Not in the top 1,000 by GitHub stars
skilld-dev/skilld
Open-source, privacy friendly skills.sh alternative for humans and 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
packages/harness/test/fixtures/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d19d25b79cfd → d19d25b79cfd
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d19d25b79cfd
No earlier version was observed for comparison.
skills/generate-package-skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
d19d25b79cfd → d19d25b79cfd
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → d19d25b79cfd
No earlier version was observed for comparison.
skills/generate-project-skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d19d25b79cfd → d19d25b79cfd
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d19d25b79cfd
No earlier version was observed for comparison.
skills/review-skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d19d25b79cfd → d19d25b79cfd
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d19d25b79cfd
No earlier version was observed for comparison.
skills/skilld/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d19d25b79cfd → d19d25b79cfd
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d19d25b79cfd
No earlier version was observed for comparison.
skills/skilld-tui-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d19d25b79cfd → d19d25b79cfd
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d19d25b79cfd
No earlier version was observed for comparison.
skills/update-package-skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d19d25b79cfd → d19d25b79cfd
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d19d25b79cfd
No earlier version was observed for comparison.
tests/fixtures/v3-rust/local-skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
d19d25b79cfd → d19d25b79cfd
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → d19d25b79cfd
No earlier version was observed for comparison.
Verified commit d19d25b79cfdf6bef33bd8f981f9dca46ffcffa2
git clone --filter=blob:none --no-checkout https://github.com/skilld-dev/skilld.git .hotskills/skilld-dev-skilld && git -C .hotskills/skilld-dev-skilld checkout --detach d19d25b79cfdf6bef33bd8f981f9dca46ffcffa2
# Copy each selected skill directory from .hotskills/skilld-dev-skilld into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/skilld-dev/skilld.git .hotskills/skilld-dev-skilld && git -C .hotskills/skilld-dev-skilld checkout --detach d19d25b79cfdf6bef33bd8f981f9dca46ffcffa2
# Copy each selected skill directory from .hotskills/skilld-dev-skilld into .agents/skills/<skill-name>/Heat
4.6- 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
- fixture-skill
packages/harness/test/fixtures/skill - generate-package-skill
skills/generate-package-skill - generate-project-skill
skills/generate-project-skill - review-skill
skills/review-skill - skilld
skills/skilld - skilld-tui-design
skills/skilld-tui-design - update-package-skill
skills/update-package-skill - local-skill
tests/fixtures/v3-rust/local-skill
How it works
fixture-skill
When your agent uses it
Use this Skill to exercise the Harness review fixture.
What it loads into context
Frontmatter
18 tokensAlways available to the agent
SKILL.md
29 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
../../../../../.claude-plugin/marketplace.jsonasset632 bytes../../../../../.claude-plugin/plugin.jsonasset384 bytesSKILL.mdcore147 bytes
generate-package-skill
When your agent uses it
Generate or update an Agent Skill that teaches consumers one npm or local package the user maintains, including framework modules and wrappers. Tests each example against the installed version. Use when a maintainer asks for a package Skill, a SKILL.md for their library, or a Skill update after a release.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
3,145 tokensWhen the skill is activated
Reference documents
195 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Inputs
- 1. Research
- 2. Test the examples
- 3. Write
- 4. Check and report
Scripts executed separately
scripts/extract-blocks.mjsscripts/serve-fixture.mjs
Files
SKILL.mdcore13,860 bytesSKILL.mdcore13,860 bytesSKILL.mdcore13,860 bytesSKILL.mdcore13,860 bytesSKILL.mdcore13,860 bytesSKILL.mdcore13,860 bytesSKILL.mdcore13,860 bytesSKILL.mdcore13,860 bytesSKILL.mdcore13,860 bytesSKILL.mdcore13,860 bytesSKILL.mdcore13,860 bytesSKILL.mdcore13,860 bytesassets/harness-request.mddoc939 bytesscripts/extract-blocks.mjsruns4,299 bytesscripts/serve-fixture.mjsruns9,635 bytes
Read SKILL.md
# Generate a package Skill
Write a short Skill that stops an Agent from misusing one package version.
