examples/14-trust-bridge.pngasset711,189 bytesreferences/composition-patterns.mddoc3,967 bytesreferences/prompt-template.mddoc3,212 bytesreferences/qa-checklist.mddoc2,304 bytesreferences/style-dna.mddoc2,236 bytesreferences/xiaohei-ip.mddoc1,751 bytes
Read SKILL.md
# Xiaohei Illustrations
## Purpose
Create 16:9 horizontal illustrations for article body sections and blog headers. The goal is not commercial illustration, a slide, or a cute cartoon. Turn the article's key judgment, process, structure, state, or metaphor into a clean, weird, creative, readable-but-not-instructional hand-drawn explanation.
The default visual IP is Xiaohei: a solid-black creature with white dot eyes, thin legs, and a blank expression, seriously doing something absurd but meaningful. Xiaohei must participate in the central action, not stand beside it as decoration.
## Default language rule
All visible image text must be English by default. This includes labels, notes, signs, fictional UI text, and tiny annotations. Do not mix in Chinese or other languages unless the user explicitly requests another language.
Keep English labels short, natural, and correctly spelled. Prefer 2–5 words per label.
compare-screenshots
When your agent uses it
Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
2,402 tokensWhen the skill is activated
Reference documents
2,272 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Useful Metrics
- Single-Image Metrics
- Distance Score
- Score Discipline
- Tooling
- References
Scripts executed separately
scripts/visual-parity-diff.eval.mjsscripts/visual-parity-diff.mjstest/visual-parity-diff.test.mjsvendor/pixelmatch/index.jsvendor/pixelmatch/package.jsonvendor/pngjs/lib/bitmapper.jsvendor/pngjs/lib/bitpacker.jsvendor/pngjs/lib/chunkstream.jsvendor/pngjs/lib/constants.jsvendor/pngjs/lib/crc.jsvendor/pngjs/lib/filter-pack.jsvendor/pngjs/lib/filter-parse-async.jsvendor/pngjs/lib/filter-parse-sync.jsvendor/pngjs/lib/filter-parse.jsvendor/pngjs/lib/format-normaliser.jsvendor/pngjs/lib/interlace.jsvendor/pngjs/lib/packer-async.jsvendor/pngjs/lib/packer-sync.jsvendor/pngjs/lib/packer.jsvendor/pngjs/lib/paeth-predictor.jsvendor/pngjs/lib/parser-async.jsvendor/pngjs/lib/parser-sync.jsvendor/pngjs/lib/parser.jsvendor/pngjs/lib/png-sync.jsvendor/pngjs/lib/png.jsvendor/pngjs/lib/sync-inflate.jsvendor/pngjs/lib/sync-reader.jsvendor/pngjs/package.json
Files
SKILL.mdcore10,672 bytesreferences/reference-landmarks.mddoc3,016 bytesreferences/subagent-visual-review.mddoc3,695 bytesscripts/visual-parity-diff.eval.mjsruns13,936 bytesscripts/visual-parity-diff.mjsruns23,653 bytestest/fixtures/target-without-helper-packages/README.mddoc70 bytestest/fixtures/target-without-helper-packages/candidate/fixture.pngasset297 bytestest/fixtures/target-without-helper-packages/reference/fixture.pngasset297 bytestest/visual-parity-diff.test.mjsruns2,536 bytesvendor/pixelmatch/LICENSEasset738 bytesvendor/pixelmatch/index.jsruns12,015 bytesvendor/pixelmatch/package.jsonruns904 bytesvendor/pngjs/LICENSEasset1,150 bytesvendor/pngjs/lib/bitmapper.jsruns6,477 bytesvendor/pngjs/lib/bitpacker.jsruns4,670 bytesvendor/pngjs/lib/chunkstream.jsruns4,249 bytesvendor/pngjs/lib/constants.jsruns662 bytesvendor/pngjs/lib/crc.jsruns853 bytesvendor/pngjs/lib/filter-pack.jsruns4,279 bytesvendor/pngjs/lib/filter-parse-async.jsruns558 bytesvendor/pngjs/lib/filter-parse-sync.jsruns483 bytesvendor/pngjs/lib/filter-parse.jsruns4,798 bytesvendor/pngjs/lib/format-normaliser.jsruns2,366 bytesvendor/pngjs/lib/interlace.jsruns2,004 bytesvendor/pngjs/lib/packer-async.jsruns1,162 bytesvendor/pngjs/lib/packer-sync.jsruns1,193 bytesvendor/pngjs/lib/packer.jsruns3,723 bytesvendor/pngjs/lib/paeth-predictor.jsruns372 bytesvendor/pngjs/lib/parser-async.jsruns4,368 bytesvendor/pngjs/lib/parser-sync.jsruns2,580 bytesvendor/pngjs/lib/parser.jsruns7,720 bytesvendor/pngjs/lib/png-sync.jsruns252 bytesvendor/pngjs/lib/png.jsruns4,418 bytesvendor/pngjs/lib/sync-inflate.jsruns3,751 bytesvendor/pngjs/lib/sync-reader.jsruns1,114 bytesvendor/pngjs/package.jsonruns1,812 bytes../design-with-images/SKILL.mddoc4,482 bytes
Read SKILL.md
# Compare Screenshots
Judge images against the intended result. A user-approved design is the target;
a historical baseline is only an earlier attempt and may be wrong. Metrics locate
differences, never decide correctness. Use
[design-with-images](../design-with-images/SKILL.md) for the full exploration-to-implementation loop.
## Workflow
1. **Establish the target.** Use the user-approved reference and stated design
requirements when available; do not replace them with your own taste. Otherwise
derive the target from the visual requirement, what the thing depicts in reality
and the domain skill that owns the look. Write it down in one or two
concrete sentences ("low sun should cast long shadows east; trees fill thedesign-with-images
When your agent uses it
Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
880 tokensWhen the skill is activated
Reference documents
5,724 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Rules
Files
../compare-screenshots/SKILL.mddoc10,672 bytes../compare-screenshots/references/reference-landmarks.mddoc3,016 bytesSKILL.mdcore4,482 bytesSKILL.mdcore4,482 bytes../preview-shots/SKILL.mddoc2,046 bytes../screenshot-critique/SKILL.mddoc10,096 bytes
Read SKILL.md
# Design With Images
The deliverable is the working design, visibly matched to the approved reference.
Image generation explores the target; real screenshots prove the implementation.
For an exploration-only request, deliver the options and wait for a selection.
## Workflow
1. **Frame the decision.** Read the relevant design skill and capture the actual
surface. Pin what may change and what must stay: content, framing, palette,
interactions and surrounding UI. Keep the original capture.
2. **Generate alternatives.** Use the available image-generation skill/tool with
that capture as a reference. Produce a small, labelled set of distinct visual
directions. Show them as concepts, never as screenshots of implemented code.preview-shots
When your agent uses it
Open image shots (screenshots, snapshot baselines, montages, renders) in ONE macOS Preview window so the user can eyeball them. Use when the user asks to open / show / pull up / review shots in Preview or Finder, or right after producing visual artifacts the user should look at before signing off.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
464 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Rules
Files
SKILL.mdcore2,046 bytes
Read SKILL.md
# Preview Shots
Put the review-worthy images in front of the user in a single Preview window they can flip through.
## Workflow
1. **Curate the set** — the images that answer "is this right?": the just-changed or just-blessed baselines, the integrated result, and the reference image when there's something to compare against. Don't dump every PNG in the folder; pick the smallest set that lets the user judge the change. If the user named specific shots, open exactly those.
2. **One window** — open them with a single `open -a Preview <path> <path> ...` call. One `open` invocation lands all the files in one window with a thumbnail sidebar; separate calls spawn separate windows.
3. **Caption them** — list one line per shot (what it is) so the user knows what they're flipping through.
## Rules
- macOS only (`open`); pass absolute or repo-root-relative paths.
- Order the files most-important-first; the first one is what Preview shows on open.screenshot-critique
When your agent uses it
Use the unprimed sub agent as a second set of eyes before accepting visual work — MANDATORY before declaring any user-reported visual bug fixed or claiming a visual change verified; primed eyes pass defects fresh eyes catch.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
2,242 tokensWhen the skill is activated
Reference documents
616 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Sub-Agent Prompt
- Receipts
- Rules
Scripts executed separately
scripts/receipts.eval.mjsscripts/receipts.mjs
Files
../compare-screenshots/references/reference-landmarks.mddoc3,016 bytesSKILL.mdcore10,096 bytesscripts/receipts.eval.mjsruns20,874 bytesscripts/receipts.mjsruns18,680 bytes
Read SKILL.md
# Screenshot Critique
Use an unprimed sub-agent as a second set of eyes before accepting visual work.
This is for visual defects, not pixel metrics; pair it with
`compare-screenshots` when you also need numbers — including on a single shot
with nothing to compare against, whose scene metrics say whether the frame has
any content in it at all.
## Workflow
1. Capture or locate the exact PNGs/GIF frames under review.
2. Keep native-size evidence and create supplementary 2x-4x crops for every
key feature, plus the full screenshot. Include complete endpoints and fades;
recheck crop bounds after geometry changes. Crop selected units, city/townSkills included
- audit-agents
- eval-skills
- write-skills
- audit-decisions
- audit-performance
- audit-tests
- auto-research
- claude
- close-spec
- code-review
- codex
- eli5
- explore-unknowns
- handoff-spec
- implement-spec
- implement-spec-with-codex
- implement-spec-with-goal
- marketing-pages
- port-features
- ratchet-files
- refactor-clean
- retro
- review
- write-docs
- write-spec
- write-tests
- cinematic-shot
- isometric-motion
- launch-video
- renderer
- xiaohei-illustrations
- compare-screenshots
- design-with-images
- preview-shots
- screenshot-critique
Repository facts
- License
- MIT
- Created
- Jul 2, 2026
- Last pushed
- Nov 4, 2026
- Forks
- 85
- Open issues
- 1
- Project activity
- Active
Rank over the last 12 weeks
Now #680 · best #582 · up 14 in 30 days
- #672 on Oct 31
- #674 on Nov 1
- #676 on Nov 2
- #679 from Nov 3 to Nov 4
- #681 on Nov 5
- #680 since Nov 6
70 earlier periods
- #857 on Aug 1
- #773 on Aug 11
- #762 on Aug 14
- #736 on Aug 15
- #759 on Aug 16
- #775 on Aug 19
- #735 on Aug 20
- #720 on Aug 21
- #683 on Aug 22
- #715 on Aug 23
- #738 on Aug 24
- #747 on Aug 25
- #716 on Aug 26
- #723 on Aug 27
- #746 on Aug 28
- #688 on Aug 29
- #689 on Aug 30
- #713 on Aug 31
- #720 on Sep 1
- #706 on Sep 2
- #664 on Sep 3
- #639 on Sep 4
- #634 on Sep 5
- #650 on Sep 6
- #665 on Sep 7
- #683 on Sep 8
- #673 on Sep 9
- #674 on Sep 10
- #663 on Sep 11
- #666 on Sep 13
- #687 on Sep 14
- #673 on Sep 15
- #687 on Sep 16
- #691 on Sep 17
- #684 on Sep 18
- #659 on Sep 19
- #710 on Sep 22
- #701 on Sep 23
- #660 on Sep 25
- #661 on Sep 26
- #687 on Sep 27
- #685 on Sep 28
- #728 on Sep 29
- #702 on Sep 30
- #668 on Oct 1
- #674 on Oct 2
- #654 on Oct 3
- #686 on Oct 4
- #681 on Oct 5
- #686 on Oct 6
- #694 on Oct 7
- #733 on Oct 8
- #703 on Oct 9
- #689 on Oct 10
- #652 on Oct 11
- #599 on Oct 12
- #589 on Oct 13
- #599 on Oct 14
- #594 on Oct 15
- #603 on Oct 16
- #592 on Oct 17
- #582 on Oct 18
- #594 on Oct 19
- #605 on Oct 20
- #600 on Oct 22
- #593 on Oct 23
- #587 on Oct 24
- #657 on Oct 25
- #662 on Oct 28
- #669 from Oct 29 to Oct 30
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Changed on Nov 3, 2026
New signal: Instruction override signal
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 89 notes
skills/authoring/write-skills/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/authoring/write-skills/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/audit-tests/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/claude/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/close-spec/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/close-spec/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/code-review/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/code-review/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/codex/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/marketing-pages/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/marketing-pages/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/port-features/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/ratchet-files/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/ratchet-files/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/ratchet-files/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/write-docs/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/write-spec/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/graphics/isometric-motion/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/graphics/isometric-motion/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/graphics/isometric-motion/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- 2 broad permissionsin 1 file: code-review/SKILL.md:1
- 8 dangerous shell commandsin 3 files: isometric-motion/kit/audit.mjs:230 isometric-motion/kit/turn-audit.mjs:758 compare-screenshots/test/visual-parity-diff.test.mjs:2
- 171 network referencesin 37 files: codex/SKILL.md:19 isometric-motion/scripts/turn-check.mjs:41 compare-screenshots/vendor/pixelmatch/package.json:27 and 34 more
- 2 obfuscation signalsin 2 files: isometric-motion/kit/turn-fixed.mjs:463 isometric-motion/kit/turn.mjs:428
- 3 instruction override signalsin 1 file: claude/SKILL.md:95
- 123 executable scriptsin 123 files: ratchet-files/scripts/check-file-size.mjs:1 ratchet-files/scripts/install-git-hooks.mjs:1 ratchet-files/scripts/install-git-hooks.test.mjs:1 and 120 more
- 1 reference to secretsin 1 file: claude/SKILL.md:112
- No requests to vote in Hot
Show all 310 signals by file
skills/engineering/claude/SKILL.md
- Instruction override signalline 95
- Read/review: `--tools "Read,Grep,Glob,Bash" --permission-mode dontAsk`. - Narrow edits: add edit tools and keep the prompt's allowed paths explicit. - Broad autonomous work: use `--dangerously-skip-permissions` only in a - Instruction override signalline 96
- Narrow edits: add edit tools and keep the prompt's allowed paths explicit. - Broad autonomous work: use `--dangerously-skip-permissions` only in a dedicated worktree, with a self-authored prompt and a mandatory diff - Instruction override signalline 97
- Broad autonomous work: use `--dangerously-skip-permissions` only in a - Access to secretsline 112
[Credential-related source omitted]
skills/engineering/code-review/SKILL.md
skills/engineering/codex/SKILL.md
- Network accessline 19
When `codex` is missing from PATH, offer to install it — **ask the user for approval first**, never install on your own initiative. On yes, follow the current instructions at https://developers.openai.com/codex/cli. First-run - Network accessline 19
When `codex` is missing from PATH, offer to install it — **ask the user for approval first**, never install on your own initiative. On yes, follow the current instructions at https://developers.openai.com/codex/cli. First-run - Network accessline 20
approval first**, never install on your own initiative. On yes, follow the current instructions at https://developers.openai.com/codex/cli. First-run authentication is interactive — hand that step to the user. Verify with - Network accessline 20
approval first**, never install on your own initiative. On yes, follow the current instructions at https://developers.openai.com/codex/cli. First-run authentication is interactive — hand that step to the user. Verify with - Network accessline 21
current instructions at https://developers.openai.com/codex/cli. First-run - Network accessline 21
current instructions at https://developers.openai.com/codex/cli. First-run - Network accessline 108
- Pure code + typecheck/unit: `codex exec --sandbox workspace-write "<task>"`. Network is off; add `-c sandbox_workspace_write.network_access=true` only when the task must fetch (e.g. new deps). - Network accessline 108
- Pure code + typecheck/unit: `codex exec --sandbox workspace-write "<task>"`. Network is off; add `-c sandbox_workspace_write.network_access=true` only when the task must fetch (e.g. new deps). - Network accessline 109
Network is off; add `-c sandbox_workspace_write.network_access=true` only when the task must fetch (e.g. new deps). - **Browser verification, dev servers, or full test runs: use - Network accessline 109
Network is off; add `-c sandbox_workspace_write.network_access=true` only when the task must fetch (e.g. new deps). - **Browser verification, dev servers, or full test runs: use - Network accessline 110
when the task must fetch (e.g. new deps). - Network accessline 110
when the task must fetch (e.g. new deps).
