Ready to supercharge your AI agents?

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

Get Started Free →

ai-shifu Skills Entry | DecimalAI

agent toolingby ai-shifu

ai-shifu Skills Entry

ai-shifu/ai-shifu-skills-entry

Source ai-shifu/ai-shifu ↗License Apache-2.0

- This file only keeps repository-level skill routing and boundary notes.

SkillScore100Maintained

Automatic

Doc Ops pack

Last verified 9/3/2026

What it changes

Passed 19 of 19 test cases with the skill, and 5 of 19 without it.

Without skill27%

With skill100%

Checks it passed that the model alone missed

src/api/skills/
src/web/skills/
src/api/SKILL.md

and 15 more in the full report

16 fixed6 passed either way0 still failing0 broke

Pass-rate lift: +73 pp
Tokens: -40%
Agent turns: 0%
Response time: -38%

Model gemini-3.6-flashMeasured 9/3/2026v222 of 22 cases passed with skill · 19 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/ai-shifu-ai-shifu-skills-entry/SKILL.md https://app.decimal.ai/s/ai-shifu-ai-shifu-skills-entry/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add ai-shifu-ai-shifu-skills-entry, 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/ai-shifu-ai-shifu-skills-entry/ and pins it in .decimal/skills.lock

decimalai skills add ai-shifu-ai-shifu-skills-entry

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

curl -fsSL --create-dirs -o .claude/skills/ai-shifu-ai-shifu-skills-entry/SKILL.md https://app.decimal.ai/s/ai-shifu-ai-shifu-skills-entry/SKILL.md

Raw file: /s/ai-shifu-ai-shifu-skills-entry/SKILL.md ↗ · machine-readable summary at /s/ai-shifu-ai-shifu-skills-entry.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

Where is the dedicated frontend skills index document located in the repository? Base models often guess src/web/INDEX.md or docs/skills/web.md.

What was checked, without and with the skill
Checked	Without skill	With skill
src/web/skills/README.md	Missed	Passed

case-10 · gemini-3.6-flash · 9/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md25 lines25 filesincludes scripts

ai-shifu Skills Entry

Scope

This file only keeps repository-level skill routing and boundary notes.
Backend and frontend maintain their own skill entry points so this file does not grow into a mixed troubleshooting manual.

Placement Rules

Keep ai-shifu/SKILL.md for cross-project skill routing, ownership boundaries, and migration notes.
Keep src/api/SKILL.md for backend project-level skill entry points and focused skill indexes.
Keep src/web/SKILL.md for long-lived Cook Web constraints and focused skill indexes.
Keep src/api/skills/xxx/SKILL.md or src/web/skills/xxx/SKILL.md for focused skills with triggers, workflows, and regression checklists.

Entry Points

Backend: src/api/SKILL.md
Frontend: src/web/SKILL.md
Frontend skills index: src/web/skills/README.md
Backend skills index: src/api/skills/README.md

Migration Notes

Stable rules belong in layered AGENTS.md / CLAUDE.md.
Troubleshooting knowledge that needs step-by-step execution or long-term reuse belongs in the relevant subproject SKILL.md system.

Track record

Benchmark

19 / 19

test cases passed, vs 5 / 19 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 — 9/3/2026

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

ai-shifu / ai-shifu

SKILL.md

View on GitHub ↗

License Apache-2.0Imported 9/3/2026Version v2Bundled 24 files · scripts

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

Ready to supercharge your AI agents?

See it in action

What's inside

ai-shifu Skills Entry

Scope

Placement Rules

Entry Points

Migration Notes

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills