Not in the top 1,000 by GitHub stars
LichAmnesia/lich-skills
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/build-until-pass/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ebbc355b6db9 → ebbc355b6db9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ebbc355b6db9
No earlier version was observed for comparison.
skills/debug-hypothesis/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ebbc355b6db9 → ebbc355b6db9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ebbc355b6db9
No earlier version was observed for comparison.
skills/frontend-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ebbc355b6db9 → ebbc355b6db9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ebbc355b6db9
No earlier version was observed for comparison.
skills/go-no-go/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ebbc355b6db9 → ebbc355b6db9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ebbc355b6db9
No earlier version was observed for comparison.
skills/google-analytics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ebbc355b6db9 → ebbc355b6db9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ebbc355b6db9
No earlier version was observed for comparison.
skills/nano-banana/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ebbc355b6db9 → ebbc355b6db9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ebbc355b6db9
No earlier version was observed for comparison.
skills/skills-map/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ebbc355b6db9 → ebbc355b6db9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ebbc355b6db9
No earlier version was observed for comparison.
skills/spec-driven-dev/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ebbc355b6db9 → ebbc355b6db9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ebbc355b6db9
No earlier version was observed for comparison.
skills/spec-driven-dev-v2/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ebbc355b6db9 → ebbc355b6db9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ebbc355b6db9
No earlier version was observed for comparison.
skills/subagent-brief/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ebbc355b6db9 → ebbc355b6db9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ebbc355b6db9
No earlier version was observed for comparison.
skills/tavily-search/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ebbc355b6db9 → ebbc355b6db9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ebbc355b6db9
No earlier version was observed for comparison.
skills/wiki-aggregate/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
ebbc355b6db9 → ebbc355b6db9
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → ebbc355b6db9
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit ebbc355b6db90b445649efba9a58022d049c9ee2
git clone --filter=blob:none --no-checkout https://github.com/LichAmnesia/lich-skills.git .hotskills/lichamnesia-lich-skills && git -C .hotskills/lichamnesia-lich-skills checkout --detach ebbc355b6db90b445649efba9a58022d049c9ee2
# Copy each selected skill directory from .hotskills/lichamnesia-lich-skills into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/LichAmnesia/lich-skills.git .hotskills/lichamnesia-lich-skills && git -C .hotskills/lichamnesia-lich-skills checkout --detach ebbc355b6db90b445649efba9a58022d049c9ee2
# Copy each selected skill directory from .hotskills/lichamnesia-lich-skills into .gemini/skills/<skill-name>/232GitHub stars
1star in 7 days
12skills in this repository
0commits in 30 days
Heat
1.8- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- build-until-pass
skills/build-until-pass - debug-hypothesis
skills/debug-hypothesis - frontend-design
skills/frontend-design - go-no-go
skills/go-no-go - google-analytics
skills/google-analytics - nano-banana
skills/nano-banana - skills-map
skills/skills-map - spec-driven-dev
skills/spec-driven-dev - spec-driven-dev-v2
skills/spec-driven-dev-v2 - subagent-brief
skills/subagent-brief - tavily-search
skills/tavily-search - wiki-aggregate
skills/wiki-aggregate
How it works
build-until-pass
When your agent uses it
Use when a build, typecheck, lint, or test command is failing and you want the agent to drive it to green on its own — run the check, read the errors, apply the smallest fix, re-run, repeat until exit code 0. Stops the human from being the while-loop (run → read error → fix one line → run again) and stops the agent from bulldozing huge speculative rewrites between checks.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
2,799 tokensWhen the skill is activated
Reference documents
40,333 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- When NOT to Use
- The Loop
- Phase 0: LOCK THE CHECK COMMAND
- Phase 1: RUN CHECK
- Phase 2: FIX SMALLEST
- Phase 3: RE-RUN & GATE
- When the Loop Stops Red
- Verification
- The Anti-Thrash Rule
Scripts executed separately
../google-analytics/scripts/analyze.ts../google-analytics/scripts/daily-report.ts../google-analytics/scripts/ga-client.ts../google-analytics/scripts/package.json../nano-banana/scripts/generate_image.py../spec-driven-dev-v2/scripts/governance-check.sh../spec-driven-dev-v2/scripts/task-lint.sh../tavily-search/scripts/search.py
Files
../../.claude-plugin/marketplace.jsonasset1,075 bytes../../.claude-plugin/marketplace.jsonasset1,075 bytes../../.claude-plugin/plugin.jsonasset1,043 bytes../../.claude-plugin/plugin.jsonasset1,043 bytesSKILL.mdcore11,497 bytes../debug-hypothesis/SKILL.mddoc10,307 bytes../frontend-design/LICENSE.txtdoc10,758 bytes../frontend-design/SKILL.mddoc4,275 bytes../go-no-go/README.mddoc6,383 bytes../go-no-go/SKILL.mddoc16,446 bytes../go-no-go/packs/content-creator.ymlasset2,748 bytes../go-no-go/packs/indie-dev.ymlasset2,634 bytes../go-no-go/packs/solo-founder.ymlasset3,515 bytes../go-no-go/packs/solo-founder.ymlasset3,515 bytes../go-no-go/templates/commitment.mddoc3,231 bytes../go-no-go/templates/config.ymlasset4,357 bytes../go-no-go/templates/journal-entry.mddoc581 bytes../google-analytics/.env.exampleasset1,129 bytes../google-analytics/EXAMPLES.mddoc5,287 bytes../google-analytics/REFERENCE.mddoc7,456 bytes../google-analytics/SKILL.mddoc8,174 bytes../google-analytics/scripts/analyze.tsruns13,908 bytes../google-analytics/scripts/daily-report.tsruns22,583 bytes../google-analytics/scripts/ga-client.tsruns10,124 