The reader knows the language, the framework, and the domain. Write only what it would get wrong.
## Inputs
Take a package name, directory, or prepared source. Ask for the destination only when it is missing.
In a monorepo, put the Skill in the published package directory.
Write one Skill per installed package, unless a second package has distinct users.
Skip an internal package, whose users are the repository's own packages, such as a shared engine or types package. Report why, and write nothing.
`assets/` holds the Harness request. A direct run ignores it.
## 1. ResearchView the complete source on GitHubgenerate-project-skill
When your agent uses it
Generate or update an Agent Skill from the observed workflows, boundaries, and conventions of one software project.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
1,064 tokensWhen the skill is activated
Reference documents
103 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Inputs
- Inspect
- Project navigation
- Output
- Cross-Agent portability
- Quality checks
Files
SKILL.mdcore5,238 bytesSKILL.mdcore5,238 bytesSKILL.mdcore5,238 bytesSKILL.mdcore5,238 bytesSKILL.mdcore5,238 bytesassets/harness-request.mddoc473 bytes
Read SKILL.md
# Generate a project Skill
Create a compact, searchable Skill from the project itself.
This Skill is for maintainers who author a draft Skill they own.
## Inputs
Use the project directory or prepared project source.
Ask for the destination only when the request does not provide one.
## Inspect
1. Read project instructions and decision records first.
2. Read manifests, exported entry points, and build configuration.View the complete source on GitHubreview-skill
When your agent uses it
Review an Agent Skill for valid structure, clear triggers, usable instructions, current evidence, and risky or unclear actions.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
583 tokensWhen the skill is activated
Reference documents
158 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Checks
Files
SKILL.mdcore2,719 bytesassets/harness-request.mddoc602 bytes
Read SKILL.md
# Review a Skill
Review the supplied Skill as an Agent would use it.
## Checks
1. Confirm `SKILL.md` exists and its parent directory matches its name.
2. Confirm frontmatter uses supported fields and valid values.
3. Confirm the description says what the Skill does and when to use it, in the third person, with the terms a user types.
4. Follow every linked reference and script.
5. Report missing or broken links.
6. Reject symbolic links, special files, and paths that leave the Skill directory.
7. Check instructions for missing inputs, unclear outcomes, and silent failure paths.
8. Check commands for destructive scope, credential exposure, and unverified downloads.View the complete source on GitHubskilld
When your agent uses it
Operate skilld CLI for Skill discovery, use, installation, inspection, updates, authentication, configuration, restoration, and removal, including Repository, curator, and collection refs. Also read the skilld.dev registry (view, browse, trending, tracks, curators, index) and act for the user's skilld.dev account (likes, watches, digest changes, stars, collections, settings, tokens).
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
4,464 tokensWhen the skill is activated
Reference documents
1,653 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Use Agent output
- Sync declared Skills
- Search for a Skill
- Run a Skill
- Author a Skill from the user's own code
- List the Skills a Repository, curator, or collection names
- Read the registry
- Choose the source
- Install a Skill
- Fork a Skill
- Restore locked Skills
- Inspect installed Skills
- Check and apply updates
- Verify source integrity
- Report outdated and unmanaged Skills
- Review Skill files across projects
- Account and configuration
- Remove a Skill
- Handle failures
Files
SKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesSKILL.mdcore19,926 bytesreferences/account-and-configuration.mddoc2,964 bytesreferences/declared-skills.mddoc4,710 bytes
Read SKILL.md
# Use skilld CLI
Use skilld CLI to find, load, install, inspect, restore, update, verify, and remove Skills.
Run a Skill first. Install a Skill only when the user asks to keep it.
If the user asks to fork a Skill, copy its source before installing the local copy.
## Use Agent output
Use `--json` with `search`, `run`, and `update --check`.
Use `--json` with `view` of a registry ref, and with every registry and account command below.
Their `data` is the skilld.dev answer. A command whose answer has no body returns `data: null`.
