Registry skillby fchastanet

Sample AI Skill

fchastanet/sample-ai-skill

Source fchastanet/ai-linter ↗License MIT

A sample skill demonstrating the AI Linter validation

SkillScore92Maintained

Automatic

AI Engineer pack

Last verified 8/3/2026

What it changes

Passed 21 of 23 test cases with the skill, and 10 of 23 without it.

Without skill42%

With skill92%

Checks it passed that the model alone missed

The response references README.md.
The response lists Files as a section header.
The list includes the 500 line maximum limit.

and 17 more in the full report

12 fixed10 passed either way2 still failing0 broke

Pass-rate lift: +50 pp
Tokens: -33%
Agent turns: 0%
Response time: -47%

Model gemini-3.6-flashMeasured 8/3/2026v122 of 24 cases passed with skill · 23 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/fchastanet-sample-ai-skill/SKILL.md https://app.decimal.ai/s/fchastanet-sample-ai-skill/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add fchastanet-sample-ai-skill, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/fchastanet-sample-ai-skill/ and pins it in .decimal/skills.lock

decimalai skills add fchastanet-sample-ai-skill

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/fchastanet-sample-ai-skill/SKILL.md https://app.decimal.ai/s/fchastanet-sample-ai-skill/SKILL.md

Raw file: /s/fchastanet-sample-ai-skill/SKILL.md ↗ · machine-readable summary at /s/fchastanet-sample-ai-skill.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

What's inside

The instructions your model reads when the skill loads.

SKILL.md31 linessingle file

Sample AI Skill

This is an example skill file that demonstrates the proper format for AI skills that will pass AI Linter validation.

Purpose

This skill serves as an example of:

Proper frontmatter formatting
Correct metadata structure
Valid file references
Appropriate content length

Implementation

The skill implementation would go here. This content is validated for:

Token count (must be under 5000 tokens)
Line count (must be under 500 lines)
File references (all must exist)

Files

This skill references the following files:

README.md - Main documentation
pyproject.toml - Package configuration

Usage

Example usage instructions would be provided here.

Track record

Benchmark

21 / 23

test cases passed, vs 10 / 23 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review