skills/engineering/ratchet-files/scripts/check-file-size.mjs
- Executable scriptline 1
#!/usr/bin/env node
skills/engineering/ratchet-files/scripts/install-git-hooks.mjs
- Executable scriptline 1
Executable file
skills/engineering/ratchet-files/scripts/install-git-hooks.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/SKILL.md
- Network accessline 8
> Copied from [wheresryan22/anatomy](https://github.com/wheresryan22/anatomy) (MIT, see `LICENSE`) and repurposed for animations and interactive elements in the same style.
skills/graphics/isometric-motion/examples/arcade-cabinet/arcade-cabinet-light.html
- Network accessline 156
.ac-marquee[data-on] .ac-marquee-art{fill:var(--anatomy-lit)} .ac-marquee-frame{fill:none;stroke:var(--anatomy-lo);stroke-width:.5px;vector-effect:non-scaling-stroke} </style><figure class="iso-figure"><div class="iso-plate"><div class="iso - Network accessline 157
.ac-marquee-frame{fill:none;stroke:var(--anatomy-lo);stroke-width:.5px;vector-effect:non-scaling-stroke} </style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corn - Network accessline 158
</style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 4</span><span class="iso-plate-corner" data-corner="title">Upright cabinet, sid - Network accessline 689
const style = standalone ? `<style>${ISO_CSS}</style>` : ""; return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", - Network accessline 690
return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", class: `iso-svg${standalone ? " iso" : ""}${className ? ` ${className}` : ""}`, - Network accessline 691
xmlns: "http://www.w3.org/2000/svg",
skills/graphics/isometric-motion/examples/arcade-cabinet/arcade-cabinet.html
- Network accessline 156
.ac-marquee[data-on] .ac-marquee-art{fill:var(--anatomy-lit)} .ac-marquee-frame{fill:none;stroke:var(--anatomy-lo);stroke-width:.5px;vector-effect:non-scaling-stroke} </style><figure class="iso-figure"><div class="iso-plate"><div class="iso - Network accessline 157
.ac-marquee-frame{fill:none;stroke:var(--anatomy-lo);stroke-width:.5px;vector-effect:non-scaling-stroke} </style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corn - Network accessline 158
</style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 4</span><span class="iso-plate-corner" data-corner="title">Upright cabinet, sid - Network accessline 689
const style = standalone ? `<style>${ISO_CSS}</style>` : ""; return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", - Network accessline 690
return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", class: `iso-svg${standalone ? " iso" : ""}${className ? ` ${className}` : ""}`, - Network accessline 691
xmlns: "http://www.w3.org/2000/svg",
skills/graphics/isometric-motion/examples/arcade-cabinet/build.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/arcade-cabinet/live.js
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/arcade-cabinet/parts.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/arcade-cabinet/screen.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/desk-computer/build.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/desk-computer/desk-computer-light.html
- Network accessline 135
.iso-stage:focus{outline:none} .iso-stage:focus-visible{outline:1px solid var(--anatomy-muted);outline-offset:6px} </style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso- - Network accessline 136
.iso-stage:focus-visible{outline:1px solid var(--anatomy-muted);outline-offset:6px} </style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig" - Network accessline 137
</style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 2</span><span class="iso-plate-corner" data-corner="title">Desk computer</span> - Network accessline 668
const style = standalone ? `<style>${ISO_CSS}</style>` : ""; return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", - Network accessline 669
return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", class: `iso-svg${standalone ? " iso" : ""}${className ? ` ${className}` : ""}`, - Network accessline 670
xmlns: "http://www.w3.org/2000/svg",
skills/graphics/isometric-motion/examples/desk-computer/desk-computer.html
- Network accessline 135
.iso-stage:focus{outline:none} .iso-stage:focus-visible{outline:1px solid var(--anatomy-muted);outline-offset:6px} </style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso- - Network accessline 136
.iso-stage:focus-visible{outline:1px solid var(--anatomy-muted);outline-offset:6px} </style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig" - Network accessline 137
</style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 2</span><span class="iso-plate-corner" data-corner="title">Desk computer</span> - Network accessline 668
const style = standalone ? `<style>${ISO_CSS}</style>` : ""; return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", - Network accessline 669
return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", class: `iso-svg${standalone ? " iso" : ""}${className ? ` ${className}` : ""}`, - Network accessline 670
xmlns: "http://www.w3.org/2000/svg",
skills/graphics/isometric-motion/examples/dial-indicator/build.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/dial-indicator/dial-indicator-light.html
- Network accessline 112
body{margin:0;background:var(--anatomy-page);color:var(--anatomy-text);font:14px/1.6 ui-sans-serif,system-ui,-apple-system,"Segoe UI",sans-serif;-webkit-font-smoothing:antialiased} .iso-page{width:min(650px,100% - 32px);margin:64px auto 96p - Network accessline 113
.iso-page{width:min(650px,100% - 32px);margin:64px auto 96px} </style></head><body class="iso" data-theme="light"><main class="iso-page"><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><sp - Network accessline 114
</style></head><body class="iso" data-theme="light"><main class="iso-page"><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 1</span><spa - Network accessline 645
const style = standalone ? `<style>${ISO_CSS}</style>` : ""; return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", - Network accessline 646
return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", class: `iso-svg${standalone ? " iso" : ""}${className ? ` ${className}` : ""}`, - Network accessline 647
xmlns: "http://www.w3.org/2000/svg",
skills/graphics/isometric-motion/examples/dial-indicator/dial-indicator.html
- Network accessline 112
body{margin:0;background:var(--anatomy-page);color:var(--anatomy-text);font:14px/1.6 ui-sans-serif,system-ui,-apple-system,"Segoe UI",sans-serif;-webkit-font-smoothing:antialiased} .iso-page{width:min(650px,100% - 32px);margin:64px auto 96p - Network accessline 113
.iso-page{width:min(650px,100% - 32px);margin:64px auto 96px} </style></head><body class="iso" data-theme="dark"><main class="iso-page"><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><spa - Network accessline 114
</style></head><body class="iso" data-theme="dark"><main class="iso-page"><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 1</span><span - Network accessline 645
const style = standalone ? `<style>${ISO_CSS}</style>` : ""; return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", - Network accessline 646
return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", class: `iso-svg${standalone ? " iso" : ""}${className ? ` ${className}` : ""}`, - Network accessline 647
xmlns: "http://www.w3.org/2000/svg",
skills/graphics/isometric-motion/examples/next-token/build.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/next-token/model.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/next-token/next-token-light.html
- Network accessline 136