Use `--json` with `sync` and `sync --check` for declared Skills.
Use `doctor --json` for read-only Skill discovery and cleanup findings.View the complete source on GitHubskilld-tui-design
When your agent uses it
Designs and verifies skilld CLI output, terminal pickers, and full-screen flows. Use for terminal colours, loading feedback, keyboard controls, layout, errors, or end-to-end CLI UX reviews.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
1,170 tokensWhen the skill is activated
Reference documents
540 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Establish the contract
- Put the decision first
- Use colour with independent cues
- Make state and input agree
- Explain waiting and outcomes
- Verify the whole journey
Files
SKILL.mdcore6,272 bytesSKILL.mdcore6,272 bytesSKILL.mdcore6,272 bytesSKILL.mdcore6,272 bytesreferences/source-review.mddoc2,436 bytes
Read SKILL.md
# Design skilld CLI interactions
Build the user's whole command journey, including failure, cancellation, and the return to their shell.
Read [source decisions](references/source-review.md) for the two reviewed Skills and their exact revisions.
## Establish the contract
Read the project's `GLOSSARY.md`, `COPY.md`, and `VISION.md` when present.
Keep canonical nouns and strings. Use short sentences with one idea each.
Inspect the command parser, output renderer, and terminal lifecycle before changing behavior.
Classify each affected surface as static output, a picker, a prompt, or a full-screen view.
Include command help, parser errors, startup notices, and progress indicators in the inventory.
List its starting state, successful outcome, expected failures, and cancellation behavior.
Keep the existing JSON envelope, streams, and exit codes unless the task changes that contract.View the complete source on GitHubupdate-package-skill
When your agent uses it
Updates an existing package Skill for a new release of its npm or local package by testing only what changed since the version the Skill names. Use when a maintainer asks to refresh a package Skill after a release, or when a SKILL.md names an older tested version than the package.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
986 tokensWhen the skill is activated
Reference documents
208 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Inputs
- 1. Copy, then diff
- 2. Map changes to the Skill
- 3. Test the affected lines
- 4. Edit
- 5. Report
Files
SKILL.mdcore4,478 bytesSKILL.mdcore4,478 bytesassets/harness-request.mddoc938 bytes
Read SKILL.md
# Update a package Skill
Bring an existing package Skill to a new package version with the smallest correct edit.
The current Skill was tested against an earlier version. Trust what the release did not touch.
To write a Skill from nothing, use `generate-package-skill`.
## Inputs
- The current Skill directory, and the package at the new version: a name and version, a directory, or prepared source.
- The tested version is the version the Skill's first paragraph names. If it names none, stop and report that the Skill needs a full rewrite.
- If the tested version equals the new version, change nothing and report that.
## 1. Copy, then diff
View the complete source on GitHublocal-skill
When your agent uses it
Fixture Skill for the Rust and WASIp2 command proof.
