skill-skill – Security skill for AI agents

Skill · skill

A skill is worth its tokens only if, when it runs, the output is different: a decision is made that wouldn't have been, an artifact exists that wouldn't have, a mistake is caught. Length is not the problem; lines that change nothing are. For every paragraph ask: what will the model do differently because of this? If nothing, it belongs in a reference that a step explicitly uses, or nowhere.

For heavy benchmarking (many evals, variance, description optimisation loops) use Anthropic's skill-creator; this skill is the fast path for turning real work into a skill that bites.

When to Use This Skill

• the user wants to create, rewrite or rename a Claude skill
• the user wants to turn a conversation, workflow or methodology into a skill
• a skill is not taking effect and needs an audit

1 · Distil from the real work

Mine the conversation (or the user's notes) before writing anything:

• Corrections and rejections in the user's own words ("太 PPT", "越改越不好", "too EDM"). Each becomes a rule with its reason, or a check.
• Accepted outputs: what finally worked and *why* (the mechanism, not the adjectives).
• Repeated work: anything done by hand twice (a conversion, a check, a render) becomes a script in scripts/.
• Facts from research: keep only those that change a decision; mark what was verified (✓) and what wasn't (u). Never let an unverified number become a rule.

2 · Turn knowledge into forcing functions

Advice is skipped; structure is followed. Prefer, in this order:

1. Required artifact at a step: "write audio-plan.md with these columns before step 4". The model can't skip a file the next step reads.

2. Gate: "don't start the picture until the track is locked"; "propose 3 directions before building".

3. Script for deterministic or fiddly parts (render, analyse, convert, lint). Scripts run without loading into context and don't drift.

4. Checklist run at a named moment ("run against the shot map before coding"), each line traceable to a past failure.

5. Template / example of the output, including one bad → good pair when taste is involved.

6. Reference file: only when a step says *when* to read it and *what to output* after reading. A reference nothing points to is never read.

Explain the why in one clause instead of shouting MUST; the model generalises from reasons.

3 · Write it

name-of-skill/
├── SKILL.md        # frontmatter + the steps (≲500 lines; the workflow, gates, artifacts)
├── scripts/        # deterministic tools the steps call
├── references/     # detail a step loads on purpose (cases, palettes, specs)
└── assets/         # templates / files copied into outputs

• Name: short, brandable, lowercase-hyphen, same as the folder. Check collisions with installed skills *and* famous tools (e.g. "remotion" = a React video framework → ambiguous).
• Description (≤1024 chars, the only thing seen before triggering): what it does + "Use when…" with the user's real phrases in every language they use (中文 too). Slightly pushy; models under-trigger.
• Body: numbered steps in the order work happens; each step ends in an artifact, a decision or a check. Lessons and taste go in a lessons file under references/, pointed to from the step where they bite.

4 · Audit (static, seconds)

python3 <this skill's base directory>/scripts/skill_audit.py <skill_dir>     # or --all; --badge prints a README badge

Flags: bad name / folder mismatch, description too long or without a trigger clause, name collisions, orphan files never mentioned in SKILL.md, dangling paths, oversized body, ALL-CAPS overuse, steps that produce nothing. Prints a 0–100 health score (−15 per ✗, −5 per warning). Fix every ✗. To benchmark public repos (report + chart + data), run scripts/skill_report.py owner/repo ….

Runtime prerequisite

Pinned upstream reference: [jack-reson8/skill-skill at 0889698c67805fe293293f07ef0ec1e9e725fd24](https://github.com/jack-reson8/skill-skill/tree/0889698c67805fe293293f07ef0ec1e9e725fd24).

This catalog entry bundles documentation and LICENSE only; scripts/skill_audit.py and scripts/skill_report.py are not bundled. Perform the static structure checks directly using read-only file inspection, or obtain user consent before fetching and inspecting the scripts at the pinned commit above.

5 · Effect test (minutes, not a benchmark)

1. Write 2–3 prompts a real user would type (with context, typos, mixed language).

2. For each, write 3 observable effects the skill should cause ("reply contains an energy-map table", "asks for no music file but writes a generator prompt", "uses audio_post.py for the loop").

3. Run each prompt with the skill (a subagent, or yourself in a fresh pass) and, if in doubt, without it. An effect that appears in both runs isn't the skill's doing; an effect missing in the skill run means a section isn't biting → convert it into a stronger forcing function (§2), don't add more prose.

6 · Keep it alive

• Every new rejection / acceptance → one line in lessons.md and, if it recurs, a check or a gate.
• After an edit, rerun the audit; show the user the diff summary, not the whole file.
• Prune what never fires in effect tests. Rename only with the collision check; update every path in SKILL.md.

Examples

• Distil a workflow into a skill: "Turn our 10-round UI review loop into a reusable skill." Extract the rejected/accepted patterns, convert each rule into a required step artifact or gate, write SKILL.md under 500 lines, and verify that every referenced support path exists.
• Audit an existing skill: "Why does my skill never change the output?" Check the frontmatter trigger clause, scan for orphan references or dangling paths, and replace passive prose advice with explicit step artifacts and gates.

Limitations

• The audit is static and checks structure, not whether the instructions are correct.
• The effect test is a quick with/without comparison, not a benchmark.