.iso-stage:focus{outline:none} .iso-stage:focus-visible{outline:1px solid var(--anatomy-muted);outline-offset:6px} </style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso- - Network accessline 137
.iso-stage:focus-visible{outline:1px solid var(--anatomy-muted);outline-offset:6px} </style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig" - Network accessline 138
</style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 1</span><span class="iso-plate-corner" data-corner="title">Next token</span><sp - Network accessline 669
const style = standalone ? `<style>${ISO_CSS}</style>` : ""; return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", - Network accessline 670
return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", class: `iso-svg${standalone ? " iso" : ""}${className ? ` ${className}` : ""}`, - Network accessline 671
xmlns: "http://www.w3.org/2000/svg",
skills/graphics/isometric-motion/examples/next-token/next-token.html
- Network accessline 136
.iso-stage:focus{outline:none} .iso-stage:focus-visible{outline:1px solid var(--anatomy-muted);outline-offset:6px} </style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso- - Network accessline 137
.iso-stage:focus-visible{outline:1px solid var(--anatomy-muted);outline-offset:6px} </style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig" - Network accessline 138
</style><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 1</span><span class="iso-plate-corner" data-corner="title">Next token</span><sp - Network accessline 669
const style = standalone ? `<style>${ISO_CSS}</style>` : ""; return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", - Network accessline 670
return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", class: `iso-svg${standalone ? " iso" : ""}${className ? ` ${className}` : ""}`, - Network accessline 671
xmlns: "http://www.w3.org/2000/svg",
skills/graphics/isometric-motion/examples/raptor-engine/build.mjs
- Executable scriptline 1
Executable file - Network accessline 889
const backSvg = k.figureSvg({ width: W, height: H, label: LABEL_TEXT, body: back, className: "rp-back" }); const frontSvg = `<svg xmlns="http://www.w3.org/2000/svg" class="iso-svg rp-front" viewBox="0 0 ${W} ${H}" aria-hidden="true"><g clas - Network accessline 890
const frontSvg = `<svg xmlns="http://www.w3.org/2000/svg" class="iso-svg rp-front" viewBox="0 0 ${W} ${H}" aria-hidden="true"><g class="rp-engine">${groups.join("")}</g></svg>`; - Network accessline 923
const corners = `<div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 1</span><span class="iso-plate-corner" data-corner="title">Raptor 2 · test stand</span><span class="iso-plate-corner" da - Network accessline 924
const controls = `<div class="rp-controls"><button type="button" class="rp-fire" data-fire><span class="rp-lamp" aria-hidden="true"></span><span data-fire-label>Ignite</span></button><span class="rp-hint">Hover the engine to take it apart</ - Network accessline 925
const glowSvg = `<svg xmlns="http://www.w3.org/2000/svg" class="iso-svg rp-glow" viewBox="0 0 ${W} ${H}" aria-hidden="true"><g class="rp-glow-g"><path class="rp-rim rp-rim-soft" d="${LIP}"/><path class="rp-rim" d="${LIP}"/></g></svg>`;
skills/graphics/isometric-motion/examples/raptor-engine/live.js
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/raptor-engine/raptor-engine-light.html
- Network accessline 471
stroke: none; } </style><figure class="iso-figure rp"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 1</span><span class="iso-plate-corner" data-corner="title">R - Network accessline 473
</style><figure class="iso-figure rp"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 1</span><span class="iso-plate-corner" data-corner="title">Raptor 2 · test s
skills/graphics/isometric-motion/examples/raptor-engine/raptor-engine.html
- Network accessline 471
stroke: none; } </style><figure class="iso-figure rp"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 1</span><span class="iso-plate-corner" data-corner="title">R - Network accessline 473
</style><figure class="iso-figure rp"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 1</span><span class="iso-plate-corner" data-corner="title">Raptor 2 · test s
skills/graphics/isometric-motion/examples/ripple-tank/build.mjs
- Executable scriptline 1
Executable file - Network accessline 529
const backSvg = k.figureSvg({ width: W, height: H, label: LABEL_TEXT, body: back, className: "rt-back" }); const layerSvg = (name, body) => `<svg xmlns="http://www.w3.org/2000/svg" class="iso-svg rt-layer ${name}" viewBox="0 0 ${W} ${H}" ar - Network accessline 530
const layerSvg = (name, body) => `<svg xmlns="http://www.w3.org/2000/svg" class="iso-svg rt-layer ${name}" viewBox="0 0 ${W} ${H}" aria-hidden="true">${body.join("")}</svg>`;
skills/graphics/isometric-motion/examples/ripple-tank/live.js
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/ripple-tank/model.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/ripple-tank/ripple-tank-light.html
- Network accessline 215
} } </style><div class="rt"><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 3</span><span class="iso-plate-corner" data-corner="title"> - Network accessline 216
} </style><div class="rt"><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 3</span><span class="iso-plate-corner" data-corner="title">Ri - Network accessline 217
</style><div class="rt"><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 3</span><span class="iso-plate-corner" data-corner="title">Ripp - Network accessline 748
const style = standalone ? `<style>${ISO_CSS}</style>` : ""; return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", - Network accessline 749
return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", class: `iso-svg${standalone ? " iso" : ""}${className ? ` ${className}` : ""}`, - Network accessline 750
xmlns: "http://www.w3.org/2000/svg",
skills/graphics/isometric-motion/examples/ripple-tank/ripple-tank.html
- Network accessline 215
} } </style><div class="rt"><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 3</span><span class="iso-plate-corner" data-corner="title"> - Network accessline 216
} </style><div class="rt"><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 3</span><span class="iso-plate-corner" data-corner="title">Ri - Network accessline 217
</style><div class="rt"><figure class="iso-figure"><div class="iso-plate"><div class="iso-plate-corners" aria-hidden="true"><span class="iso-plate-corner" data-corner="fig">Fig 3</span><span class="iso-plate-corner" data-corner="title">Ripp - Network accessline 748
const style = standalone ? `<style>${ISO_CSS}</style>` : ""; return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", - Network accessline 749
return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", class: `iso-svg${standalone ? " iso" : ""}${className ? ` ${className}` : ""}`, - Network accessline 750
xmlns: "http://www.w3.org/2000/svg",
skills/graphics/isometric-motion/examples/spot-plate/art.tsx
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/spot-plate/drops.ts
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/spot-plate/fan.ts
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/spot-plate/figure.tsx
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/spot-plate/geometry.ts
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/spot-plate/live.tsx
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/spot-plate/rig.ts
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/test-rig/art.tsx
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/test-rig/figure.tsx
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/test-rig/geometry.ts
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/test-rig/live.tsx
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/test-rig/pose.ts
