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

91%

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

82%Weight 40%Scale 1-5

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

A strong, technical reference skill that documents an undocumented integration contract with actionable commands and a verification checklist. Minor room to tighten framing prose and add an explicit error-recovery loop for upgrades.

Suggestions

Trim framing sentences like 'This skill helps verify changes don't break that contract.' since the header and description already convey the purpose.

Add an explicit validate→fix→retry loop in the 'When Upgrading' section (e.g., 'If the diff -r output shows renamed attributes, update unsafeCSS selectors and re-run the checklist before testing').

Consider moving the full API surface tables (props, options, selectors, CSS variables) into a references/ file to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and focused on undocumented internals Claude would not know (selectors, CSS variables, grid assumptions); a few framing sentences ('This skill helps verify changes don't break that contract') could be trimmed but earn their place.	4 / 5
Actionability	Provides concrete, executable guidance throughout — exact file paths, copy-paste bash (`cp -r ... /tmp/pierre-old`, `diff -r ...`), run commands (`bun run dev:review`, `bun run --cwd apps/review build && bun run build:hook`), and grep targets covering the common cases.	5 / 5
Workflow Clarity	The 'When Upgrading' section gives a clear numbered sequence with validation (diffing .d.ts files, running the checklist) and the verification checklist provides checkpoints, but there is no explicit validate→fix→retry error-recovery loop.	4 / 5
Progressive Disclosure	Well-organized with clear section headers (Source of Truth, API Surface, Verification Checklist, When Upgrading) and no nested references; the lengthy selector/variable tables are defensible inline as the core contract but the skill is over 50 lines and could optionally split the API surface into a reference file.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

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

An excellent description: third-person, specific, with clear 'what' and 'when' clauses and rich natural trigger phrases tied to a distinct niche. No fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete guarding actions — 'modifying DiffViewer.tsx', 'upgrading the @pierre/diffs package', 'changing unsafeCSS injection', 'adding new props to FileDiff', 'touching shadow DOM selectors or CSS variables' — giving comprehensive coverage of the integration's surface.	5 / 5
Completeness	Explicitly states what ('Guard against breaking the @pierre/diffs integration in Plannotator's code review UI') and when ('Use this skill whenever modifying DiffViewer.tsx...') with concrete trigger phrases, satisfying both halves.	5 / 5
Trigger Term Quality	Covers natural user phrases ('will this break the diff viewer', 'is this safe to change', 'reviewing PRs that touch the review-editor package') alongside specific technical triggers and file/package names, including synonyms and concrete identifiers.	5 / 5
Distinctiveness Conflict Risk	Targets a narrow, named niche (@pierre/diffs integration in Plannotator) with highly specific triggers tied to a single file and package, making conflict with other skills minimal.	5 / 5
	Total	20 / 20 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: 79cb016

Reviewed: 1 day 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.