← 返回 Skills 市场
g-hanasq

clawhub-publish-flow

作者 G-Hanasq · GitHub ↗ · v0.1.3 · MIT-0
cross-platform ⚠ suspicious
328
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install clawhub-publish-flow
功能描述
Publish or update an OpenClaw skill on ClawHub using the local authenticated ClawHub session and direct API upload. Use when the user wants to publish a new...
使用说明 (SKILL.md)

ClawHub Publish Flow

Use this skill to publish a local skill folder to ClawHub through the already-authenticated local ClawHub account.

Core rule

Only publish skills that have already passed local review. Do not publish directly from vague drafts, half-finished folders, or unreviewed third-party skills.

Preferred workflow

  1. Confirm the local skill folder path.
  2. Check login state with clawhub whoami.
  3. Inspect the current remote skill with clawhub inspect \x3Cslug> when updating an existing skill.
  4. Decide the target version and changelog.
  5. Perform a public-release sensitive-data review on the exact outbound payload.
  6. Package the skill with package_skill.py if a distributable artifact is needed.
  7. Upload using scripts/publish_to_clawhub.js.
  8. Verify with clawhub inspect \x3Cslug> after upload.
  9. Report the final remote version and URL.

Assistant-created skills policy

When the user has explicitly asked that assistant-created skills be uploaded to ClawHub, treat this skill as the single publish flow for both:

  • one-off manual releases
  • newly created local skills after review and commit

For newly created assistant-authored skills:

  1. Confirm the new skill folder exists under workspace/skills/\x3Cslug>.
  2. Confirm it has already been reviewed and committed locally.
  3. Inspect remote state with clawhub inspect \x3Cslug>.
  4. Versioning:
    • if missing remotely: publish 0.1.0
    • if already present: bump patch version
  5. Use a short changelog such as Initial release, Add runtime notes, Refine trigger description, or Document proven workflow.
  6. Publish and verify.
  7. If a registry sheet exists, update it too.

Rate-limit fallback for new skills

ClawHub may rate-limit new skill creation (for example: max 5 new skills per hour).

When a publish attempt for a new skill fails due to rate limiting:

  1. Do not keep hammering the endpoint.
  2. Record the pending publish locally.
  3. Schedule a delayed retry instead of requiring the user to remind you.
  4. Use the same verified publish flow when retrying.

Preferred local queue file:

  • workspace/research/clawhub-publish-queue.md

Queue fields:

  • date
  • slug
  • local skill path
  • target version
  • changelog
  • reason queued
  • next retry note

Retry rule:

  • wait until the rate-limit window has plausibly cleared
  • then retry publication once
  • verify with clawhub inspect \x3Cslug> after success

Safety and release rules

  • Do not publish without an explicit user request.
  • Do not guess ownership, slug, or version when ambiguity matters.
  • Prefer patch bumps for small documentation or rule updates.
  • If the remote state is unclear, inspect first instead of overwriting blindly.
  • If a third-party publisher skill promises features but lacks code, ignore it and use this verified local flow.
  • Treat package-style publisher shells as untrusted until verified locally: if the folder is mostly README / metadata and lacks runnable implementation, do not route publishing through it.
  • Do not publish vague drafts or half-finished skills just because they were created; assistant-created skills still need to be coherent and committed.
  • ClawHub is a public-release path unless explicitly proven otherwise; use the highest sensitivity review bar.
  • Before upload, inspect the exact outbound payload for secrets, tokens, passwords, cookies, local absolute paths, runtime artifacts, .env, and machine-specific config.
  • If the skill package contains anything that should stay local-only, stop and fix the package before publishing.

Required local assumptions

This skill expects:

  • local clawhub CLI installed and authenticated
  • local ClawHub config present under the current user
  • a real skill directory containing SKILL.md
  • Node available for the publish script

Scripts

Use scripts/publish_to_clawhub.js for the actual API upload.