bytes../google-analytics/scripts/package.jsonruns426 bytes../nano-banana/SKILL.mddoc4,438 bytes../nano-banana/scripts/generate_image.pyruns5,617 bytes../skills-map/README.mddoc1,440 bytes../skills-map/SKILL.mddoc8,777 bytes../spec-driven-dev-v2/SKILL.mddoc12,632 bytes../spec-driven-dev-v2/scripts/governance-check.shruns6,737 bytes../spec-driven-dev-v2/scripts/task-lint.shruns3,170 bytes../spec-driven-dev-v2/templates/artifact-registry/RULE.mddoc2,444 bytes../spec-driven-dev-v2/templates/project/PLAN.mddoc2,826 bytes../spec-driven-dev-v2/templates/project/RFC.mddoc2,098 bytes../spec-driven-dev-v2/templates/project/STATE.jsonasset319 bytes../spec-driven-dev-v2/templates/review/REVIEW.mddoc5,039 bytes../spec-driven-dev-v2/templates/sprint/REVIEWS.mddoc1,449 bytes../spec-driven-dev-v2/templates/sprint/SPRINT.mddoc1,638 bytes../spec-driven-dev-v2/templates/sprint/STATE.jsonasset550 bytes../spec-driven-dev-v2/templates/sprint/TASKS.mddoc1,578 bytes../spec-driven-dev-v2/templates/task/TASK.mddoc2,211 bytes../spec-driven-dev/SKILL.mddoc14,167 bytes../spec-driven-dev/templates/plan.mddoc3,655 bytes../spec-driven-dev/templates/review.mddoc3,809 bytes../spec-driven-dev/templates/ship.mddoc5,130 bytes../spec-driven-dev/templates/spec.mddoc4,183 bytes../subagent-brief/SKILL.mddoc6,296 bytes../tavily-search/SKILL.mddoc4,134 bytes../tavily-search/scripts/search.pyruns5,868 bytes../wiki-aggregate/SKILL.mddoc12,283 bytes
Read SKILL.md
# Build Until Pass
A bounded self-correcting loop: run the project's check command, capture its
errors, apply the **smallest** diff that addresses the first failure, re-run,
and repeat until it exits 0 — or until a hard attempt cap is hit.
The core principle: **the check command is the judge, not you.** You do not
declare the build "basically fixed." Green is `exit code 0`. Anything else is
red, and red means another round.
This is the engineering-discipline counterpart to "run it and hope." The cap
exists so the agent backs off instead of burning tokens thrashing on an error
it cannot fix without human input.
debug-hypothesis
When your agent uses it
Use when debugging any non-trivial bug — wrong output, crash, flaky test, performance regression, or "it works locally but not in CI." Forces a scientific-method loop (Observe → Hypothesize → Experiment → Conclude) so the agent stops guessing and starts reasoning. Prevents the
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
2,430 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
- When to Use
- When NOT to Use
- The Debug Loop
- Phase 1: OBSERVE
- Phase 2: HYPOTHESIZE
- Phase 3: EXPERIMENT
- Phase 4: CONCLUDE
- The Anti-Bulldozer Rule
Files
SKILL.mdcore10,307 bytes
Read SKILL.md
# Hypothesis-Driven Debugging
A four-phase loop that turns debugging from "try random fixes and hope" into
a disciplined investigation. Each phase has a goal, hard rules, and a
rationalization table for the excuses an agent will invent to skip it.
The core principle: **you may not write a fix until you have evidence that
your hypothesis is correct.** Guessing is not debugging.
## When to Use
- A test fails and the cause is not immediately obvious
- The same bug has been "fixed" twice and came back
- The agent tried a fix that didn't work — stop it from trying anotherfrontend-design
When your agent uses it
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
823 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
- Design Thinking
- Frontend Aesthetics Guidelines
Files
LICENSE.txtdoc10,758 bytesSKILL.mdcore4,275 bytes
Read SKILL.md
This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices.
The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints.
## Design Thinking
Before coding, understand the context and commit to a BOLD aesthetic direction:
- **Purpose**: What problem does this interface solve? Who uses it?
- **Tone**: Pick an extreme: brutally minimal, maximalist chaos, retro-futuristic, organic/natural, luxury/refined, playful/toy-like, editorial/magazine, brutalist/raw, art deco/geometric, soft/pastel, industrial/utilitarian, etc. There are so many flavors to choose from. Use these for inspiration but design one that is true to the aesthetic direction.
- **Constraints**: Technical requirements (framework, performance, accessibility).
- **Differentiation**: What makes this UNFORGETTABLE? What's the one thing someone will remember?
**CRITICAL**: Choose a clear conceptual direction and execute it with precision. Bold maximalism and refined minimalism both work - the key is intentionality, not intensity.
go-no-go
When your agent uses it
Use BEFORE any spec, plan, or code exists — the Stage 0 gate that decides whether a project should start at all. NO-GO is the default. GO requires passing five framework checks (Differentiation · Audience–Market Fit · Acquisition Channel · Capacity · 7-Factor Wedge), a memory check against your own prior attempts, and a 24-hour pattern-interrupt if enthusiasm-high is detected. Output is a public commitment artifact with pre-mortemed kill criteria (D14/D30/D60/D90 review gates). Triggered by "/go-no-go [project]", any "I want to build / start / take on X" intent, or before opening any new repo or signing any new contract. Pairs with spec-driven-dev (this is Stage 0, that is Stage 1).
What it loads into context
Frontmatter
173 tokensAlways available to the agent
SKILL.md
3,961 tokensWhen the skill is activated
Reference documents
2,602 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- When NOT to Use
- How It Differs From Other Pre-Build Skills
- Loading Constraints
- The Eight Steps
- Output Structure
- Configuration
- Memory Store Modes
- Integration With Other Skills In This Repo
- Common Rationalizations to Watch For
- Red Flags Mid-Session
- Verification Checklist (run before issuing GO)
- Why The Default Is NO-GO
Files
README.mddoc6,383 bytesSKILL.mdcore16,446 bytesSKILL.mdcore16,446 bytespacks/content-creator.ymlasset2,748 bytespacks/indie-dev.ymlasset2,634 bytespacks/solo-founder.ymlasset3,515 bytestemplates/commitment.mddoc3,231 bytestemplates/config.ymlasset4,357 bytestemplates/journal-entry.mddoc581 bytes
Read SKILL.md
# Go / No-Go — Stage 0
> **NO-GO is the default. GO requires evidence.**
Most AI coding skills help you build. This one helps you **not** build.
