pierre-guard

Guard against breaking the @pierre/diffs integration in Plannotator's code review UI. Use this skill whenever modifying DiffViewer.tsx, upgrading the @pierre/diffs package, changing unsafeCSS injection, adding new props to FileDiff, or touching shadow DOM selectors or CSS variables that cross into Pierre's shadow boundary. Also trigger when someone asks "will this break the diff viewer", "is this safe to change", or when reviewing PRs that touch the review-editor package.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A focused, actionable guard skill with executable commands, validation checkpoints, and tight reference tables. The main weakness is progressive disclosure: the detailed API-surface tables live inline in SKILL.md with no bundle reference files to offload them.

Suggestions

Move the exhaustive shadow-DOM selector and CSS-variable tables into a references/ file (e.g. references/pierre-api-surface.md) and keep SKILL.md as a concise overview that links to it, so the selector inventory is one level deep.

Consolidate the grid-layout discussion — currently split between section 5 ("CSS Variables We Inject") and section 6 ("Grid Layout Assumption") — into a single section to remove the duplicated grid-template-columns explanation.

If the reference split is made, add a short "Quick check" summary at the top of SKILL.md pointing to the API-surface reference and the upgrade checklist for fast triage.

Dimension	Reasoning	Score
Conciseness	Lean reference material that assumes Claude's competence — no generic explanations of Shadow DOM or libraries — where the prop, option, selector, and CSS-variable tables each earn their place for the guard purpose.	3 / 3
Actionability	Provides concrete executable guidance throughout — `bun run dev:review`, the `diff -r /tmp/pierre-old node_modules/@pierre/diffs/dist` upgrade snippet, and grep-based verification steps — not vague direction.	3 / 3
Workflow Clarity	The upgrade workflow is a clear numbered sequence with validation checkpoints (snapshot/diff .d.ts files, run the full checklist, test the resizable split pane), and the verification checklist supplies explicit per-category checkpoints.	3 / 3
Progressive Disclosure	Well-organized into clear sections with one-level-deep external pointers (upstream repo, local .d.ts), but the exhaustive selector and CSS-variable tables are kept fully inline in SKILL.md rather than split into a reference file.	2 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with concrete actions, natural trigger phrases, and an explicit use-when clause scoped to a narrow integration. Third-person imperative voice is used correctly throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "modifying DiffViewer.tsx", "upgrading the @pierre/diffs package", "changing unsafeCSS injection", "adding new props to FileDiff", "touching shadow DOM selectors or CSS variables" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ("Guard against breaking the @pierre/diffs integration") and when ("Use this skill whenever..." plus "Also trigger when..."), with explicit triggers rather than implied ones.	3 / 3
Trigger Term Quality	Includes natural phrases a developer would actually say — "will this break the diff viewer", "is this safe to change", "reviewing PRs that touch the review-editor package" — alongside concrete file/package triggers.	3 / 3
Distinctiveness Conflict Risk	A clear narrow niche — the @pierre/diffs integration in Plannotator's review UI — with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: backnotprop/plannotator
Path: .agents/skills/pierre-guard/SKILL.md
Commit: 193b07e

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.