tidybot-services/tidybot-universe/tidybot-skill-publish

Claude Code and agent skill by tidybot-services/tidybot-universe

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Publish a tested robot skill to the tidybot-skills org. Use when the user approves publishing a skill from the dev/ folder.

Install

npx vskill@latest install tidybot-services/tidybot-universe/tidybot-skill-publish

SKILL.md

Tidybot Skill Publishing

Only publish when the user explicitly approves. Ask first: "Want me to publish this so other Tidybots can use it?"

Prerequisites

  • Skill has dev-tb- prefix with proper OpenClaw structure (SKILL.md, scripts/main.py, scripts/deps.txt)
  • Skill has 70%+ cumulative success rate
  • Stats were not invalidated by recent code changes (any code change resets stats — re-test first)
  • GitHub CLI authenticated (gh auth login)

Publishing Steps

  1. Rename from `dev-tb-` to `tb-`: Move the skill folder from dev-tb-my-skill/ to tb-my-skill/.
  1. Create a repo in the tidybot-skills org. The repo name drops the tb- prefix (e.g. local tb-pick-up-object → remote tidybot-skills/pick-up-object):

``bash gh repo create tidybot-skills/<skill-name-without-tb-prefix> --public ``

  1. Push skill code to the new repo
  1. Update `catalog.json` in tidybot-skills/wishlist:

``json { "<skill-name>": { "repo": "tidybot-skills/<skill-name>", "description": "What the skill does", "author": "<your-agent-name>", "dependencies": ["dep1", "dep2"], "success_rate": 0, "total_trials": 0, "institutions_tested": 0 } } ` Set success_rate and total_trials to 0` — public stats start fresh.

  1. Update `wishlist.json` if this skill fulfills a wishlist item — set status to "done" and add the repo path

Catalog Fields

FieldDescription
repoGitHub repo path (tidybot-skills/<name>)
descriptionWhat the skill does
authorAgent or person who built it
dependenciesList of skill repo names this depends on
success_ratePercentage of successful trials (0–100)
total_trialsTotal number of trial runs performed
institutions_testedNumber of distinct labs that tested this

Wishlist Status Values

StatusMeaning
pendingNot started
buildingAgent working on it
doneAvailable in catalog.json

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
57
Repository forks
2
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/tidybot-services/tidybot-universe/tidybot-skill-publish/badge)](https://verified-skill.com/skills/tidybot-services/tidybot-universe/tidybot-skill-publish)

Something wrong with this skill or its page? Tell us.