菜单
Use when deciding whether a Trails hardening finding belongs in Warden, repo-local Oxlint, docs, an advisory skill, or no rule. Helps agents classify prevention candidates by owner source, Warden tier, lifecycle, diagnostic shape, and false-positive risk.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Trails framework co-architect & CTO persona — constitutional hierarchy, drift guard, vocabulary enforcement, and architectural judgment. Use when evaluating Trails architecture, enforcing vocabulary, reviewing framework coherence, or when Clark's judgment is needed on a Trails question.
Trails framework co-architect & CTO persona — constitutional hierarchy, drift guard, vocabulary enforcement, and architectural judgment. Use when evaluating Trails architecture, enforcing vocabulary, reviewing framework coherence, or when Clark's judgment is needed on a Trails question.
Build with the Trails framework — define trail contracts, open CLI/MCP surfaces, test with examples, debug errors, migrate codebases, run governance. Use when creating trails, adding surfaces, testing, debugging Trails errors, migrating to Trails, running warden, or any work involving @ontrails/* packages.
Author, update, and manage Trails ADRs. Use when creating new ADRs, promoting drafts to accepted, updating the ADR index, renaming or renumbering ADRs, or when the user mentions ADR, architecture decision, or decision record.
Complete Trails editorial review workflow. Use when reviewing docs, ADRs, README changes, release notes, agent guidance, or docs-heavy PRs for voice, style, structure, correctness, and readiness.
Trails documentation structure and maintenance guidance. Use when creating or reorganizing Trails docs, READMEs, guides, reference pages, release docs, or agent-facing documentation.
| name | trails-warden-advisory |
| description | Use when deciding whether a Trails hardening finding belongs in Warden, repo-local Oxlint, docs, an advisory skill, or no rule. Helps agents classify prevention candidates by owner source, Warden tier, lifecycle, diagnostic shape, and false-positive risk. |
Use this skill before filing or implementing static guardrails from a Trails audit finding.
retireWhen, advisory, or no-rule.docs/contributing/warden-rules.mddocs/warden.mddocs/adr/0036-warden-rules-ship-only-as-trails.mddocs/adr/0037-owner-first-authority.mdpackages/warden/src/rules/metadata.tspackages/warden/src/rules/types.tsplugin/skills/trails/references/warden-guide.md@ontrails/oxlint or a public parser package for framework correctness.canonicalSource(), generic registries, TSDoc canonical tags, or shadow owner tables.Return a recommendation with: