web-best-practices
Assimilated TLC/web-quality best-practices skill. Apply modern web security, compatibility, and code-quality checks. Triggers: apply best practices, security audit, modernize code, code quality review, check for vulnerabilities. Do not use as the primary skill for accessibility, SEO (ai-seo), or a full multi-area audit.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- web-best-practices
- license
- MIT
- metadata
- { "author": "Tech Leads Club", "version": "1.0.0", "owner_agent": "codenavi-agent" }
- description
- Assimilated TLC/web-quality best-practices skill. Apply modern web security, compatibility, and code-quality checks. Triggers: apply best practices, security audit, modernize code, code quality review, check for vulnerabilities. Do not use as the primary skill for accessibility, SEO (ai-seo), or a full multi-area audit.
02 资源文件 8
- 参考文档.skill-meta.json120 B
- 参考文档PERMISSIONS.yaml302 B
- 参考文档POLICY.md101 B
- 参考文档references/lenses/retained/legacy-contract.md202 B
- 参考文档references/ORIGINAL_SKILL.md12.5 KB
- 参考文档references/package-notes.md161 B
- 参考文档references/provenance.md938 B
- 参考文档references/tlc/UPSTREAM.md12.5 KB
03 SKILL.md 正文
Best Practices
Governance: CodENavi Full Workspace v2. Skill of codenavi-agent; inherit AGENTS.md.
Lifecycle: BRIEFING → RECON → PLAN → EXECUTE → VERIFY → DEBRIEF.
Source roles/workers are internal lenses. Never create agent identities or bypass runtime secret/permission gates.
Assimilated from installed best-practices 1.0 (web-quality-skills / TLC catalog). Original contract: references/ORIGINAL_SKILL.md.
Identity
A skill of the single canonical codenavi-agent. It creates no new agent identity.
Mission
Audit and remediate web security, browser compatibility, deprecated APIs, and code-quality issues using current official guidance, not training memory.
Activation
- User asks to apply best practices, run a security/quality review, or modernize frontend code.
Non-activation
- Dedicated SEO (
ai-seo). - Accessibility-only work.
- Full multi-area site audit (
web-quality-audit).
Critical rules
- Verify current header, CSP, and API guidance before calling anything "best".
- Do not weaken tests or delete failing checks to pass.
- Surgical fixes only. Do not rewrite unrelated files.
- Follow checklists and examples in
references/ORIGINAL_SKILL.md. - Secrets stay runtime-only.
Continuity
Record only verified, durable security decisions in .notebook/MEMORY.md.
TLC source
For the catalog workflow and its local resources, read TLC contract. Apply root governance and the local constraints above; upstream does not grant extra authority.
Provenance and source freshness: provenance.
Read package-notes.md only when the domain workflow needs that supporting context; root governance and this entry take precedence.
04 同仓库更多 Skills
workspace-brain
Operate the CodENavi workspace brain MCP and CLI — cloud DeepSeek RAG, disk corpus at WORKSPACE_BRAIN_ROOT, Jev URL curation, and event logging for Cursor/Codex/OpenCode/Claude. Use when ingesting repo knowledge, asking the brain, mapping web seeds, or recording AI-driven file changes. Do NOT use for local Ollama RAG or storing API keys in git.
workbench-profile-resolver
Provide enterprise-grade capability for `workbench-profile-resolver` inside AEOS v1.1. Use when the user requests workbench profile resolver or invokes workbench-profile-resolver. Do NOT use for unrelated tools or unapproved remote writes.
wordpress-expert
Staff-level WordPress engineering super-skill for one-shot site mapping, clean-code AI-assisted project creation/modification, the complete installed plugin universe, governed remote wp-admin operations, themes/blocks/layout, third-party integrations and production-safe changes. Use when the user requests wordpress expert or invokes wordpress-expert. Do NOT use for unrelated languages, domains or production deployment.
whatsapp-simulator
Generate synthetic WhatsApp-style conversation fixtures for testing conversational systems, support flows and automation. Use when the user requests whatsapp simulator or invokes whatsapp-simulator. Do NOT use for unrelated tools or unapproved remote writes.
web-quality-audit
Assimilated TLC/web-quality multi-area audit. Review performance, accessibility, SEO and best practices in one pass. Triggers: audit my site, review web quality, check page quality, optimize my website across areas. Do not use for a single-area job (core-web-vitals, ai-seo, best-practices, perf-lighthouse).
voiceai
Provide an evidence-backed voice interface for AEOS. Activating this skill is treated as explicit current-session consent for `voiceai` to record user audio or transcribe audio from user-authorized audio/video media within the declared scope. The skill can: Use when the user requests voiceai or invokes voiceai. Do NOT use for unrelated tools or unapproved remote writes.