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/test-rig/rig.ts
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/test-rig/view.ts
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/turning-dial/build.mjs
- Executable scriptline 1
Executable file - Network accessline 449
const LABEL = "A combination dial on a raised door plate. A small robot hand lies on the dial's hub and turns with it: a palm with a cover plate, a connector block, a piston on two saddles with a ball joint, three jointed fingers whose tips - Network accessline 450
const backSvg = k.figureSvg({ width: WIDTH, height: HEIGHT, label: LABEL, body: BACK }); const staticSvg = (list) => `<svg xmlns="http://www.w3.org/2000/svg" class="iso-svg iso-layer" viewBox="0 0 ${WIDTH} ${HEIGHT}" aria-hidden="true">${li - Network accessline 451
const staticSvg = (list) => `<svg xmlns="http://www.w3.org/2000/svg" class="iso-svg iso-layer" viewBox="0 0 ${WIDTH} ${HEIGHT}" aria-hidden="true">${list.join("")}</svg>`;
skills/graphics/isometric-motion/examples/turning-dial/live.js
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/examples/turning-dial/stress.mjs
- Executable scriptline 1
Executable file - Network accessline 191
for (let f = 0; f < 5; f++) { const tag = f < 4 ? `f${f}` : "thumb"; const curl = (Math.sin(t * 1.3 + f * 0.9) * 0.5 + 0.5) * lift; - Network accessline 192
const tag = f < 4 ? `f${f}` : "thumb"; const curl = (Math.sin(t * 1.3 + f * 0.9) * 0.5 + 0.5) * lift; out[`${tag}.j0`] = -5 + 10 * curl; - Network accessline 193
const curl = (Math.sin(t * 1.3 + f * 0.9) * 0.5 + 0.5) * lift; - Network accessline 223
const BACK = [`<path class="iso-halo" d="${k.haloOf(BENCH, BENCH_TOP - 6, 6, P)}"/>`, ...layerOf("back")]; const backSvg = k.figureSvg({ width: WIDTH, height: HEIGHT, label: "A dense robot hand on a turntable in a workshop: a stress scene f - Network accessline 224
const backSvg = k.figureSvg({ width: WIDTH, height: HEIGHT, label: "A dense robot hand on a turntable in a workshop: a stress scene for the 3D mode.", body: BACK }); const staticSvg = (list) => `<svg xmlns="http://www.w3.org/2000/svg" class - Network accessline 225
const staticSvg = (list) => `<svg xmlns="http://www.w3.org/2000/svg" class="iso-svg iso-layer" viewBox="0 0 ${WIDTH} ${HEIGHT}" aria-hidden="true">${list.join("")}</svg>`;
skills/graphics/isometric-motion/examples/turning-dial/turning-dial-light.html
- Network accessline 167
.td-led-core{fill:var(--td-led-pale)} .td-stage[data-gl] .td-led{opacity:var(--td-fallback,0)} </style><div class="iso-stage iso-turn td-stage" tabindex="0" role="slider" aria-label="Combination dial: drag around the dial or use the arrow k - Network accessline 168
.td-stage[data-gl] .td-led{opacity:var(--td-fallback,0)} </style><div class="iso-stage iso-turn td-stage" tabindex="0" role="slider" aria-label="Combination dial: drag around the dial or use the arrow keys to turn it, press B to break the p - Network accessline 169
</style><div class="iso-stage iso-turn td-stage" tabindex="0" role="slider" aria-label="Combination dial: drag around the dial or use the arrow keys to turn it, press B to break the pod off" aria-valuemin="0" aria-valuemax="99" aria-valueno
skills/graphics/isometric-motion/examples/turning-dial/turning-dial-verify-light.html
- Network accessline 167
.td-led-core{fill:var(--td-led-pale)} .td-stage[data-gl] .td-led{opacity:var(--td-fallback,0)} </style><div class="iso-stage iso-turn td-stage" tabindex="0" role="slider" aria-label="Combination dial: drag around the dial or use the arrow k - Network accessline 168
.td-stage[data-gl] .td-led{opacity:var(--td-fallback,0)} </style><div class="iso-stage iso-turn td-stage" tabindex="0" role="slider" aria-label="Combination dial: drag around the dial or use the arrow keys to turn it, press B to break the p - Network accessline 169
</style><div class="iso-stage iso-turn td-stage" tabindex="0" role="slider" aria-label="Combination dial: drag around the dial or use the arrow keys to turn it, press B to break the pod off" aria-valuemin="0" aria-valuemax="99" aria-valueno
skills/graphics/isometric-motion/examples/turning-dial/turning-dial.html
- Network accessline 167
.td-led-core{fill:var(--td-led-pale)} .td-stage[data-gl] .td-led{opacity:var(--td-fallback,0)} </style><div class="iso-stage iso-turn td-stage" tabindex="0" role="slider" aria-label="Combination dial: drag around the dial or use the arrow k - Network accessline 168
.td-stage[data-gl] .td-led{opacity:var(--td-fallback,0)} </style><div class="iso-stage iso-turn td-stage" tabindex="0" role="slider" aria-label="Combination dial: drag around the dial or use the arrow keys to turn it, press B to break the p - Network accessline 169
</style><div class="iso-stage iso-turn td-stage" tabindex="0" role="slider" aria-label="Combination dial: drag around the dial or use the arrow keys to turn it, press B to break the pod off" aria-valuemin="0" aria-valuemax="99" aria-valueno
skills/graphics/isometric-motion/examples/turning-dial/turning-stress-light.html
- Network accessline 157
.iso-turn{position:relative} .iso-turn>.iso-layer{position:absolute;inset:0;width:100%;height:100%;pointer-events:none} .ts-stage{outline:none}</style><div class="iso-stage iso-turn ts-stage" tabindex="0" role="img" aria-label="A dense robo - Network accessline 158
.iso-turn>.iso-layer{position:absolute;inset:0;width:100%;height:100%;pointer-events:none} .ts-stage{outline:none}</style><div class="iso-stage iso-turn ts-stage" tabindex="0" role="img" aria-label="A dense robot hand turning on a turntable - Network accessline 159
.ts-stage{outline:none}</style><div class="iso-stage iso-turn ts-stage" tabindex="0" role="img" aria-label="A dense robot hand turning on a turntable"><svg xmlns="http://www.w3.org/2000/svg" class="iso-svg" viewBox="0 0 760 560" role="img"
skills/graphics/isometric-motion/kit/audit.mjs
- Executable scriptline 1
Executable file - Dangerous shell operationline 230
const rm = Math.max(...poly.map(([, r]) => r)); - Dangerous shell operationline 233
const spread = [0, 1, 2].map((i) => rm * Math.sqrt(Math.max(0, 1 - F.a[i] * F.a[i]))); - Dangerous shell operationline 340
const { aV, uV, vV, s0, s1, rm } = shape._f; - Dangerous shell operationline 356
const qc = xc * xc + yc * yc - rm * rm; - Dangerous shell operationline 362
} else if (xc * xc + yc * yc > rm * rm) return null;
skills/graphics/isometric-motion/kit/canvas-painter.mjs
- Network accessline 1
const CP_Q = 64; const CP_SVG = "http://www.w3.org/2000/svg"; - Executable scriptline 1
Executable file - Network accessline 2
const CP_SVG = "http://www.w3.org/2000/svg"; - Network accessline 689
const theme = holder ? holder.getAttribute("data-theme") : "dark"; const card = getComputedStyle(stage.closest(".iso-plate") || stage).getPropertyValue("--anatomy-card").trim() || "#fff"; return `<svg xmlns="http://www.w3.org/20 - Network accessline 690
const card = getComputedStyle(stage.closest(".iso-plate") || stage).getPropertyValue("--anatomy-card").trim() || "#fff"; return `<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 ${W} ${H}" width="${W}" height="${H}"><style>${css.r - Network accessline 691
return `<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 ${W} ${H}" width="${W}" height="${H}"><style>${css.replace(/<\/style/gi, "")}</style><g class="iso" data-theme="${theme}"><g class="iso-plate" style="padding:0;box-shadow:none">${
skills/graphics/isometric-motion/kit/gl-shared.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/kit/gl.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/kit/iso-kit.mjs
- Executable scriptline 1
Executable file - Network accessline 532
const style = standalone ? `<style>${ISO_CSS}</style>` : ""; return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", - Network accessline 533
return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", class: `iso-svg${standalone ? " iso" : ""}${className ? ` ${className}` : ""}`, - Network accessline 534
xmlns: "http://www.w3.org/2000/svg",
skills/graphics/isometric-motion/kit/iso-kit.ts
- Executable scriptline 1
Executable file - Network accessline 669
const style = standalone ? `<style>${ISO_CSS}</style>` : ""; return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", - Network accessline 670
return `<svg${attrs({ xmlns: "http://www.w3.org/2000/svg", class: `iso-svg${standalone ? " iso" : ""}${className ? ` ${className}` : ""}`, - Network accessline 671
xmlns: "http://www.w3.org/2000/svg",
skills/graphics/isometric-motion/kit/lathe.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/kit/react/draw.tsx
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/kit/react/live.tsx
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/kit/tube.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/kit/turn-audit.mjs
skills/graphics/isometric-motion/kit/turn-build.mjs
- Executable scriptline 1
Executable file - Network accessline 1267
}; const out = { svg: markup, data: packed, css: TURN_CSS, report, scene, frames, planesByName }; out.layerSvg = (name, { width, height, label = "" }) => `<svg xmlns="http://www.w3.org/2000/svg" class="iso-svg iso-live iso-layer" data-l - Network accessline 1268
const out = { svg: markup, data: packed, css: TURN_CSS, report, scene, frames, planesByName }; out.layerSvg = (name, { width, height, label = "" }) => `<svg xmlns="http://www.w3.org/2000/svg" class="iso-svg iso-live iso-layer" data-live=" - Network accessline 1269
out.layerSvg = (name, { width, height, label = "" }) => `<svg xmlns="http://www.w3.org/2000/svg" class="iso-svg iso-live iso-layer" data-live="${esc(name)}" viewBox="0 0 ${width} ${height}" aria-hidden="true"${label ? ` aria-label="${esc(la
skills/graphics/isometric-motion/kit/turn-fixed.mjs
skills/graphics/isometric-motion/kit/turn.mjs
skills/graphics/isometric-motion/references/verify.md
- Network accessline 14
node scripts/capture.mjs page.html --out shots/joint.png --zoom 200,80,220,170 # close-up at 4x, in card px node scripts/capture.mjs page.html --out shots/still.png --reduced # reduced motion node scripts/capture.mjs http://lo - Network accessline 16
node scripts/capture.mjs http://localhost:3000/docs --select "figure:nth-of-type(3) .iso-plate" # one figure on a dev-server page
skills/graphics/isometric-motion/references/webgl.md
- Network accessline 166
const DATA = { W, H, camera: glCamera(P), plateR: 40, deck: [DECK.w / 2, DECK.r] }; const backSvg = k.figureSvg({ width: W, height: H, label: LABEL, body: back }); const frontSvg = `<svg xmlns="http://www.w3.org/2000/svg" class="iso-svg fx- - Network accessline 167
const backSvg = k.figureSvg({ width: W, height: H, label: LABEL, body: back }); const frontSvg = `<svg xmlns="http://www.w3.org/2000/svg" class="iso-svg fx-layer" viewBox="0 0 ${W} ${H}" aria-hidden="true">${front.join("")}</svg>`; const st - Network accessline 168
const frontSvg = `<svg xmlns="http://www.w3.org/2000/svg" class="iso-svg fx-layer" viewBox="0 0 ${W} ${H}" aria-hidden="true">${front.join("")}</svg>`;
skills/graphics/isometric-motion/scripts/audit-affine-bounds.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/audit-cache.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/audit-clearance-envelope.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/audit-empty-clipping.test.mjs
- Executable scriptline 1
Executable file - Network accessline 21
try{ const page=join(directory,"figure.html");await writeFile(page,'<!doctype html><div class="iso-plate"></div>'); const expression=`(async()=>{const fixtures=${JSON.stringify(fixtures.map(([,m])=>m))};const result=[];for(const m of fi - Network accessline 22
const page=join(directory,"figure.html");await writeFile(page,'<!doctype html><div class="iso-plate"></div>'); const expression=`(async()=>{const fixtures=${JSON.stringify(fixtures.map(([,m])=>m))};const result=[];for(const m of fixtures) - Network accessline 23
const expression=`(async()=>{const fixtures=${JSON.stringify(fixtures.map(([,m])=>m))};const result=[];for(const m of fixtures){const svg='<svg xmlns="http://www.w3.org/2000/svg" width="64" height="64" viewBox="0 0 64 64">'+m+'</svg>';const
skills/graphics/isometric-motion/scripts/audit-order-convergence.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/audit-path-origin.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/audit-profile.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/audit-projection.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/audit-slide-clearance.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/audit-svg-attributes.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/audit-taper.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/capture-current-geometry.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/capture-selector.test.mjs
- Executable scriptline 1
Executable file - Network accessline 15
const out = join(directory, "capture.png"); const content = svgOnly ? '<svg width="80" height="40" xmlns="http://www.w3.org/2000/svg"><rect width="80" height="40" fill="green"/></svg>' - Network accessline 16
const content = svgOnly ? '<svg width="80" height="40" xmlns="http://www.w3.org/2000/svg"><rect width="80" height="40" fill="green"/></svg>' : `<div class="iso-plate" tabindex="0" id="first" style="width:100px;height:80px;backgr - Network accessline 17
? '<svg width="80" height="40" xmlns="http://www.w3.org/2000/svg"><rect width="80" height="40" fill="green"/></svg>'
skills/graphics/isometric-motion/scripts/capture.mjs
- Executable scriptline 1
Executable file - Network accessline 123
}; try { const target = await (await fetch(`http://127.0.0.1:${port}/json/new?about:blank`, { method: "PUT" })).json(); - Network accessline 124
try { const target = await (await fetch(`http://127.0.0.1:${port}/json/new?about:blank`, { method: "PUT" })).json(); const socket = new WebSocket(target.webSocketDebuggerUrl); - Network accessline 125
const target = await (await fetch(`http://127.0.0.1:${port}/json/new?about:blank`, { method: "PUT" })).json();
skills/graphics/isometric-motion/scripts/capture.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/chrome-port.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/chrome-startup.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/drive-actions.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/drive-async-until.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/drive-turn-controller.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/drive.mjs
- Executable scriptline 1
Executable file - Network accessline 128
}; try { const page = await (await fetch(`http://127.0.0.1:${port}/json/new?about:blank`, { method: "PUT" })).json(); - Network accessline 129
try { const page = await (await fetch(`http://127.0.0.1:${port}/json/new?about:blank`, { method: "PUT" })).json(); const socket = new WebSocket(page.webSocketDebuggerUrl); - Network accessline 130
const page = await (await fetch(`http://127.0.0.1:${port}/json/new?about:blank`, { method: "PUT" })).json();
skills/graphics/isometric-motion/scripts/drive.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/enter-key.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/fidelity-cut.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/fidelity-tube-coverage.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/fingerprint.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/inline-kit.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/line-ends.mjs
