菜单
Preflight a spec draft without saving. Runs the same three checks as the write-boundary hooks — PlantUML syntax, required diagram presence, and AC-to-sequence traceability — and prints a compact pass/fail table. Use while iterating so the hooks don't bite on save.
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
Cialdini 7 principles applied to global marketing — reciprocity, scarcity, authority, social proof, liking, commitment, unity. Universal psychology with international examples (Apple, Tesla, Patagonia, Spotify). Trigger: 'marketing psychology', 'Cialdini', 'persuasion principles', 'consumer psychology', 'behavioral marketing'.
MANDATORY skill for ALL code generation. Enforces top-down composition, consistent abstraction layers, and proper module hierarchy. Apply every time you write or modify code — in any language — no exceptions.
Workflow Phase 7 — Mechanical cleanup pass over the branch diff, followed by a `code-structure` review pass and a `verify` re-stamp. Shadows the global `simplify` skill at project scope; the cleanup pass is performed inline rather than via Skill self-call.
PM-mode brainstorm helper. Captures the requirement via Socratic dialogue before any entry phase (`/intake`, `/spec`, `/tdd`) drafts its artifact. Stage 0 skip-check, Stage 1 gap-analysis, Stage 2 probe-loop, Stage 3 confirm-and-persist. Output lives at `docs/brief/<slug>.md`. Never proposes solutions — Stage 2 dialogue discipline is structurally enforced via `discipline.mjs`.
Workflow Phase 9 — Integration and Verification. Runs the full test suite, stamps the binding verdict at .claude/state/last_test_result, optionally runs a cross-engine smoke check, and writes harness_state so the harness auto-continues or yields. No subagent delegation.
Workflow Phase 8 (optional) — OWASP-aligned security review of pending code changes. Produces a prioritized findings report (Critical/High/Medium/Low) mapped to OWASP Top 10 and CWE IDs. Output at `docs/security/<slug>-<date>.md`. Read-only.
| name | spec-lint |
| owner | baseline |
| description | Preflight a spec draft without saving. Runs the same three checks as the write-boundary hooks — PlantUML syntax, required diagram presence, and AC-to-sequence traceability — and prints a compact pass/fail table. Use while iterating so the hooks don't bite on save. |
Checker config (tier-dial:read-path): this checker's floor/ceiling come from the tier dial at
.claude/hooks/lib/tier-dial.mjsviaresolveCheckerThreshold('spec'). Advisory only this slice (v1 piece 2); blocking is piece 5.
Invocable by both user (/spec-lint <slug>) and Claude (when iterating on a spec and wanting to check status before writing).
Three checks, same logic as the hooks, but advisory (no writes are blocked):
| # | Check | Hook it mirrors |
|---|---|---|
| 1 | Every plantuml fence parses under plantuml -checkonly | plantuml_syntax_guard |
| 2 | Required diagram kinds present (config: project.json → artifacts.required_diagrams.spec) | spec_diagram_presence_guard |
| 3 | Every AC-NNN row in the Acceptance criteria table references a §Behavior #N section that exists | (no hook — unique to the lint) |
/spec-lint <slug> — where <slug> corresponds to docs/specs/<slug>.md.
docs/specs/<slug>.md must exist.node .claude/skills/spec-lint/lint.mjs <slug>
check status
---------------------------------- ------
plantuml_syntax PASS
diagram_presence FAIL (missing: c4_component, dependency_graph)
ac_traceability FAIL (AC-002 → §Behavior #2 not found)
---------------------------------- ------
overall FAIL
Exit 0 on overall PASS, 1 on overall FAIL. Intended for use in CI or a pre-commit loop as well as interactively.
plantuml CLI on PATH for check #1 (if absent, #1 is reported as SKIP (no plantuml); #2 and #3 still run).spec-lint runs against the on-disk file, not proposed content. Save or use the hooks to validate an unsaved draft.spec-lint does not render. Use /spec-render <slug> for that.