Half the cost of solo work is starting the wrong thing. Once a repo exists,
sunk cost and identity-protection make it hard to quit. So you grind 3–6
months before admitting the start itself was wrong.
`go-no-go` is the gate before any `/spec`, `/plan`, `/build`. It runs five
framework checks (configurable), a memory check against your own past
attempts, and a 24-hour cooldown if your enthusiasm is too high. The output
is a public commitment doc with pre-mortemed kill criteria. If anythinggoogle-analytics
When your agent uses it
Analyze Google Analytics 4 data — review website performance, identify traffic patterns, diagnose high-bounce pages, compare time periods, and suggest data-driven improvements. Use when the user asks about analytics, website metrics, traffic analysis, conversion rates, user behavior, or performance optimization.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
2,000 tokensWhen the skill is activated
Reference documents
3,262 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Setup
- Scripts
- Workflow
- Run it every day (automation)
- Troubleshooting
- Security & privacy
Scripts executed separately
scripts/analyze.tsscripts/daily-report.tsscripts/ga-client.tsscripts/package.json
Files
.env.exampleasset1,129 bytesEXAMPLES.mddoc5,287 bytesREFERENCE.mddoc7,456 bytesSKILL.mdcore8,174 bytesSKILL.mdcore8,174 bytesSKILL.mdcore8,174 bytesSKILL.mdcore8,174 bytesSKILL.mdcore8,174 bytesSKILL.mdcore8,174 bytesSKILL.mdcore8,174 bytesscripts/analyze.tsruns13,908 bytesscripts/daily-report.tsruns22,583 bytesscripts/ga-client.tsruns10,124 bytesscripts/package.jsonruns426 bytes
Read SKILL.md
# Google Analytics 4 Analysis
Pull GA4 data via the Data API and turn it into actionable, prioritized recommendations. Scripts are **TypeScript** (run with [Bun](https://bun.sh) or `npx tsx`).
## When to use
- "Give me a daily SEO report for this property" → **`daily-report.ts`** (the out-of-the-box default)
- "Review our Google Analytics performance for the last 30 days"
- "How is organic search doing?" / "Which landing pages pull organic traffic?"
- "What are our top traffic sources?"
- "Which pages have the highest bounce rates?"
- "Compare this month vs last month"
- "Why is mobile converting worse than desktop?"
nano-banana
When your agent uses it
Generate or edit images with Google's Nano Banana 2 (`gemini-3.1-flash-image-preview`). Use when the user asks to generate an image, edit an image, or create a picture. Supports 512 / 1K / 2K / 4K resolutions.
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
1,213 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
- When to use
- When NOT to use
- Setup
- Generate
- Edit
- Flags
- Resolution mapping
- Prompt template (generation)
- Prompt template (editing)
- Environment
- Fast checks
- Common failures
- Red flags
- Verification
Scripts executed separately
scripts/generate_image.py
Files
SKILL.mdcore4,438 bytesSKILL.mdcore4,438 bytesSKILL.mdcore4,438 bytesSKILL.mdcore4,438 bytesSKILL.mdcore4,438 bytesSKILL.mdcore4,438 bytesSKILL.mdcore4,438 bytesscripts/generate_image.pyruns5,617 bytes
Read SKILL.md
# Nano Banana 2
Text-to-image and image edit via Google's **Nano Banana 2** model, aka `gemini-3.1-flash-image-preview`. Fast, cheap, high-quality. Returns PNG.
## When to use
- User asks for an image, picture, photo, thumbnail, cover art, poster, icon, etc.
- User provides an input image and wants it modified (background change, object removal, style swap)
- You need a quick visual for a blog post, README, demo, or slide
## When NOT to use
- User wants a video — Nano Banana is image-only
- User wants a pixel-perfect UI mockup — use a design toolskills-map
When your agent uses it
Use at the START of any task, or whenever you are unsure which lich-skill applies. The router for this collection — it maps every lich-skill to the phase of work it belongs to (Decide → Spec → Plan → Build → Debug → Fan-out → Research → Media → Analyze) and walks a decision tree to pick the right one. Prevents the two failure modes of a skill collection: forgetting a skill exists, and reaching for the wrong skill at the wrong phase. Triggered by "/skills-map", "which skill should I use", "what skills do I have", or any moment of skill-selection doubt.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
2,025 tokensWhen the skill is activated
Reference documents
377 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- When NOT to Use
- The Map (by phase of work)
- Decision Tree
- Quick Reference
- Typical Sequences
- Skill Rules
- Anti-Rationalization
- Maintenance
Files
README.mddoc1,440 bytesSKILL.mdcore8,777 bytesSKILL.mdcore8,777 bytes
Read SKILL.md
# Skills Map — the router for lich-skills
> Most skills help you *do* the work. This one helps you pick *which* skill does the work.
A skill collection has a discovery problem: the skills only fire if the agent
remembers they exist and reaches for the right one at the right moment. Left to
chance, the agent forgets `go-no-go` and starts building, or hand-rolls a debug
crawl instead of running `debug-hypothesis`. `skills-map` is the index + decision
tree that closes that gap.
It does three things:
1. **Identify** the phase of work the current task is in.
2. **Route** to the matching skill via the decision tree.spec-driven-dev
When your agent uses it
Use when starting any non-trivial feature, refactor, or new project that will touch more than one file. Drives an AI coding agent through a gated Spec → Plan → Build → Test → Review → Ship lifecycle so work is specified before it is built, verified before it is reviewed, and reviewed before it ships.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
3,394 tokensWhen the skill is activated
Reference documents
4,414 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- When NOT to Use
- The Gated Workflow
- Phase 1: SPEC
- Phase 2: PLAN
- Phase 3: BUILD
- Phase 4: TEST
- Phase 5: REVIEW
- Phase 6: SHIP
- Red Flags: Signs the Agent Is Skipping Phases
- Verification Checklist
- Templates
- Related Skills
Files
SKILL.mdcore14,167 bytesSKILL.mdcore14,167 bytestemplates/plan.mddoc3,655 bytestemplates/review.mddoc3,809 bytestemplates/ship.mddoc5,130 bytestemplates/spec.mddoc4,183 bytes
Read SKILL.md
# Spec-Driven Development
A gated, six-phase workflow for shipping real software with an AI coding
agent. Each phase has a goal, exit criteria, and a rationalization table for
the excuses an agent will invent to skip it. Do not advance until the current
gate is closed.