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
37 tokensWhen the skill is activated
Reference documents
8 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore162 bytesreferences/check.mddoc30 bytes
Read SKILL.md
# Local Skill
Read `references/check.md` before returning a result.View the complete source on GitHubSkills included
- fixture-skill
- generate-package-skill
- generate-project-skill
- review-skill
- skilld
- skilld-tui-design
- update-package-skill
- local-skill
Repository facts
- License
- MIT
- Created
- Feb 3, 2026
- Last pushed
- Oct 10, 2026
- Forks
- 10
- Open issues
- 1
- Project activity
- Active
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 63 notes
skills/generate-package-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/generate-package-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/generate-package-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/generate-package-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/generate-package-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/generate-package-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/generate-package-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/generate-package-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/generate-package-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/generate-package-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/generate-package-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/generate-project-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/generate-project-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/generate-project-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/generate-project-skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skilld/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skilld/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skilld/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skilld/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/skilld/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 45 network referencesin 7 files: generate-package-skill/SKILL.md:135 .claude-plugin/marketplace.json:4 skilld-tui-design/references/source-review.md:9 and 4 more
- No hidden or obfuscated text
- No instruction overrides
- 2 executable scriptsin 2 files: generate-package-skill/scripts/extract-blocks.mjs:1 generate-package-skill/scripts/serve-fixture.mjs:1
- 1 reference to secretsin 1 file: skilld/references/account-and-configuration.md:18
- No requests to vote in Hot
Show all 48 signals by file
.claude-plugin/marketplace.json
- Network accessline 4
"owner": { "name": "skilld", "url": "https://skilld.dev" - Network accessline 5
"name": "skilld", "url": "https://skilld.dev" }, - Network accessline 6
"url": "https://skilld.dev" - Network accessline 11
"source": "./", "description": "The skilld-maintained Skills and the skilld.dev discovery MCP server. Search curated Skills, then run or install them with the skilld CLI.", "homepage": "https://skilld.dev/developers", - Network accessline 12
"description": "The skilld-maintained Skills and the skilld.dev discovery MCP server. Search curated Skills, then run or install them with the skilld CLI.", "homepage": "https://skilld.dev/developers", "mcpServers": { - Network accessline 13
"homepage": "https://skilld.dev/developers", - Network accessline 15
"skilld": { "type": "http", "url": "https://skilld.dev/api/mcp" - Network accessline 16
"type": "http", "url": "https://skilld.dev/api/mcp" } - Network accessline 17
"url": "https://skilld.dev/api/mcp"
.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "Harlan Wilton", "url": "https://harlanzw.com" - Network accessline 6
"name": "Harlan Wilton", "url": "https://harlanzw.com" }, - Network accessline 7
"url": "https://harlanzw.com" - Network accessline 8
}, "homepage": "https://skilld.dev", "repository": "https://github.com/skilld-dev/skilld", - Network accessline 9
"homepage": "https://skilld.dev", - Network accessline 10
"repository": "https://github.com/skilld-dev/skilld",
skills/generate-package-skill/SKILL.md
- Network accessline 135
Before finishing, extract every block with [scripts/extract-blocks.mjs](scripts/extract-blocks.mjs): `node SKILL_DIR/scripts/extract-blocks.mjs SKILL.md DIR`. Copy each block into the fixture and run it unchanged. Never test a copy you edit - Network accessline 137
`--replace https://example.com=http://localhost:PORT` swaps a placeholder. `DIR/blocks.json` maps each block to its line. - Network accessline 152
- If the Skill sits inside the published package directory, add its directory to `files` in `package.json`. After one build, list packed files with `npm pack --dry-run --ignore-scripts`; `pnpm pack` rejects that flag. - For npm packages, us - Network accessline 153
- For npm packages, use `skills/<name>/SKILL.md` beside the package's `package.json`. Include linked files in the tarball. [pnpm 12.11 and newer](https://pnpm.io/agent-skills) link Skills from approved direct dependencies. Document `pnp - Network accessline 154
[pnpm 12.11 and newer](https://pnpm.io/agent-skills) link Skills from approved direct dependencies. - Network accessline 163
<a href="https://skilld.dev/gh/OWNER/REPOSITORY"> - Network accessline 164
<picture> <source media="(prefers-color-scheme: dark)" srcset="https://skilld.dev/b/OWNER/REPOSITORY?theme=dark"> <source media="(prefers-color-scheme: light)" srcset="https://skilld.dev/b/OWNER/REPOSITORY?theme=light"> - Network accessline 165
<source media="(prefers-color-scheme: dark)" srcset="https://skilld.dev/b/OWNER/REPOSITORY?theme=dark"> - Network accessline 166
<source media="(prefers-color-scheme: light)" srcset="https://skilld.dev/b/OWNER/REPOSITORY?theme=light"> - Network accessline 167
<img alt="Skill repository on skilld.dev" src="https://skilld.dev/b/OWNER/REPOSITORY?theme=light"> - Network accessline 173
> [!TIP] > Using an AI agent? Get the PACKAGE Skill on [skilld.dev/gh/OWNER/REPOSITORY](https://skilld.dev/gh/OWNER/REPOSITORY). - Network accessline 174
> Using an AI agent? Get the PACKAGE Skill on [skilld.dev/gh/OWNER/REPOSITORY](https://skilld.dev/gh/OWNER/REPOSITORY).
skills/generate-package-skill/scripts/extract-blocks.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 6
// Block N goes to OUT_DIR/N/. A first line that names a path, such as `// server/api/search.ts`, // `# scripts/check.sh`, or `<!-- app/pages/index.vue -->`, sets the file name. Otherwise the file is `block.EXT`. // `--replace` swaps a plac - Network accessline 7
// `# scripts/check.sh`, or `<!-- app/pages/index.vue -->`, sets the file name. Otherwise the file is `block.EXT`. // `--replace` swaps a placeholder in every block, such as `https://example.com=http://localhost:3000`. // OUT_DIR/blocks.jso - Network accessline 8
// `--replace` swaps a placeholder in every block, such as `https://example.com=http://localhost:3000`.
skills/generate-package-skill/scripts/serve-fixture.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 5
// // The script replaces `{port}` in each argument and sets PORT, NITRO_PORT, and NUXT_PORT. // It prints `ready http://localhost:PORT` on stderr when the server answers. - Network accessline 6
// The script replaces `{port}` in each argument and sets PORT, NITRO_PORT, and NUXT_PORT. // It prints `ready http://localhost:PORT` on stderr when the server answers. // `--fetch` asks for HTML. `--fetch-raw` asks for any type, such as an - Network accessline 7
// It prints `ready http://localhost:PORT` on stderr when the server answers. - Network accessline 107
const options = parseArgs(process.argv.slice(2)) const port = await freePort() const origin = `http://localhost:${port}` - Network accessline 108
const port = await freePort() const origin = `http://localhost:${port}` const [command, ...args] = options.command.map(part => part.replaceAll('{port}', String(port))) - Network accessline 109
const origin = `http://localhost:${port}`
skills/generate-project-skill/SKILL.md
- Network accessline 70
Keep one source Skill for Claude Code, Codex, Gemini CLI, and other compatible Agents. Their discovery paths differ. Keep installation instructions outside the generated Skill. The [Agent Skills specification](https://agentskills.io/specifi - Network accessline 72
The [Agent Skills specification](https://agentskills.io/specification) defines the shared format.
skills/skilld-tui-design/references/source-review.md
- Network accessline 9
Repository: `diegomarino/tui-design`. Revision: `57c199f22dbf04f057c279431d45346cc1fd5dcd`. [Reviewed SKILL.md](https://github.com/diegomarino/tui-design/blob/57c199f22dbf04f057c279431d45346cc1fd5dcd/skills/tui-design/SKILL.md). - Network accessline 10
Revision: `57c199f22dbf04f057c279431d45346cc1fd5dcd`. [Reviewed SKILL.md](https://github.com/diegomarino/tui-design/blob/57c199f22dbf04f057c279431d45346cc1fd5dcd/skills/tui-design/SKILL.md). License: MIT, declared in the reviewed Skill fron - Network accessline 11
[Reviewed SKILL.md](https://github.com/diegomarino/tui-design/blob/57c199f22dbf04f057c279431d45346cc1fd5dcd/skills/tui-design/SKILL.md). - Network accessline 34
Repository: `NVIDIA/OpenShell`. Revision: `fb8f6c0885127fe4ca29993739131a3bdbaed477`. [Reviewed SKILL.md](https://github.com/NVIDIA/OpenShell/blob/fb8f6c0885127fe4ca29993739131a3bdbaed477/.agents/skills/tui-development/SKILL.md). - Network accessline 35
Revision: `fb8f6c0885127fe4ca29993739131a3bdbaed477`. [Reviewed SKILL.md](https://github.com/NVIDIA/OpenShell/blob/fb8f6c0885127fe4ca29993739131a3bdbaed477/.agents/skills/tui-development/SKILL.md). License: [Apache-2.0 at the reviewed revis - Network accessline 36
[Reviewed SKILL.md](https://github.com/NVIDIA/OpenShell/blob/fb8f6c0885127fe4ca29993739131a3bdbaed477/.agents/skills/tui-development/SKILL.md). - Network accessline 37
License: [Apache-2.0 at the reviewed revision](https://github.com/NVIDIA/OpenShell/blob/fb8f6c0885127fe4ca29993739131a3bdbaed477/LICENSE).
