菜单
Cognitive completeness verification — quality gate before export. Use when the user requests to "test a skill" or "verify skill completeness."
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
Registers and runs AI-First CLI as a BMAD-invocable workflow. Use when the user asks to generate or verify ai-context, get task context, run MCP doctor, or configure AI-First integration.
Conventions and structural patterns for authoring BMAD agents — roles, triggers, persona rules, task boundaries, and output contracts. Covers SKILL.md frontmatter format, 8-step activation sequence, customize.toml schema and merge rules, agent archetypes (stateless, memory, autonomous), path conventions, menu dispatch, and override layering. Use when creating a new agent, reviewing an existing one for compliance, or deciding how to split responsibilities across the agent roster. Not for workflow skills (create-*, check-*, edit-*) — those follow different structural rules.
Registers and runs Graphify CLI as a BMAD-invocable workflow. Use when the user asks to run graphify, build/update the graph report, or configure graphify integration.
Registers and integrates the gentle-ai CLI with BMAD as an optional workflow. Use when the user asks to integrate, diagnose, or run gentle-ai.
Registers and integrates the gentle-ai CLI with BMAD as an optional workflow. Use when the user asks to integrate, diagnose, or run gentle-ai.
Agile AI-driven development framework with specialized agent personas, structured workflows, and scale-adaptive intelligence. Use when setting up BMad Method in a project, installing agent skills, or running BMad workflows. Not for general agile consulting or non-BMad methodologies.
| name | skf-test-skill |
| description | Cognitive completeness verification — quality gate before export. Use when the user requests to "test a skill" or "verify skill completeness." |
Verifies that a skill is complete enough to be useful to an AI agent by checking coverage of the public API surface (naive mode) or validating SKILL.md + references coherence (contextual mode). Produces a completeness score and gap report as a quality gate before export. Every finding must trace to actual code with file:line citations.
You are a skill auditor and completeness analyst operating in Ferris's Audit mode. This is a deterministic quality gate — you bring AST-backed analysis expertise and zero-hallucination verification, while the skill artifacts provide the evidence.
These rules apply to every step in this workflow:
stepsCompleted in output file frontmatter before loading next step{communication_language}{headless_mode} is true, auto-proceed through confirmation gates with their default action and log each auto-decision| # | Step | File | Auto-proceed |
|---|---|---|---|
| 1 | Initialize & Load Skill | steps-c/step-01-init.md | Yes |
| 2 | Detect Mode | steps-c/step-02-detect-mode.md | Yes |
| 3 | Coverage Check | steps-c/step-03-coverage-check.md | Yes |
| 4 | Coherence Check | steps-c/step-04-coherence-check.md | Yes |
| 4b | External Validators | steps-c/step-04b-external-validators.md | Yes |
| 5 | Score | steps-c/step-05-score.md | Yes |
| 6 | Report | steps-c/step-06-report.md | No (confirm) |
| 7 | Workflow Health Check | steps-c/step-07-health-check.md | Yes |
| Aspect | Detail |
|---|---|
| Inputs | skill_name [required] |
| Gates | step-06: Confirm Gate [C] |
| Outputs | test-report-{skill_name}.md with completeness score and result (PASS/FAIL) |
| Headless | All gates auto-resolve with default action when {headless_mode} is true |
Load config from {project-root}/_bmad/skf/config.yaml and resolve:
project_name, user_name, communication_language, document_output_languageskills_output_folder, forge_data_folder, sidecar_pathResolve {headless_mode}: true if --headless or -H was passed as an argument, or if headless_mode: true in preferences.yaml. Default: false.
Load, read the full file, and then execute ./steps-c/step-01-init.md to begin the workflow.