new-skill
Scaffold a new brooks-lint analysis skill so it passes `npm run validate` and `npm run evals` on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (s
Install
npx skills add https://github.com/hyhmrright/brooks-lint/tree/main/.agents/skills/new-skill
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install hyhmrright-brooks-lint@llmmart
git clone https://github.com/hyhmrright/brooks-lint.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole hyhmrright/brooks-lint collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
brooks-lint — New Skill Scaffold
Skill name comes from the user request (kebab-case, e.g. brooks-security). If empty,
ask for the name and a one-line purpose first.
Follow the repo's "Adding a New Skill" checklist exactly:
- Create
skills/{name}/SKILL.mdwith frontmatter —name, adescriptionthat ends with aDo NOT trigger for:clause (validate-enforced for shipped skills; omitting it causes false triggering),metadata:withopencode/slash: "true", and aProcesssection of 3–6 bullets that cite the guide's step ranges inline (e.g.Scan risks (Steps 1–6 of the guide)). Mirror the structure of an existing skill such asskills/brooks-review/SKILL.md(Setup → Process → Mode line). - Create
skills/{name}/{name}-guide.mdwith sequentially numbered steps — no gaps, no duplicates. Sub-steps likeStep 2aare allowed. The guide owns the detailed steps; the SKILL.md Process is just an orientation skeleton. - Wire the framework. The new SKILL.md Setup section must Read the relevant
_shared/files (common.mdfor Iron Law + Report Template, plusdecay-risks.md/test-decay-risks.mdas applicable) —_shared/is NOT auto-loaded. - Add eval coverage to
evals/evals.json: append with the next sequentialidat least one happy-path scenario (with the relevant risk code inexpected_output) and at least one false-positive scenario flaggedno_risk_codes: true. Each scenario needsid,name,prompt,expected_output,mode,files. - Validate.
npm run validate(structure + step continuity + Process-section presence) andnpm run evals(eval schema). Fix until both pass. - Local-test. Link the new skill folder from
skills/into.agents/skills/alongside the_sharedsymlink, then invoke it with$<skill-name>in a Codex session and verify the Iron Law output.
Codex discovers repository skills directly; no command wrapper is needed. Report the files created and the validate/evals results.
Files (brooks-lint)
-
agents
-
openai.yaml 43 B
Loading…
-
-
SKILL.md 2.7 KB
--- name: new-skill description: > Scaffold a new brooks-lint analysis skill so it passes `npm run validate` and `npm run evals` on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends paired eval scenarios. Triggers when the maintainer asks to "add a new skill", "scaffold a skill", or "create a brooks-lint mode". Do NOT trigger for: editing an existing skill's content, adding a single eval to an existing skill, or authoring skills for some other plugin. --- # brooks-lint — New Skill Scaffold Skill name comes from the user request (kebab-case, e.g. `brooks-security`). If empty, ask for the name and a one-line purpose first. Follow the repo's "Adding a New Skill" checklist exactly: 1. **Create `skills/{name}/SKILL.md`** with frontmatter — `name`, a `description` that ends with a `Do NOT trigger for:` clause (validate-enforced for shipped skills; omitting it causes false triggering), `metadata:` with `opencode/slash: "true"`, and a `Process` section of 3–6 bullets that cite the guide's step ranges inline (e.g. `Scan risks (Steps 1–6 of the guide)`). Mirror the structure of an existing skill such as `skills/brooks-review/SKILL.md` (Setup → Process → Mode line). 2. **Create `skills/{name}/{name}-guide.md`** with sequentially numbered steps — no gaps, no duplicates. Sub-steps like `Step 2a` are allowed. The guide owns the detailed steps; the SKILL.md Process is just an orientation skeleton. 3. **Wire the framework.** The new SKILL.md Setup section must Read the relevant `_shared/` files (`common.md` for Iron Law + Report Template, plus `decay-risks.md` / `test-decay-risks.md` as applicable) — `_shared/` is NOT auto-loaded. 4. **Add eval coverage** to `evals/evals.json`: append with the next sequential `id` at least one happy-path scenario (with the relevant risk code in `expected_output`) and at least one false-positive scenario flagged `no_risk_codes: true`. Each scenario needs `id`, `name`, `prompt`, `expected_output`, `mode`, `files`. 5. **Validate.** `npm run validate` (structure + step continuity + Process-section presence) and `npm run evals` (eval schema). Fix until both pass. 6. **Local-test.** Link the new skill folder from `skills/` into `.agents/skills/` alongside the `_shared` symlink, then invoke it with `$<skill-name>` in a Codex session and verify the Iron Law output. Codex discovers repository skills directly; no command wrapper is needed. Report the files created and the validate/evals results.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.