- Executable scriptline 1
Executable file - Network accessline 98
} else if (C === "A") { const arc = document.createElementNS("http://www.w3.org/2000/svg", "path"); - Network accessline 99
else if (C === "A") { const arc = document.createElementNS("http://www.w3.org/2000/svg", "path"); arc.setAttribute("d", `M${x} ${y}${command}${args}`); - Network accessline 100
const arc = document.createElementNS("http://www.w3.org/2000/svg", "path"); - Network accessline 287
problems.sort((a, b) => b.gap - a.gap); if (show) { const ns = "http://www.w3.org/2000/svg"; - Network accessline 288
if (show) { const ns = "http://www.w3.org/2000/svg"; const overlay = document.createElementNS(ns, "svg"); - Network accessline 289
const ns = "http://www.w3.org/2000/svg";
skills/graphics/isometric-motion/scripts/lines-arcs.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/lines-bezier.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/lines-round.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/lines-rounded-rect.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/lines.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/lines.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/navigation.test.mjs
- Executable scriptline 1
Executable file - Network accessline 19
const server = createServer(); await new Promise((resolve) => server.listen(0, "127.0.0.1", resolve)); target = `http://127.0.0.1:${server.address().port}/`; - Network accessline 20
await new Promise((resolve) => server.listen(0, "127.0.0.1", resolve)); target = `http://127.0.0.1:${server.address().port}/`; await new Promise((resolve) => server.close(resolve)); - Network accessline 21
target = `http://127.0.0.1:${server.address().port}/`;
skills/graphics/isometric-motion/scripts/orbit-sampling.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/react-dots-opacity.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/react-readout-first-write.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/react-readout-target.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/react-solid-seamless.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/react-visibility-target.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/turn-bench.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/turn-check.mjs
- Executable scriptline 1
Executable file - Network accessline 41
const chrome = spawn(chromePath(), ["--headless=new", ...(process.platform === "linux" ? ["--no-sandbox"] : []), ...(process.platform === "win32" ? ["--do-not-de-elevate"] : []), "--remote-debugging-port=0", `--user-data-dir=${profile}`, "- - Network accessline 42
const port = await chromePort(chrome, profile); const page = await (await fetch(`http://127.0.0.1:${port}/json/new?about:blank`, { method: "PUT" })).json(); const socket = new WebSocket(page.webSocketDebuggerUrl); - Network accessline 43
const page = await (await fetch(`http://127.0.0.1:${port}/json/new?about:blank`, { method: "PUT" })).json(); - Network accessline 276
} } return '<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 ' + W + " " + H + '" width="' + w + '" height="' + h + '" shape-rendering="crispEdges"><rect width="100%" height="100%" fill="rgb(0,0,0)"/>' + out.join("") + "</svg>"; - Network accessline 277
} return '<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 ' + W + " " + H + '" width="' + w + '" height="' + h + '" shape-rendering="crispEdges"><rect width="100%" height="100%" fill="rgb(0,0,0)"/>' + out.join("") + "</svg>"; }; - Network accessline 278
return '<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 ' + W + " " + H + '" width="' + w + '" height="' + h + '" shape-rendering="crispEdges"><rect width="100%" height="100%" fill="rgb(0,0,0)"/>' + out.join("") + "</svg>"; - Network accessline 348
const h = H * SCALE; let hidden = null; const svgString = () => '<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 ' + W + " " + H + '" width="' + w + '" height="' + h + '" class="iso iso-svg" data-theme="' + theme + '" style="--anat - Network accessline 349
let hidden = null; const svgString = () => '<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 ' + W + " " + H + '" width="' + w + '" height="' + h + '" class="iso iso-svg" data-theme="' + theme + '" style="--anatomy-paper:var(--anatomy - Network accessline 350
const svgString = () => '<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 ' + W + " " + H + '" width="' + w + '" height="' + h + '" class="iso iso-svg" data-theme="' + theme + '" style="--anatomy-paper:var(--anatomy-card)"><style>' + cs - Network accessline 592
if (argv.includes("--lines")) { const angles = Array.from({ length: 24 }, (_, i) => i * 15); const planted = await page.evaluate(`(() => { window.__isoTurn.set(0); const part = document.querySelector("svg[data-live] [data-p]"); - Network accessline 593
const angles = Array.from({ length: 24 }, (_, i) => i * 15); const planted = await page.evaluate(`(() => { window.__isoTurn.set(0); const part = document.querySelector("svg[data-live] [data-p]"); const el = document.createElementNS("h - Network accessline 594
const planted = await page.evaluate(`(() => { window.__isoTurn.set(0); const part = document.querySelector("svg[data-live] [data-p]"); const el = document.createElementNS("http://www.w3.org/2000/svg", "path"); el.setAttribute("class", "iso-
skills/graphics/isometric-motion/scripts/turn-fidelity.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/turn-group-reference.test.mjs
- Executable scriptline 1
Executable file
skills/graphics/isometric-motion/scripts/turn-split-owner.test.mjs
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/scripts/visual-parity-diff.eval.mjs
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/scripts/visual-parity-diff.mjs
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/test/visual-parity-diff.test.mjs
skills/visual/compare-screenshots/vendor/pixelmatch/index.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pixelmatch/package.json
- Executable scriptline 1
Executable file - Network accessline 27
"repository": { "type": "git", "url": "git+https://github.com/mapbox/pixelmatch.git" - Network accessline 28
"type": "git", "url": "git+https://github.com/mapbox/pixelmatch.git" }, - Network accessline 29
"url": "git+https://github.com/mapbox/pixelmatch.git" - Network accessline 37
"license": "ISC", "bugs": { "url": "https://github.com/mapbox/pixelmatch/issues" - Network accessline 38
"bugs": { "url": "https://github.com/mapbox/pixelmatch/issues" }, - Network accessline 39
"url": "https://github.com/mapbox/pixelmatch/issues" - Network accessline 40
}, "homepage": "https://github.com/mapbox/pixelmatch#readme" } - Network accessline 41
"homepage": "https://github.com/mapbox/pixelmatch#readme"
skills/visual/compare-screenshots/vendor/pngjs/lib/bitmapper.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/bitpacker.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/chunkstream.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/constants.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/crc.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/filter-pack.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/filter-parse-async.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/filter-parse-sync.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/filter-parse.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/format-normaliser.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/interlace.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/packer-async.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/packer-sync.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/packer.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/paeth-predictor.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/parser-async.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/parser-sync.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/parser.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/png-sync.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/png.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/sync-inflate.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/lib/sync-reader.js
