Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Skill Registry · gentleman-programming | DecimalAI

agent toolingby gentleman-programming

Skill Registry

gentleman-programming/skill-registry

Source gentleman-programming/gentle-ai ↗License MIT

Trigger: update skills, skill registry, actualizar skills, after skill changes. Index available skills by trigger and path.

SkillScore90Maintained

Automatic

AI Engineer pack

Last verified 10/7/2026

What it changes

Passed 18 of 20 test cases with the skill, and 12 of 20 without it.

Without skill60%

With skill90%

Checks it passed that the model alone missed

Sets type parameter to config
Sets title parameter to skill-registry
Avoids generating compact rules by default

and 8 more in the full report

8 fixed10 passed either way0 still failing2 broke3 errored

Pass-rate lift: +30 pp
Tokens: -20%
Agent turns: 0%
Response time: -55%

Model gemini-3.6-flashMeasured 10/7/2026v218 of 23 cases passed with skill · 20 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/gentleman-programming-skill-registry/SKILL.md https://app.decimal.ai/s/gentleman-programming-skill-registry/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add gentleman-programming-skill-registry, 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/gentleman-programming-skill-registry/ and pins it in .decimal/skills.lock

decimalai skills add gentleman-programming-skill-registry

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

curl -fsSL --create-dirs -o .claude/skills/gentleman-programming-skill-registry/SKILL.md https://app.decimal.ai/s/gentleman-programming-skill-registry/SKILL.md

Raw file: /s/gentleman-programming-skill-registry/SKILL.md ↗ · machine-readable summary at /s/gentleman-programming-skill-registry.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

During manual skill scanning, a skill named `lint-code` was found in two global directories: `/etc/skills/lint-code/SKILL.md` (scanned first) and `~/.skills/lint-code/SKILL.md` (scanned second). Which one should be retained?

What was checked, without and with the skill
Checked	Without skill	With skill
Selects the first global skill source from scan order	Missed	Passed

case-10 · gemini-3.6-flash · 10/7/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md43 linessingle file

Activation Contract

Use this skill after installing, removing, creating, moving, or renaming skills, or when a delegator needs a fresh skill index.

Hard Rules

The registry is an index, not a compiler or summary. SKILL.md remains the source of truth.
Do not generate or inject compact rules by default; preserve author intent by passing exact skill paths to subagents.
Always write .atl/skill-registry.md, whether or not Engram is available.
Save the registry to Engram as topic_key: skill-registry when available, with capture_prompt: false.
Generate the registry with gentle-ai skill-registry refresh --cwd <project>: it owns the scan order, deduplication, and the skills it never indexes. Scan by hand only when that command is unavailable.
When scanning by hand, skip _shared and skill-registry; deduplicate by skill name, preferring project-level skills over user-level skills.
Add .atl/ to .gitignore when possible unless explicitly disabled.

Decision Gates

Situation	Action
Same skill exists globally and in project	Keep the project-level skill
Same skill exists in multiple global locations	Keep the first source in scan order
No skills found	Write an empty registry so agents stop searching blindly
Agent will delegate work	Select matching registry rows and pass their `SKILL.md` paths

Execution Steps

Run gentle-ai skill-registry refresh --cwd <project> (add --force after skill changes); it writes .atl/skill-registry.md. If it reports the refresh was skipped (not a project), stop: there is no registry to persist. If it succeeds, go to step 4. If it fails, report the error instead of scanning by hand.
Only if the command is unavailable: scan all known user and project skill directories for */SKILL.md, reading frontmatter only as needed to extract name and description trigger text.
Render .atl/skill-registry.md with scanned sources, registry contract, skill name, trigger/description, scope, and exact path.
Persist to Engram when available using title: skill-registry, topic_key: skill-registry, type: config, and capture_prompt: false.
Return the registry path, skill count, cache status, and whether Engram was updated.

Output Contract

Return:

Project name and .atl/skill-registry.md path.
Number of indexed skills.
Whether the cache was hit or regenerated.
Any skipped or duplicate skills when relevant.

References

Track record

Benchmark

18 / 20

test cases passed, vs 12 / 20 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 v5 — 10/6/2026

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

Source

Imported

gentleman-programming / gentle-ai

internal/assets/skills/skill-registry/SKILL.md

View on GitHub ↗

License MITImported 10/6/2026Version v2

More skills from the same source and nearby in the registry, with their headline benchmark lift.