new-skill

Name: new-skill
Author: hyhmrright

63installs59forks

How to install new-skill?

hyhmrright/brooks-lint/new-skill

$npx -y skills add hyhmrright/brooks-lint --skill new-skill

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	# brooks-lint — New Skill Scaffold
2
3	Skill name comes from `$ARGUMENTS` (kebab-case, e.g. `brooks-security`). If empty,
4	ask for the name and a one-line purpose first.
5
6	Follow the repo's "Adding a New Skill" checklist exactly:
7
8	1. Create `skills/{name}/SKILL.md` with frontmatter — `name`, a `description`
9	that ends with a `Do NOT trigger for:` clause (validate-enforced for shipped
10	skills; omitting it causes false triggering), and a `Process` section of 3–6
11	bullets that cite the guide's step ranges inline (e.g. `Scan risks (Steps 1–6 of
12	the guide)`). Mirror the structure of an existing skill such as
13	`skills/brooks-review/SKILL.md` (Setup → Process → Mode line).
14	2. Create `skills/{name}/{name}-guide.md` with sequentially numbered steps —
15	no gaps, no duplicates. Sub-steps like `Step 2a` are allowed. The guide owns the
16	detailed steps; the SKILL.md Process is just an orientation skeleton.
17	3. Wire the framework. The new SKILL.md Setup section must Read the relevant
18	`_shared/` files (`common.md` for Iron Law + Report Template, plus
19	`decay-risks.md` / `test-decay-risks.md` as applicable) — `_shared/` is NOT
20	auto-loaded.
21	4. Add eval coverage to `evals/evals.json`: append with the next sequential
22	`id` at least one happy-path scenario (with the relevant risk code in
23	`expected_output`) and at least one false-positive scenario flagged
24	`no_risk_codes: true`. Each scenario needs `id`, `name`, `prompt`,
25	`expected_output`, `mode`, `files`.
26	5. Validate. `npm run validate` (structure + step continuity + Process-section
27	presence) and `npm run evals` (eval schema). Fix until both pass.
28	6. Local-test. `cp -r skills/* ~/.claude/skills/brooks-lint/` (if you've
29	symlinked `~/.claude/skills/brooks-lint` to the repo, skip this — edits are
30	already live), trigger the new skill in a Claude session, verify the Iron Law
31	output, then restore the marketplace copy: `/plugin marketplace update` →
32	`/plugin install brooks-lint@brooks-lint-marketplace`.
33
34	Do NOT register a slash command by hand — short forms are auto-installed by the
35	session-start hook. Report the files created and the validate/evals results.

People who liked this also viewed

6 picks

Type

new-skill

63installs59forks

View on GitHub

How to install new-skill?

hyhmrright/brooks-lint/new-skill

$npx -y skills add hyhmrright/brooks-lint --skill new-skill

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# brooks-lint — New Skill Scaffold
2
3	Skill name comes from `$ARGUMENTS` (kebab-case, e.g. `brooks-security`). If empty,
4	ask for the name and a one-line purpose first.
5
6	Follow the repo's "Adding a New Skill" checklist exactly:
7
8	1. Create `skills/{name}/SKILL.md` with frontmatter — `name`, a `description`
9	that ends with a `Do NOT trigger for:` clause (validate-enforced for shipped
10	skills; omitting it causes false triggering), and a `Process` section of 3–6
11	bullets that cite the guide's step ranges inline (e.g. `Scan risks (Steps 1–6 of
12	the guide)`). Mirror the structure of an existing skill such as
13	`skills/brooks-review/SKILL.md` (Setup → Process → Mode line).
14	2. Create `skills/{name}/{name}-guide.md` with sequentially numbered steps —
15	no gaps, no duplicates. Sub-steps like `Step 2a` are allowed. The guide owns the
16	detailed steps; the SKILL.md Process is just an orientation skeleton.
17	3. Wire the framework. The new SKILL.md Setup section must Read the relevant
18	`_shared/` files (`common.md` for Iron Law + Report Template, plus
19	`decay-risks.md` / `test-decay-risks.md` as applicable) — `_shared/` is NOT
20	auto-loaded.
21	4. Add eval coverage to `evals/evals.json`: append with the next sequential
22	`id` at least one happy-path scenario (with the relevant risk code in
23	`expected_output`) and at least one false-positive scenario flagged
24	`no_risk_codes: true`. Each scenario needs `id`, `name`, `prompt`,
25	`expected_output`, `mode`, `files`.
26	5. Validate. `npm run validate` (structure + step continuity + Process-section
27	presence) and `npm run evals` (eval schema). Fix until both pass.
28	6. Local-test. `cp -r skills/* ~/.claude/skills/brooks-lint/` (if you've
29	symlinked `~/.claude/skills/brooks-lint` to the repo, skip this — edits are
30	already live), trigger the new skill in a Claude session, verify the Iron Law
31	output, then restore the marketplace copy: `/plugin marketplace update` →
32	`/plugin install brooks-lint@brooks-lint-marketplace`.
33
34	Do NOT register a slash command by hand — short forms are auto-installed by the
35	session-start hook. Report the files created and the validate/evals results.

People who liked this also viewed

6 picks

Type