## When to Use
- Starting a new project, service, or significant feature
- Requirements arrive as a paragraph, screenshot, or vague idea
- The change touches more than one file or subsystem
- You are about to make an architectural decision
- An agent is about to write more than ~100 lines without a planspec-driven-dev-v2
When your agent uses it
Use when an agent will work for hours or days across many files and multiple vertical slices. Drives a three-level Project → Sprint → Task hierarchy with isolated per-task execution, a review round-loop, context packs for subagent reviewers, governance-as-code, and orchestrator-readable state. Designed for long-running drivers like /loop, autoresearch:ship, and goal-driven.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
3,199 tokensWhen the skill is activated
Reference documents
5,217 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use v2 over v1
- The Hierarchy
- Roles
- Phase 0: PROJECT (one-time per project)
- Phase 1: SPRINT (one-time per sprint)
- Phase 2: BUILD — per task, in isolation
- Phase 3: REVIEW — the round loop
- Phase 4: SHIP — per sprint
- Governance — gap #6 made real
- Artifact Registry — gap #7
- Orchestrator contract — gap #8
- Red flags
- Templates
- Relation to v1
Scripts executed separately
scripts/governance-check.shscripts/task-lint.sh
Files
SKILL.mdcore12,632 bytesSKILL.mdcore12,632 bytesSKILL.mdcore12,632 bytesSKILL.mdcore12,632 bytesscripts/governance-check.shruns6,737 bytesscripts/task-lint.shruns3,170 bytestemplates/artifact-registry/RULE.mddoc2,444 bytestemplates/project/PLAN.mddoc2,826 bytestemplates/project/RFC.mddoc2,098 bytestemplates/project/STATE.jsonasset319 bytestemplates/review/REVIEW.mddoc5,039 bytestemplates/sprint/REVIEWS.mddoc1,449 bytestemplates/sprint/SPRINT.mddoc1,638 bytestemplates/sprint/STATE.jsonasset550 bytestemplates/sprint/TASKS.mddoc1,578 bytestemplates/task/TASK.mddoc2,211 bytes
Read SKILL.md
# Spec-Driven Development v2
v1 assumed one agent shipping one feature in one session. v2 assumes an
orchestrator (or a human) driving the agent across many sessions — possibly
for days — and keeps work correct the entire time.
v2 adds:
1. **Three-layer hierarchy** — Project → Sprint → Task
2. **Per-task state** — JSON files an orchestrator can read to resume cold
3. **Review round-loop** — review → feedback → modify → re-review until clean
4. **Worktree isolation** — every task runs in a clean checkout, revertable alone
5. **Context pack** — the briefing a reasoning-blind subagent reviewer needs
6. **Mechanical task gate** — sizing/acceptance/rollback checks enforced by scriptsubagent-brief
When your agent uses it
Use BEFORE invoking the Task or Agent tool to spawn a subagent. Anthropic does NOT share prefix cache across subagents — every subagent cold-starts and re-tokenizes its full prompt (system prompt + tool definitions + the context you handed it). Spawning N subagents with full context = N× token cost; a single fan-out can burn an entire Max-plan day. This skill enforces a pre-flight discipline: compress every subagent prompt into a ≤200-word brief before spawning. Triggers when the agent is about to call Task / Agent tool, especially with long files, full repo dumps, or N parallel subagents on similar work.
What it loads into context
Frontmatter
141 tokensAlways available to the agent
SKILL.md
1,534 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
- When to Use
- When NOT to Use
- The Discipline
- The Brief Template
- Rationalizations to Reject
- After the Brief
- Red Flags in Your Own Output
- Why This Skill Exists
Files
SKILL.mdcore6,296 bytes
Read SKILL.md
# Subagent Brief Discipline
Pre-flight checklist for spawning subagents in Claude Code. The single most
expensive mistake in multi-agent workflows is treating subagents as free
threads. They are not. Each subagent is an independent LLM call that
re-tokenizes the entire prompt you hand it.
There is **no prefix sharing across subagents** in Anthropic's serving stack
today. The multi-agent topology is a known optimization opportunity (see
arXiv 2604.25899 *Pythia: Predictability-Driven Agent-Native LLM Serving*,
2026-04) but has not yet shipped in production. Until it does, the burden
of compression falls on the orchestrating agent.
The math: 20 subagents × 50K shared context = ~1M tokens per fan-out. Onetavily-search
When your agent uses it
Web search and content extraction via the Tavily API. Use when you need real-time web results, citations, or raw article content without a browser. Requires TAVILY_API_KEY.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
1,124 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
- When to use
- When NOT to use
- Setup
- Search
- Extract a single URL
- Output format (default, human-readable)
- Examples
- Environment
- Common failures
- Red flags
- Verification
Scripts executed separately
scripts/search.py
Files
SKILL.mdcore4,134 bytesSKILL.mdcore4,134 bytesSKILL.mdcore4,134 bytesSKILL.mdcore4,134 bytesSKILL.mdcore4,134 bytesSKILL.mdcore4,134 bytesSKILL.mdcore4,134 bytesSKILL.mdcore4,134 bytesSKILL.mdcore4,134 bytesscripts/search.pyruns5,868 bytes
Read SKILL.md
# Tavily Search
Headless web search and content extraction using [Tavily](https://tavily.com). Built for LLM agents — returns clean, summarised results with optional raw article bodies. No browser required.
