跳到正文
cccskills
免费在 GitHub 公开

omcustom-takeover

Extract canonical spec from existing agent or skill files

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md2.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Takeover Skill

Extract a canonical specification from an existing agent or skill file. Inspired by codespeak.dev's reverse compilation concept — deriving specs from existing implementations.

Purpose

When an agent or skill has evolved organically without a formal spec, takeover reverse-engineers a structured specification that captures its intent, invariants, workflow contract, and I/O contract.

Usage

/omcustom-takeover <agent-name>
/omcustom-takeover <skill-name>

Workflow

Phase 1: Read Target

1. Determine target type:
   - Agent: read .claude/agents/<name>.md
   - Skill: read .claude/skills/<name>/SKILL.md
2. Parse frontmatter (YAML metadata)
3. Parse body (markdown content)

Phase 2: Extract Spec Components

Extract these components from the target:

ComponentSourceDescription
intentDescription field + first paragraphOne-line purpose statement
invariantsRules referenced, constraints mentionedThings that must always be true
workflow_contractWorkflow/stages sectionsInput → processing → output steps
io_contractTools field, input/output patternsWhat the agent consumes and produces
dependenciesSkills field, guide referencesExternal knowledge required
boundariesLimitations field, disallowedToolsWhat the agent explicitly cannot do

Phase 3: Generate Spec

Output structured spec to .claude/specs/<name>.spec.md:

---
name: <name>
type: agent | skill
source: .claude/agents/<name>.md | .claude/skills/<name>/SKILL.md
generated: <ISO-8601 timestamp>
---

# Spec: <name>

## Intent
<one-line purpose>

## Invariants
- <rule or constraint that must always hold>
- ...

## Workflow Contract
### Input
<what the agent/skill receives>

### Processing
1. <step>
2. <step>

### Output
<what the agent/skill produces>

## I/O Contract
### Consumes
- Tools: [<tools used>]
- Files: [<files read>]
- MCP: [<MCP tools if any>]

### Produces
- Files: [<files created/modified>]
- Output: [<what is returned>]

## Dependencies
- Skills: [<referenced skills>]
- Guides: [<referenced guides>]
- Rules: [<rules enforced>]

## Boundaries
- <what the agent explicitly cannot do>

Phase 4: Report

[Done] Spec extracted: .claude/specs/<name>.spec.md
├── Intent: <summary>
├── Invariants: <count> rules
├── Workflow: <step count> steps
└── Dependencies: <count> refs

Notes

  • Specs are git-untracked (under .claude/)
  • Regenerate anytime with /omcustom-takeover <name>
  • Used by /dev-refactor --spec for invariant-preserving refactoring
  • Advisory output — human review recommended before using as contract

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Pre-action boundary checking — validates agent tool calls against declared capabilities and task contracts

中文简介正在准备中。当前显示原文说明。

baekenough/second-brain152026年10月8日 更新

Auto-detect project context and optimize harness — deactivate unused agents/skills, suggest missing experts, generate project profile

中文简介正在准备中。当前显示原文说明。

baekenough/second-brain152026年10月8日 更新

Adversarial code review using attacker mindset — trust boundary, attack surface, business logic, and defense evaluation

中文简介正在准备中。当前显示原文说明。

baekenough/second-brain152026年10月8日 更新

Apache Airflow best practices for DAG authoring, testing, and production deployment

中文简介正在准备中。当前显示原文说明。

baekenough/second-brain152026年10月8日 更新

Alembic migration patterns for naming conventions, safety checks, expand-contract, env.py configuration, and CI integration

中文简介正在准备中。当前显示原文说明。

baekenough/second-brain152026年10月8日 更新

Pre-routing ambiguity analysis — scores request clarity and asks clarifying questions when needed (inspired by ouroboros)

中文简介正在准备中。当前显示原文说明。

baekenough/second-brain152026年10月8日 更新

查看 baekenough 的全部技能

报告此技能的问题