- Executable scriptline 1
Executable file
skills/visual/compare-screenshots/vendor/pngjs/package.json
- Executable scriptline 1
Executable file - Network accessline 17
"Eugene Kulabuhov" ], "homepage": "https://github.com/lukeapage/pngjs", - Network accessline 18
], "homepage": "https://github.com/lukeapage/pngjs", "keywords": [ - Network accessline 19
"homepage": "https://github.com/lukeapage/pngjs", - Network accessline 59
"license": "MIT", "bugs": { "url": "https://github.com/pngjs/pngjs/issues" - Network accessline 60
"bugs": { "url": "https://github.com/pngjs/pngjs/issues" }, - Network accessline 61
"url": "https://github.com/pngjs/pngjs/issues"
skills/visual/screenshot-critique/scripts/receipts.eval.mjs
- Executable scriptline 1
#!/usr/bin/env node
skills/visual/screenshot-critique/scripts/receipts.mjs
- Executable scriptline 1
#!/usr/bin/env node
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 10 facts
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionisometric-motion/examples/raptor-engine/build.mjs:890High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionisometric-motion/examples/ripple-tank/build.mjs:530High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionisometric-motion/examples/turning-dial/build.mjs:451High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionisometric-motion/examples/turning-dial/stress.mjs:225High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionisometric-motion/kit/canvas-painter.mjs:2High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionisometric-motion/kit/iso-kit.mjs:534High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionisometric-motion/kit/iso-kit.ts:671High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionisometric-motion/kit/turn-build.mjs:1269High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionisometric-motion/scripts/line-ends.mjs:100High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionisometric-motion/scripts/turn-check.mjs:278High confidence
Signal confidence: 234 facts
- Instruction override signal in prose of the SKILL.mdclaude/SKILL.md:95High confidence
- Instruction override signal in prose of the SKILL.mdclaude/SKILL.md:96High confidence
- Instruction override signal in prose of the SKILL.mdclaude/SKILL.md:97High confidence
- Access to secrets in prose of the SKILL.mdclaude/SKILL.md:112Low confidence
- Broad permissions in the frontmatter of the SKILL.mdcode-review/SKILL.md:1High confidence
- Broad permissions in the frontmatter of the SKILL.mdskills/engineering/code-review/SKILL.md:1High confidence
- Network access in prose of the SKILL.mdcodex/SKILL.md:19Low confidence
- Network access in prose of the SKILL.mdskills/engineering/codex/SKILL.md:19Low confidence
- Network access in prose of the SKILL.mdcodex/SKILL.md:20Low confidence
- Network access in prose of the SKILL.mdskills/engineering/codex/SKILL.md:20Low confidence
- Network access in prose of the SKILL.mdcodex/SKILL.md:21Low confidence
- Network access in prose of the SKILL.mdskills/engineering/codex/SKILL.md:21Low confidence
- Network access in prose of the SKILL.mdcodex/SKILL.md:108Low confidence
- Network access in prose of the SKILL.mdskills/engineering/codex/SKILL.md:108Low confidence
- Network access in prose of the SKILL.mdcodex/SKILL.md:109Low confidence
- Network access in prose of the SKILL.mdskills/engineering/codex/SKILL.md:109Low confidence
- Network access in prose of the SKILL.mdcodex/SKILL.md:110Low confidence
- Network access in prose of the SKILL.mdskills/engineering/codex/SKILL.md:110Low confidence
- Executable script in code of a file that runsratchet-files/scripts/check-file-size.mjs:1High confidence
- Executable script in a comment of a file that runsratchet-files/scripts/install-git-hooks.mjs:1Low confidence
- Executable script in code of a testratchet-files/scripts/install-git-hooks.test.mjs:1Low confidence
- Network access in prose of the SKILL.mdisometric-motion/SKILL.md:8Low confidence
- Executable script in code of a file that runsisometric-motion/examples/arcade-cabinet/build.mjs:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/arcade-cabinet/live.js:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/arcade-cabinet/parts.mjs:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/arcade-cabinet/screen.mjs:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/desk-computer/build.mjs:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/dial-indicator/build.mjs:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/next-token/build.mjs:1High confidence
- Executable script in a comment of a file that runsisometric-motion/examples/next-token/model.mjs:1Low confidence
- Executable script in code of a file that runsisometric-motion/examples/raptor-engine/build.mjs:1High confidence
- Network access in code of a file that runsisometric-motion/examples/raptor-engine/build.mjs:889High confidence
- Network access in code of a file that runsisometric-motion/examples/raptor-engine/build.mjs:890High confidence
- Network access in code of a file that runsisometric-motion/examples/raptor-engine/build.mjs:923High confidence
- Network access in code of a file that runsisometric-motion/examples/raptor-engine/build.mjs:924High confidence
- Network access in code of a file that runsisometric-motion/examples/raptor-engine/build.mjs:925High confidence
- Executable script in code of a file that runsisometric-motion/examples/raptor-engine/live.js:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/ripple-tank/build.mjs:1High confidence
- Network access in code of a file that runsisometric-motion/examples/ripple-tank/build.mjs:529High confidence
- Network access in code of a file that runsisometric-motion/examples/ripple-tank/build.mjs:530High confidence
- Executable script in code of a file that runsisometric-motion/examples/ripple-tank/live.js:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/ripple-tank/model.mjs:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/spot-plate/art.tsx:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/spot-plate/drops.ts:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/spot-plate/fan.ts:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/spot-plate/figure.tsx:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/spot-plate/geometry.ts:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/spot-plate/live.tsx:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/spot-plate/rig.ts:1High confidence
- Executable script in code of a file that runsisometric-motion/examples/test-rig/art.tsx:1High confidence
and 184 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Frontmatter field disable-model-invocation in skills/authoring/audit-agents/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/authoring/audit-agents/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/authoring/audit-agents/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/authoring/audit-agents/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/authoring/audit-agents/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/authoring/audit-agents/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/dzhng-skills/)