## When to use
- You need up-to-date web information (news, docs, pricing, facts)
- You want cited sources with URLs for a research/writing task
- You need the full readable body of a URL as markdown
- Brave/Google search is not available or rate-limited
## When NOT to use
- You already have the page in your contextwiki-aggregate
When your agent uses it
Use when you have N≥3 raw research artifacts (notes, podcast summaries, deep-research dumps, daily intel, paper analyses) on one topic and want to lift them into a single structured pack with cross-source claims and provenance — instead of one-shot summarization that loses 90% of intermediate evidence. Treats the N sources as an environment a lite aggregator agent navigates with `inspect` / `search` / `synthesize` tools, rather than concatenating into one prompt.
What it loads into context
Frontmatter
107 tokensAlways available to the agent
SKILL.md
2,758 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
- Why this exists
- When to Use
- When NOT to Use
- The Aggregation Loop
- Process
- Anti-rationalizations
- Verification
- Related skills in this repo
Files
SKILL.mdcore12,283 bytesSKILL.mdcore12,283 bytesSKILL.mdcore12,283 bytesSKILL.mdcore12,283 bytesSKILL.mdcore12,283 bytesSKILL.mdcore12,283 bytesSKILL.mdcore12,283 bytesSKILL.mdcore12,283 bytesSKILL.mdcore12,283 bytesSKILL.mdcore12,283 bytesSKILL.mdcore12,283 bytesSKILL.mdcore12,283 bytes
Read SKILL.md
# Wiki Aggregate — N raw sources → 1 structured pack
A protocol for **agentic aggregation** of long-horizon research material. Inverts the standard "concat all → ask LLM to summarize" pipeline: instead, an aggregator agent navigates the N source files with three tools, building a notes scratchpad with full `path:line` provenance, and finally writes a structured pack (brief / findings / sources / aggregation log).
**Core principle**: don't read everything upfront. Don't merge final answers. Treat the N sources as a queryable environment.
## Why this exists
Three traditional ways to aggregate N parallel research outputs all fail on long-horizon, open-ended tasks:
```
❌ concat all sources into one prompt
→ 200K+ token explosion, attention collapse on long context
Skills included
- build-until-pass
- debug-hypothesis
- frontend-design
- go-no-go
- google-analytics
- nano-banana
- skills-map
- spec-driven-dev
- spec-driven-dev-v2
- subagent-brief
- tavily-search
- wiki-aggregate
Repository facts
- License
- MIT
- Created
- Apr 11, 2026
- Last pushed
- Jun 9, 2026
- Forks
- 26
- Open issues
- 0
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 43 notes
.claude-plugin/marketplace.json:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude-plugin/plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/go-no-go/packs/solo-founder.yml:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notes.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notesskills/go-no-go/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/google-analytics/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/google-analytics/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/google-analytics/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/google-analytics/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/google-analytics/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/google-analytics/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/nano-banana/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/nano-banana/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/nano-banana/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/nano-banana/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/nano-banana/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/nano-banana/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skills-map/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/spec-driven-dev/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 4 dangerous shell commandsin 2 files: skills/nano-banana/SKILL.md:36 skills/tavily-search/SKILL.md:37
- 93 network referencesin 13 files: skills/tavily-search/scripts/search.py:11 skills/google-analytics/REFERENCE.md:72 skills/go-no-go/README.md:118 and 10 more
- 2 obfuscation signalsin 1 file: skills/nano-banana/scripts/generate_image.py:157
- No instruction overrides
- 16 executable scriptsin 8 files: skills/google-analytics/scripts/analyze.ts:1 skills/google-analytics/scripts/daily-report.ts:1 skills/google-analytics/scripts/ga-client.ts:1 and 5 more
- 68 references to secretsin 5 files: skills/tavily-search/scripts/search.py:16 skills/nano-banana/SKILL.md:28 skills/nano-banana/scripts/generate_image.py:33 and 2 more
- No requests to vote in Hot
Show all 183 signals by file
.claude-plugin/marketplace.json
.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "Shen Huang (LichAmnesia)", "url": "https://github.com/LichAmnesia" - Network accessline 6
"name": "Shen Huang (LichAmnesia)", "url": "https://github.com/LichAmnesia" }, - Network accessline 7
"url": "https://github.com/LichAmnesia" - Network accessline 8
}, "homepage": "https://github.com/LichAmnesia/lich-skills", "repository": "https://github.com/LichAmnesia/lich-skills", - Network accessline 9
"homepage": "https://github.com/LichAmnesia/lich-skills", - Network accessline 10
"repository": "https://github.com/LichAmnesia/lich-skills",
skills/frontend-design/LICENSE.txt
- Network accessline 1
Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ - Network accessline 1
Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ - Network accessline 3
http://www.apache.org/licenses/ - Network accessline 3
http://www.apache.org/licenses/ - Network accessline 184
http://www.apache.org/licenses/LICENSE-2.0 - Network accessline 184
http://www.apache.org/licenses/LICENSE-2.0
skills/go-no-go/README.md
- Network accessline 118
- **file** — single markdown file, simplest, zero dependencies - **vault** — semantic search across a markdown knowledge vault. Works with [Obsidian](https://obsidian.md), [Logseq](https://logseq.com), or - Network accessline 118
- **file** — single markdown file, simplest, zero dependencies - **vault** — semantic search across a markdown knowledge vault. Works with [Obsidian](https://obsidian.md), [Logseq](https://logseq.com), or - Network accessline 119
- **vault** — semantic search across a markdown knowledge vault. Works with [Obsidian](https://obsidian.md), [Logseq](https://logseq.com), or [Atomos](https://orangebot.ai/atomos) — a local-first Personal Research OS - Network accessline 119
- **vault** — semantic search across a markdown knowledge vault. Works with [Obsidian](https://obsidian.md), [Logseq](https://logseq.com), or [Atomos](https://orangebot.ai/atomos) — a local-first Personal Research OS - Network accessline 120
[Obsidian](https://obsidian.md), [Logseq](https://logseq.com), or - Network accessline 120
[Obsidian](https://obsidian.md), [Logseq](https://logseq.com), or - Network accessline 121
[Atomos](https://orangebot.ai/atomos) — a local-first Personal Research OS - Network accessline 121
[Atomos](https://orangebot.ai/atomos) — a local-first Personal Research OS - Network accessline 153
MIT. Part of [LichAmnesia/lich-skills](https://github.com/LichAmnesia/lich-skills). - Network accessline 153
MIT. Part of [LichAmnesia/lich-skills](https://github.com/LichAmnesia/lich-skills).
