agent-rules-skill-auth…
Maintain WebDev Agent Kit source rules, skills, metadata, and validators. Excludes upgrading installed copies.
Add or tighten reusable approved patterns and anti-patterns in common/** with source-backed examples, approvals, graph links, evals, and validation. Keep project-specific patterns in local-only project/**.
$ npx -y skills add ytvee-dev/webdev-agent-kit --skill pattern-library-manager --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/pattern-library-managerContext preview
The summary Claude sees to decide when to auto-load this skill.
Add or tighten reusable approved patterns and anti-patterns in common/** with source-backed examples, approvals, graph links, evals, and validation. Keep project-specific patterns in local-only project/**.
name: pattern-library-manager
description: 'Add or tighten reusable approved patterns and anti-patterns in common/** with source-backed examples, approvals, graph links, evals, and validation. Keep project-specific patterns in local-only project/**.'
id: 'agents.skills.pattern-library-manager.skill'
title: 'Pattern Library Manager'
doc_type: 'skill'
layer: 'skill'
status: 'active'
publishable: true
local_only: false
skill: 'pattern-library-manager'
tags:
- 'agents/skill-package'
- 'agents/patterns'
- 'agents/authoring'
parent:
- '[[AGENTS|Canonical Agent Policy]]'
related:
- '[[skills/pattern-library-manager/references/pattern-entry-template|Pattern Entry Template]]'
- '[[skills/pattern-library-manager/references/example-sourcing-policy|Example Sourcing Policy]]'
- '[[common/approved-patterns|Approved Patterns]]'
- '[[common/anti-patterns|Common Anti-Patterns]]'
- '[[common/documentation-maintenance|Documentation Maintenance]]'
- '[[skills/agent-rules-skill-author/SKILL|Agent Rules And Skill Author]]'
depends_on:
- '[[AGENTS|Canonical Agent Policy]]'Add, tighten, or document reusable approved patterns and anti-patterns in this bundle without leaking host-project facts into publishable rules.
This skill owns small reusable pattern-library changes: descriptions, bad/good examples, graph links, trigger/output evals, and validation alignment.
Use this skill when the user asks to:
Do not use this skill for:
1. Read `AGENTS.md`. 2. Read `common/documentation-maintenance.md`. 3. Read `common/approved-patterns.md` or `common/anti-patterns.md` depending on the requested change. 4. Read the existing target pattern or anti-pattern file when modifying one. 5. Read `references/pattern-entry-template.md` before creating a new entry. 6. Read `references/example-sourcing-policy.md` before adding code examples. 7. Read `evals/trigger-evals.json` or `evals/output-evals.json` when routing or output behavior changes.
1. Classify the requested change as approved pattern, anti-pattern, example-only update, tightening, or eval coverage. 2. Decide whether the change is reusable bundle policy or host-project local guidance. 3. If the pattern is project-specific, stop and route to a local-only `project/**` overlay plan. 4. For reusable changes, inspect the current common rule or anti-pattern index. 5. Define the rule, allowed exceptions, bad example, good example, apply-when guidance, and validation impact. 6. Ask the user for examples when the requested pattern depends on a concrete code shape not already provided. 7. If examples are not supplied, use official or trusted sources only to understand the pattern, then write short original examples and propose them for user approval before committing. 8. Add or update the smallest owning file:
9. Update graph links so new documents have incoming edges. 10. Add trigger or output evals when the change prevents a real routing or behavior regression. 11. Run the relevant skill/bundle validators when available.
Final response: return only facts that affect the user's understanding, confidence, or next action. Omit empty fields and workflow narration.
Report:
Pattern change: Reusable or local-only decision: Files changed: Examples added or proposed: Source or user example basis: Eval changes: Validation: Risks:
Should trigger:
A cross-platform frontend kit for Codex, Claude Code, Cursor, OpenCode, etc. It helps AI coding agents work predictably and safely with existing frontend projects.
Repo: ytvee-dev/webdev-agent-kit
Maintain WebDev Agent Kit source rules, skills, metadata, and validators. Excludes upgrading installed copies.
Inspect Figma links through MCP or browser computer use, or analyze screenshots and selected-layer properties. Produce frontend specs and clarify unresolved…
Create, resume, analyze, or converge standard and deep frontend execution plans with traceable slices, evidence, and stop/resume state. Skip lightweight…
Plan architecture and ownership for standard or deep React/Next.js work across routing, state, data, styling, forms, builds, migrations, and implementation…
Diagnose and fix frontend defects from evidence, including unclear UI/runtime errors, broken routes, styling regressions, and hydration or client issues.…
Set subject-grounded visual direction for standard or deep UI work, redesign, polish, critique, anti-template review, or design handoff. Skip technical…