skill-releaser

# Skill Releaser

Orchestrates the full skill publication pipeline from internal repo to ClawhHub.

## When to Use

- User says "release {skill}" or "publish {skill} to clawhub"
- User says "prepare {skill} for release" or "check release readiness"
- User says "review {skill} for publication"
- Cron-triggered release check during refactory pipeline

## Assumptions

**How OpenClaw and user interact during release:**
- Agent runs on a machine with shell access (exec tool) for git and CLI operations
- User communicates via messaging channel (Telegram, Discord, Signal, etc.) — likely on a phone
- User reviews the private GitHub repo directly in their browser/phone — the repo IS the review artifact, not a text summary
- User approves or rejects by replying to the agent's message (natural language: "approve", "revise: fix the readme", "reject")
- Agent can create and manage GitHub repos via `gh` CLI on behalf of the user's authenticated account
- Agent pushes to the private staging repo BEFORE requesting user review, so there is something to review
- Agent does NOT publish anything publicly without explicit user approval — this is a hard gate
- The repo starts private for staging and review. At release time, history is erased via orphan branch + force push (single clean commit), then flipped to public
- The full release can span multiple sessions — the private staging repo preserves state so any agent can resume
- Multiple skills can be in different stages of the pipeline simultaneously

## Prerequisites

- `gh` CLI authenticated (for repo creation and visibility changes)
- `clawhub` CLI installed (for ClawhHub publishing)
- A skill directory with at least a `SKILL.md` file

## Scope & Boundaries

**This skill handles:** The full release pipeline — structure scaffolding, OPSEC scanning, review, publishing.
**This skill does NOT handle:** Skill content creation or design. The SKILL.md must already describe what the skill does. Everything else (boilerplate, structure, scaff...

# skill-releaser

Release agent skills to ClawhHub through a full publication pipeline.

## What It Does

Takes any skill with a finished SKILL.md and handles everything needed to publish it:

1. **Scaffolds** missing structure files (README, CHANGELOG, tests, skill.yml) from SKILL.md
2. **Scans** for OPSEC violations (secrets, personal info, hardcoded paths)
3. **Reviews** via dual process — agent checklist + user approval
4. **Stages** in a private repo for user review on any device
5. **Publishes** by erasing history (force push) and flipping repo to public, then ClawhHub

## When to Use

- "Release {skill-name} to ClawhHub"
- "Is {skill-name} ready for release?"
- "Which skills are ready to publish?"
- "Prepare {skill-name} for release"

## Key Design Decisions

- **History erased at release** — orphan branch + force push gives a single clean commit
- **One repo per skill** — starts private for staging, flipped to public at release
- **User approval is a hard gate** — nothing goes public without explicit "approve"
- **Boilerplate is auto-generated** — only SKILL.md content needs to be written by hand
- **Security scan verified** — uses browser to check VirusTotal + OpenClaw scan results on ClawhHub before declaring release complete

## Prerequisites

- `gh` CLI authenticated
- `clawhub` CLI installed
- Shell access for git operations
- Browser tool available (for ClawhHub security scan verification)

## License

MIT

## Future Work

### Multi-Agent Architecture
When release volume justifies it, refactor from single-agent to multi-agent:

```
Dispatcher (coordinator)
  ├── Scaffolder (Steps 1-2): boilerplate, validation → flash-lite
  ├── Publisher (Steps 3-10): git ops, staging, OPSEC, publish → flash-lite
  ├── Verifier (Step 11): browser-based scan verification → sonnet
  └── Dispatcher delivers Step 12 summary
```

**Triggers:** 5+ skills per session, browser failures cascading into re-runs, rate limit cascades.

**Prerequisite:** Ship 3-5 more skills through...