Not in the top 1,000 by GitHub stars
Kyure-A/agent-skills-nix
Declarative management of Agent Skills on Nix
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
examples/agent-plugin/skills/pdf/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
f48aa227f3d1 → f48aa227f3d1
test/fixtures/agent-plugin/escaping/hello/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
f48aa227f3d1 → f48aa227f3d1
test/fixtures/agent-plugin/invalid-frontmatter/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
f48aa227f3d1 → f48aa227f3d1
test/fixtures/agent-plugin/valid/hello/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
f48aa227f3d1 → f48aa227f3d1
test/fixtures/escaping-skill-target/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
f48aa227f3d1 → f48aa227f3d1
test/fixtures/multi-skill-shared-root/skill-a/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
f48aa227f3d1 → f48aa227f3d1
test/fixtures/multi-skill-shared-root/skill-b/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
f48aa227f3d1 → f48aa227f3d1
test/fixtures/nested-skills/cat-a/skill-1/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
f48aa227f3d1 → f48aa227f3d1
test/fixtures/nested-skills/cat-a/skill-2/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
f48aa227f3d1 → f48aa227f3d1
test/fixtures/rewrite-skill/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
f48aa227f3d1 → f48aa227f3d1
test/fixtures/source-root-symlinks/skill-a/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
f48aa227f3d1 → f48aa227f3d1
test/fixtures/test-skill/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
f48aa227f3d1 → f48aa227f3d1
Heat
6.4- 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
- pdf
examples/agent-plugin/skills/pdf - hello
test/fixtures/agent-plugin/escaping/hello - not-hello
test/fixtures/agent-plugin/invalid-frontmatter - hello
test/fixtures/agent-plugin/valid/hello - escaping-skill-target
test/fixtures/escaping-skill-target - skill-a
test/fixtures/multi-skill-shared-root/skill-a - skill-b
test/fixtures/multi-skill-shared-root/skill-b - skill-1
test/fixtures/nested-skills/cat-a/skill-1 - skill-2
test/fixtures/nested-skills/cat-a/skill-2 - rewrite-skill
test/fixtures/rewrite-skill - skill-a
test/fixtures/source-root-symlinks/skill-a - test-skill
test/fixtures/test-skill
How it works
When your agent uses it
Summarize document text and identify its main claims, evidence, and unanswered questions.
What it loads into context
Frontmatter
23 tokensAlways available to the agent
SKILL.md
69 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.mdcore348 bytes
Read SKILL.md
When the user provides document text, return:
1. A concise summary.
2. The main claims and supporting evidence.
3. Important limitations or unanswered questions.
Do not invent details that are absent from the supplied text.hello
When your agent uses it
Contains a symlink that intentionally resolves outside its declared source root.
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
36 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.mdcore186 bytesSKILL.mdcore186 bytesSKILL.mdcore186 bytesoutside/secret.txtdoc21 bytes
Read SKILL.md
# Escaping symlink fixture
The exporter must reject this source tree.not-hello
When your agent uses it
Intentionally has a name that does not match its exported directory.
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
42 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.mdcore198 bytes
Read SKILL.md
# Invalid frontmatter fixture
This skill must be rejected when it is exported as `hello`.hello
When your agent uses it
Greets a user and reads a bundled shared message. Use this fixture when testing portable Agent Plugin exports.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
65 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
Scripts executed separately
scripts/greet.sh
Files
.fixture-configasset23 bytesSKILL.mdcore289 bytesscripts/greet.shruns94 bytesshared/message.txtdoc61 bytes
Read SKILL.md
# Hello
Run `scripts/greet.sh`, and consult `shared/message.txt` for the shared fixture data.When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
14 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.mdcore69 bytesSKILL.mdcore69 bytes
Read SKILL.md
# Escaping Skill
This skill lives outside the declared source root.When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
14 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.mdcore55 bytesSKILL.mdcore55 bytesshared/data.txtdoc24 bytes
Read SKILL.md
# Skill A
Reads from a shared dir at the source root.When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
14 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.mdcore54 bytesshared/data.txtdoc24 bytes
When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
11 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.mdcore37 bytes
When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
12 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.mdcore45 bytes
When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
54 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.mdcore203 bytes
Read SKILL.md
# Rewrite Test Skill
Run jq to process JSON:
jq '.key' input.json
You can also pipe: cat file.json | jq '.key'
Already local: ./jq --help
Run bunx for multi-binary package coverage:
bunx --versionWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
16 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.mdcore75 byteschain/secret.txtdoc21 bytesoutside/secret.txtdoc21 bytesshared/data.txtdoc20 bytes
Read SKILL.md
# Skill A
Uses a shared directory through a source-root-relative symlink.When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
11 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.mdcore50 bytes
Skills included
- hello
- not-hello
- hello
Repository facts
- License
- MIT
- Created
- Dec 22, 2025
- Last pushed
- Nov 2, 2026
- Forks
- 22
- Open issues
- 0
- Project activity
- Active
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 4 notes
test/fixtures/agent-plugin/escaping/hello/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtest/fixtures/agent-plugin/escaping/hello/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtest/fixtures/escaping-skill-target/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtest/fixtures/multi-skill-shared-root/skill-a/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- No network access
- No hidden or obfuscated text
- No instruction overrides
- 1 executable scriptin 1 file: hello/scripts/greet.sh:1
- No access to secrets
- No requests to vote in Hot
Show the signal with its line
test/fixtures/agent-plugin/valid/hello/scripts/greet.sh
- Executable scriptline 1
#!/usr/bin/env bash
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: 1 fact
- Executable script in code of a testhello/scripts/greet.sh:1Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md examples/agent-plugin/skills/pdf/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md examples/agent-plugin/skills/pdf/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md examples/agent-plugin/skills/pdf/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md examples/agent-plugin/skills/pdf/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md examples/agent-plugin/skills/pdf/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md examples/agent-plugin/skills/pdf/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.