skills/go-no-go/SKILL.md
- Network accessline 329
- **file** — single markdown file, one entry per session, simplest - **vault** — semantic search across a markdown knowledge vault. Works with [Obsidian](https://obsidian.md), [Logseq](https://logseq.com), or - Network accessline 329
- **file** — single markdown file, one entry per session, simplest - **vault** — semantic search across a markdown knowledge vault. Works with [Obsidian](https://obsidian.md), [Logseq](https://logseq.com), or - Network accessline 330
- **vault** — semantic search across a markdown knowledge vault. Works with [Obsidian](https://obsidian.md), [Logseq](https://logseq.com), or [Atomos](https://orangebot.ai/atomos) (a local-first Personal Research OS - Network accessline 330
- **vault** — semantic search across a markdown knowledge vault. Works with [Obsidian](https://obsidian.md), [Logseq](https://logseq.com), or [Atomos](https://orangebot.ai/atomos) (a local-first Personal Research OS - Network accessline 331
[Obsidian](https://obsidian.md), [Logseq](https://logseq.com), or - Network accessline 331
[Obsidian](https://obsidian.md), [Logseq](https://logseq.com), or - Network accessline 332
[Atomos](https://orangebot.ai/atomos) (a local-first Personal Research OS - Network accessline 332
[Atomos](https://orangebot.ai/atomos) (a local-first Personal Research OS
skills/go-no-go/templates/config.yml
- Network accessline 32
# mode: vault # Works with Obsidian (https://obsidian.md), Logseq (https://logseq.com), - Network accessline 32
# mode: vault # Works with Obsidian (https://obsidian.md), Logseq (https://logseq.com), - Network accessline 33
# Works with Obsidian (https://obsidian.md), Logseq (https://logseq.com), - Network accessline 33
# Works with Obsidian (https://obsidian.md), Logseq (https://logseq.com), - Network accessline 34
# or Atomos (https://orangebot.ai/atomos — local-first Personal Research OS - Network accessline 34
# or Atomos (https://orangebot.ai/atomos — local-first Personal Research OS
skills/google-analytics/.env.example
- Access to secretsline 2
[Credential-related source omitted] - Access to secretsline 2
[Credential-related source omitted] - Access to secretsline 23
[Credential-related source omitted] - Access to secretsline 23
[Credential-related source omitted] - Access to secretsline 24
[Credential-related source omitted] - Access to secretsline 24
[Credential-related source omitted]
skills/google-analytics/REFERENCE.md
- Network accessline 72
| `pagePath` | Page URL path | /blog/post-title, /products/item | | `pageTitle` | Page title | Home, Product Page, Blog Post | | `pageLocation` | Full page URL | https://example.com/page | - Network accessline 72
| `pagePath` | Page URL path | /blog/post-title, /products/item | | `pageTitle` | Page title | Home, Product Page, Blog Post | | `pageLocation` | Full page URL | https://example.com/page | - Network accessline 73
| `pageTitle` | Page title | Home, Product Page, Blog Post | | `pageLocation` | Full page URL | https://example.com/page | | `landingPage` | First page of session | /home, /blog/article | - Network accessline 73
| `pageTitle` | Page title | Home, Product Page, Blog Post | | `pageLocation` | Full page URL | https://example.com/page | | `landingPage` | First page of session | /home, /blog/article | - Network accessline 74
| `pageLocation` | Full page URL | https://example.com/page | - Network accessline 74
| `pageLocation` | Full page URL | https://example.com/page | - Network accessline 202
- [GA4 Dimensions & Metrics Explorer](https://ga-dev-tools.google/ga4/dimensions-metrics-explorer/) - Network accessline 202
- [GA4 Dimensions & Metrics Explorer](https://ga-dev-tools.google/ga4/dimensions-metrics-explorer/) - Network accessline 203
- [GA4 Data API Reference](https://developers.google.com/analytics/devguides/reporting/data/v1) - Network accessline 203
- [GA4 Data API Reference](https://developers.google.com/analytics/devguides/reporting/data/v1) - Network accessline 204
- [GA4 Query Explorer](https://ga-dev-tools.google/ga4/query-explorer/) - Network accessline 204
- [GA4 Query Explorer](https://ga-dev-tools.google/ga4/query-explorer/) - Network accessline 205
- [`@google-analytics/data` npm](https://www.npmjs.com/package/@google-analytics/data) - Network accessline 205
- [`@google-analytics/data` npm](https://www.npmjs.com/package/@google-analytics/data)
skills/google-analytics/SKILL.md
- Network accessline 8
Pull GA4 data via the Data API and turn it into actionable, prioritized recommendations. Scripts are **TypeScript** (run with [Bun](https://bun.sh) or `npx tsx`). - Network accessline 8
Pull GA4 data via the Data API and turn it into actionable, prioritized recommendations. Scripts are **TypeScript** (run with [Bun](https://bun.sh) or `npx tsx`).
skills/google-analytics/scripts/analyze.ts
skills/google-analytics/scripts/daily-report.ts
skills/google-analytics/scripts/ga-client.ts
skills/google-analytics/scripts/package.json
skills/nano-banana/SKILL.md
- Network accessline 24
1. Get a Gemini API key: https://aistudio.google.com/app/apikey - Network accessline 24
1. Get a Gemini API key: https://aistudio.google.com/app/apikey - Access to secretsline 28
[Credential-related source omitted] - Access to secretsline 28
[Credential-related source omitted] - Access to secretsline 30
[Credential-related source omitted] - Access to secretsline 30
[Credential-related source omitted] - Dangerous shell operationline 36
command -v uv || curl -LsSf https://astral.sh/uv/install.sh | sh - Dangerous shell operationline 36
command -v uv || curl -LsSf https://astral.sh/uv/install.sh | sh - Network accessline 36
command -v uv || curl -LsSf https://astral.sh/uv/install.sh | sh - Network accessline 36
command -v uv || curl -LsSf https://astral.sh/uv/install.sh | sh - Access to secretsline 74
[Credential-related source omitted] - Access to secretsline 74
[Credential-related source omitted] - Access to secretsline 111
[Credential-related source omitted] - Access to secretsline 111
[Credential-related source omitted] - Access to secretsline 119
[Credential-related source omitted] - Access to secretsline 119
[Credential-related source omitted] - Access to secretsline 128
[Credential-related source omitted] - Access to secretsline 128
[Credential-related source omitted] - Access to secretsline 141
[Credential-related source omitted] - Access to secretsline 141
[Credential-related source omitted]
skills/nano-banana/scripts/generate_image.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 33
[Credential-related source omitted] - Access to secretsline 33
[Credential-related source omitted] - Access to secretsline 36
[Credential-related source omitted] - Access to secretsline 36
[Credential-related source omitted] - Access to secretsline 87
[Credential-related source omitted] - Access to secretsline 87
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted] - Access to secretsline 90
[Credential-related source omitted] - Access to secretsline 90
[Credential-related source omitted] - Access to secretsline 98
[Credential-related source omitted] - Access to secretsline 98
[Credential-related source omitted] - Possible obfuscationline 157
image_data = base64.b64decode(image_data) - Possible obfuscationline 157
image_data = base64.b64decode(image_data)
skills/spec-driven-dev-v2/scripts/governance-check.sh
skills/spec-driven-dev-v2/scripts/task-lint.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Network accessline 20
# - Has at least one acceptance checkbox ("- [ ]") under "## Acceptance" # # Dependency: yq (https://github.com/mikefarah/yq) — `brew install yq`. - Network accessline 20
# - Has at least one acceptance checkbox ("- [ ]") under "## Acceptance" # # Dependency: yq (https://github.com/mikefarah/yq) — `brew install yq`. - Network accessline 22
# Dependency: yq (https://github.com/mikefarah/yq) — `brew install yq`. - Network accessline 22
# Dependency: yq (https://github.com/mikefarah/yq) — `brew install yq`.
skills/tavily-search/SKILL.md
- Access to secretsline 3
[Credential-related source omitted] - Access to secretsline 3
[Credential-related source omitted] - Network accessline 8
Headless web search and content extraction using [Tavily](https://tavily.com). Built for LLM agents — returns clean, summarised results with optional raw article bodies. No browser required. - Network accessline 8
Headless web search and content extraction using [Tavily](https://tavily.com). Built for LLM agents — returns clean, summarised results with optional raw article bodies. No browser required. - Network accessline 25
1. Get a free API key: https://app.tavily.com (1000 free searches/month) - Network accessline 25
1. Get a free API key: https://app.tavily.com (1000 free searches/month) - Access to secretsline 29
[Credential-related source omitted] - Access to secretsline 29
[Credential-related source omitted] - Dangerous shell operationline 37
command -v uv || curl -LsSf https://astral.sh/uv/install.sh | sh - Dangerous shell operationline 37
command -v uv || curl -LsSf https://astral.sh/uv/install.sh | sh - Network accessline 37
command -v uv || curl -LsSf https://astral.sh/uv/install.sh | sh - Network accessline 37
command -v uv || curl -LsSf https://astral.sh/uv/install.sh | sh - Network accessline 78
uv run .../search.py --extract https://example.com/article - Network accessline 78
uv run .../search.py --extract https://example.com/article - Network accessline 109
uv run .../search.py --extract https://blog.example.com/post --json > post.json - Network accessline 109
uv run .../search.py --extract https://blog.example.com/post --json > post.json - Access to secretsline 120
[Credential-related source omitted] - Access to secretsline 120
[Credential-related source omitted] - Access to secretsline 128
[Credential-related source omitted] - Access to secretsline 128
[Credential-related source omitted] - Access to secretsline 141
[Credential-related source omitted] - Access to secretsline 141
[Credential-related source omitted]
skills/tavily-search/scripts/search.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 11
Usage: uv run search.py "query" [flags] uv run search.py --extract https://example.com/article - Network accessline 11
Usage: uv run search.py "query" [flags] uv run search.py --extract https://example.com/article - Network accessline 13
uv run search.py --extract https://example.com/article - Network accessline 13
uv run search.py --extract https://example.com/article - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Network accessline 29
SEARCH_URL = "https://api.tavily.com/search" - Network accessline 29
SEARCH_URL = "https://api.tavily.com/search" - Network accessline 30
EXTRACT_URL = "https://api.tavily.com/extract" - Network accessline 30
EXTRACT_URL = "https://api.tavily.com/extract" - Access to secretsline 34
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Access to secretsline 37
[Credential-related source omitted] - Access to secretsline 37
[Credential-related source omitted] - Access to secretsline 46
[Credential-related source omitted] - Access to secretsline 46
[Credential-related source omitted] - Access to secretsline 48
[Credential-related source omitted] - Access to secretsline 48
[Credential-related source omitted] - Network accessline 68
with httpx.Client(timeout=DEFAULT_TIMEOUT) as client: - Network accessline 68
with httpx.Client(timeout=DEFAULT_TIMEOUT) as client: - Access to secretsline 74
[Credential-related source omitted] - Access to secretsline 74
[Credential-related source omitted] - Access to secretsline 76
[Credential-related source omitted] - Access to secretsline 76
[Credential-related source omitted] - Network accessline 79
"extract_depth": "advanced", } with httpx.Client(timeout=DEFAULT_TIMEOUT) as client: - Network accessline 79
"extract_depth": "advanced", } with httpx.Client(timeout=DEFAULT_TIMEOUT) as client: - Network accessline 80
} with httpx.Client(timeout=DEFAULT_TIMEOUT) as client: response = client.post(EXTRACT_URL, json=payload) - Network accessline 80
} with httpx.Client(timeout=DEFAULT_TIMEOUT) as client: response = client.post(EXTRACT_URL, json=payload) - Network accessline 81
with httpx.Client(timeout=DEFAULT_TIMEOUT) as client: - Network accessline 81
with httpx.Client(timeout=DEFAULT_TIMEOUT) as client: - Access to secretsline 141
[Credential-related source omitted] - Access to secretsline 141
[Credential-related source omitted] - Access to secretsline 165
[Credential-related source omitted] - Access to secretsline 165
[Credential-related source omitted] - Access to secretsline 166
[Credential-related source omitted] - Access to secretsline 166
[Credential-related source omitted] - Access to secretsline 167
[Credential-related source omitted] - Access to secretsline 167
[Credential-related source omitted] - Access to secretsline 172
[Credential-related source omitted] - Access to secretsline 172
[Credential-related source omitted] - Access to secretsline 175
[Credential-related source omitted] - Access to secretsline 175
[Credential-related source omitted]
skills/wiki-aggregate/SKILL.md
- Network accessline 177
id path type captured_at url_or_origin S1 path/to/source_1.md podcast-notes 2026-04-12 https://... - Network accessline 177
id path type captured_at url_or_origin S1 path/to/source_1.md podcast-notes 2026-04-12 https://... - Network accessline 178
S1 path/to/source_1.md podcast-notes 2026-04-12 https://... - Network accessline 178
S1 path/to/source_1.md podcast-notes 2026-04-12 https://...