skills/skilld/references/account-and-configuration.md
- Access to secretsline 18
[Credential-related source omitted]
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: 33 facts
- Network access in prose of the SKILL.mdgenerate-package-skill/SKILL.md:135Low confidence
- Network access in prose of the SKILL.mdgenerate-package-skill/SKILL.md:137Low confidence
- Network access in prose of the SKILL.mdgenerate-package-skill/SKILL.md:152Low confidence
- Network access in prose of the SKILL.mdgenerate-package-skill/SKILL.md:153Low confidence
- Network access in prose of the SKILL.mdgenerate-package-skill/SKILL.md:154Low confidence
- Network access in code of the SKILL.mdgenerate-package-skill/SKILL.md:163High confidence
- Network access in code of the SKILL.mdgenerate-package-skill/SKILL.md:164High confidence
- Network access in code of the SKILL.mdgenerate-package-skill/SKILL.md:165High confidence
- Network access in code of the SKILL.mdgenerate-package-skill/SKILL.md:166High confidence
- Network access in code of the SKILL.mdgenerate-package-skill/SKILL.md:167High confidence
- Network access in code of the SKILL.mdgenerate-package-skill/SKILL.md:173High confidence
- Network access in code of the SKILL.mdgenerate-package-skill/SKILL.md:174High confidence
- Executable script in code of a file that runsgenerate-package-skill/scripts/extract-blocks.mjs:1High confidence
- Network access in a comment of a file that runsgenerate-package-skill/scripts/extract-blocks.mjs:6Low confidence
- Network access in a comment of a file that runsgenerate-package-skill/scripts/extract-blocks.mjs:7Low confidence
- Network access in a comment of a file that runsgenerate-package-skill/scripts/extract-blocks.mjs:8Low confidence
- Executable script in code of a file that runsgenerate-package-skill/scripts/serve-fixture.mjs:1High confidence
- Network access in a comment of a file that runsgenerate-package-skill/scripts/serve-fixture.mjs:5Low confidence
- Network access in a comment of a file that runsgenerate-package-skill/scripts/serve-fixture.mjs:6Low confidence
- Network access in a comment of a file that runsgenerate-package-skill/scripts/serve-fixture.mjs:7Low confidence
- Network access in code of a file that runsgenerate-package-skill/scripts/serve-fixture.mjs:107High confidence
- Network access in code of a file that runsgenerate-package-skill/scripts/serve-fixture.mjs:108High confidence
- Network access in code of a file that runsgenerate-package-skill/scripts/serve-fixture.mjs:109High confidence
- Network access in prose of the SKILL.mdgenerate-project-skill/SKILL.md:70Low confidence
- Network access in prose of the SKILL.mdgenerate-project-skill/SKILL.md:72Low confidence
- Network access in prose of documentationskilld-tui-design/references/source-review.md:9Low confidence
- Network access in prose of documentationskilld-tui-design/references/source-review.md:10Low confidence
- Network access in prose of documentationskilld-tui-design/references/source-review.md:11Low confidence
- Network access in prose of documentationskilld-tui-design/references/source-review.md:34Low confidence
- Network access in prose of documentationskilld-tui-design/references/source-review.md:35Low confidence
- Network access in prose of documentationskilld-tui-design/references/source-review.md:36Low confidence
- Network access in prose of documentationskilld-tui-design/references/source-review.md:37Low confidence
- Access to secrets in prose of documentationskilld/references/account-and-configuration.md:18Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md packages/harness/test/fixtures/skill/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md packages/harness/test/fixtures/skill/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md packages/harness/test/fixtures/skill/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md packages/harness/test/fixtures/skill/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.