Arguments:

node scripts/publish_to_clawhub.js --skill-path \x3Cpath> --slug \x3Cslug> --version \x3Cversion> --changelog \x3Ctext>

Optional:

--display-name \x3Cname>
--tag \x3Ctag>   # repeatable

References

Read references/release-checklist.md before publishing when the release is important or public.

Output style

Report with this structure:

  • skill
  • local path
  • prior remote version (if any)
  • target version
  • upload result
  • verification result
  • final URL
  • risks or follow-ups
  • whether publication succeeded immediately or was queued for delayed retry

Keep it short and operational.

安全使用建议
This skill appears to do what it says: it reads your local ClawHub config (to get a bearer token and registry URL) and uploads the entire skill folder to that registry. Before running it: 1) manually inspect the folder you plan to publish and remove or move any .env, secrets, machine-specific files, or credentials; 2) confirm the ClawHub config's registry and token are correct and not pointing to an unexpected domain; 3) run the publish on a reviewed/committed skill only (as the SKILL.md instructs). If you want extra safety, copy the skill to a temporary directory, strip sensitive files, then run the script against the sanitized copy.
功能分析
Type: OpenClaw Skill Name: clawhub-publish-flow Version: 0.1.3 The skill provides a workflow for publishing local directories to a remote registry (clawhub.ai) using a stored authentication token. The script `scripts/publish_to_clawhub.js` accesses sensitive configuration files in the user's home directory (e.g., `~/.config/clawhub/config.json`) to retrieve a Bearer token and performs a recursive file upload to an external API. While these actions are aligned with the stated purpose and the `SKILL.md` includes safety instructions for the agent to review data before release, the inherent capabilities of credential access and remote data transmission are high-risk behaviors.
能力评估
Purpose & Capability
Name/description, SKILL.md, and the included publish script consistently implement a local ClawHub publish flow. The script reads a local ClawHub config for a token and uploads the skill directory — behavior expected for a publisher.
Instruction Scope
SKILL.md narrowly scopes actions (confirm folder, inspect remote, review outbound payload, do not publish secrets). The publish script, however, will include every file under the skill path (no allowlist/denylist). This is coherent with the purpose but raises an operational risk: if the user fails to perform the required sensitive-data review, secrets (e.g., .env, credentials) could be uploaded. Also the script uses the registry URL from the local config (cfg.registry), so a compromised/misconfigured config could redirect uploads to a different endpoint.
Install Mechanism
Instruction-only skill with an included Node script; no install spec or remote downloads. Low install risk — nothing is written to disk by the installer because there is no installer.
Credentials
No environment variables are requested; the script reads ClawHub config files from standard home-directory locations for a bearer token (expected for publishing). This access is proportionate, but the script will transmit whatever is in the skill folder and uses the registry field from the config, so the config controls both the auth token and target endpoint.
Persistence & Privilege
Skill is not always-enabled, does not request persistent elevated privileges, and does not modify other skill/system configurations. Normal autonomous invocation settings apply.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install clawhub-publish-flow
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /clawhub-publish-flow 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.1.3
Sanitize local path reference from public skill
v0.1.2
Absorb redundant publisher-shell guidance and retire local duplicate clawhub-publisher skill
v0.1.1
Merge assistant-created skill auto-publish flow
v0.1.0
Initial release. Verified local ClawHub publish flow using authenticated CLI session and direct API upload, with release checklist and reusable publish script.
元数据
Slug clawhub-publish-flow
版本 0.1.3
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 4
常见问题

clawhub-publish-flow 是什么?

Publish or update an OpenClaw skill on ClawHub using the local authenticated ClawHub session and direct API upload. Use when the user wants to publish a new... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 328 次。

如何安装 clawhub-publish-flow?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install clawhub-publish-flow」即可一键安装,无需额外配置。

clawhub-publish-flow 是免费的吗?

是的,clawhub-publish-flow 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

clawhub-publish-flow 支持哪些平台?

clawhub-publish-flow 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 clawhub-publish-flow?

由 G-Hanasq(@g-hanasq)开发并维护,当前版本 v0.1.3。

💬 留言讨论