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.
Signal confidence: 162 facts
- Network access in prose of documentationskills/frontend-design/LICENSE.txt:1Low confidence
- Network access in prose of documentationfrontend-design/LICENSE.txt:1Low confidence
- Network access in prose of documentationskills/frontend-design/LICENSE.txt:3Low confidence
- Network access in prose of documentationfrontend-design/LICENSE.txt:3Low confidence
- Network access in prose of documentationskills/frontend-design/LICENSE.txt:184Low confidence
- Network access in prose of documentationfrontend-design/LICENSE.txt:184Low confidence
- Network access in prose of documentationskills/go-no-go/README.md:118Low confidence
- Network access in prose of documentationgo-no-go/README.md:118Low confidence
- Network access in prose of documentationskills/go-no-go/README.md:119Low confidence
- Network access in prose of documentationgo-no-go/README.md:119Low confidence
- Network access in prose of documentationskills/go-no-go/README.md:120Low confidence
- Network access in prose of documentationgo-no-go/README.md:120Low confidence
- Network access in prose of documentationskills/go-no-go/README.md:121Low confidence
- Network access in prose of documentationgo-no-go/README.md:121Low confidence
- Network access in prose of documentationskills/go-no-go/README.md:153Low confidence
- Network access in prose of documentationgo-no-go/README.md:153Low confidence
- Network access in prose of the SKILL.mdskills/go-no-go/SKILL.md:329Low confidence
- Network access in prose of the SKILL.mdgo-no-go/SKILL.md:329Low confidence
- Network access in prose of the SKILL.mdskills/go-no-go/SKILL.md:330Low confidence
- Network access in prose of the SKILL.mdgo-no-go/SKILL.md:330Low confidence
- Network access in prose of the SKILL.mdskills/go-no-go/SKILL.md:331Low confidence
- Network access in prose of the SKILL.mdgo-no-go/SKILL.md:331Low confidence
- Network access in prose of the SKILL.mdskills/go-no-go/SKILL.md:332Low confidence
- Network access in prose of the SKILL.mdgo-no-go/SKILL.md:332Low confidence
- Network access in prose of documentationskills/google-analytics/REFERENCE.md:72Low confidence
- Network access in prose of documentationgoogle-analytics/REFERENCE.md:72Low confidence
- Network access in prose of documentationskills/google-analytics/REFERENCE.md:73Low confidence
- Network access in prose of documentationgoogle-analytics/REFERENCE.md:73Low confidence
- Network access in prose of documentationskills/google-analytics/REFERENCE.md:74Low confidence
- Network access in prose of documentationgoogle-analytics/REFERENCE.md:74Low confidence
- Network access in prose of documentationskills/google-analytics/REFERENCE.md:202Low confidence
- Network access in prose of documentationgoogle-analytics/REFERENCE.md:202Low confidence
- Network access in prose of documentationskills/google-analytics/REFERENCE.md:203Low confidence
- Network access in prose of documentationgoogle-analytics/REFERENCE.md:203Low confidence
- Network access in prose of documentationskills/google-analytics/REFERENCE.md:204Low confidence
- Network access in prose of documentationgoogle-analytics/REFERENCE.md:204Low confidence
- Network access in prose of documentationskills/google-analytics/REFERENCE.md:205Low confidence
- Network access in prose of documentationgoogle-analytics/REFERENCE.md:205Low confidence
- Network access in prose of the SKILL.mdskills/google-analytics/SKILL.md:8Low confidence
- Network access in prose of the SKILL.mdgoogle-analytics/SKILL.md:8Low confidence
- Executable script in code of a file that runsskills/google-analytics/scripts/analyze.ts:1High confidence
- Executable script in code of a file that runsgoogle-analytics/scripts/analyze.ts:1High confidence
- Executable script in code of a file that runsskills/google-analytics/scripts/daily-report.ts:1High confidence
- Executable script in code of a file that runsgoogle-analytics/scripts/daily-report.ts:1High confidence
- Executable script in code of a file that runsskills/google-analytics/scripts/ga-client.ts:1High confidence
- Executable script in code of a file that runsgoogle-analytics/scripts/ga-client.ts:1High confidence
- Executable script in code of a file that runsskills/google-analytics/scripts/package.json:1High confidence
- Executable script in code of a file that runsgoogle-analytics/scripts/package.json:1High confidence
- Network access in prose of the SKILL.mdskills/nano-banana/SKILL.md:24Low confidence
- Network access in prose of the SKILL.mdnano-banana/SKILL.md:24Low confidence
and 112 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/build-until-pass/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/build-until-pass/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Native | Manifest gemini-extension.json | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/build-until-pass/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/build-until-pass/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.
