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。
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。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Extract a canonical specification from an existing agent or skill file. Inspired by codespeak.dev's reverse compilation concept — deriving specs from existing implementations.
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.
/omcustom-takeover <agent-name>
/omcustom-takeover <skill-name>
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)
Extract these components from the target:
| Component | Source | Description |
|---|---|---|
intent | Description field + first paragraph | One-line purpose statement |
invariants | Rules referenced, constraints mentioned | Things that must always be true |
workflow_contract | Workflow/stages sections | Input → processing → output steps |
io_contract | Tools field, input/output patterns | What the agent consumes and produces |
dependencies | Skills field, guide references | External knowledge required |
boundaries | Limitations field, disallowedTools | What the agent explicitly cannot do |
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>
[Done] Spec extracted: .claude/specs/<name>.spec.md
├── Intent: <summary>
├── Invariants: <count> rules
├── Workflow: <step count> steps
└── Dependencies: <count> refs
.claude/)/omcustom-takeover <name>/dev-refactor --spec for invariant-preserving refactoring还没有评价。欢迎分享你的使用感受。
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。
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。
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。
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。
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。
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。
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。