Repository
aiming-lab/MetaClaw agent skills
- skills
- 36
- GitHub stars
- 3.5k
GitHub description: “🦞 Just talk to your agent — it learns and EVOLVES 🧬.”
- Stars
- 3,459 (449 forks)
- Licence
- MIT
- Last push
- Jun 2026
- Created
- Mar 2026
- Homepage
- arxiv.org/abs/2603.17187
- agent
- ai-agent
- fine-tuning
- llm
- lora
- metaclaw
- online-learning
- reinforcement-learning
- skill-learning
- openclaw
- meta-learning
- continual-learning
- tinker
Install all skills
npx skills add aiming-lab/MetaClawAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in aiming-lab/MetaClaw, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Use this skill before any data analysis, transformation, or modeling. | aiming-lab/ | 3.5k | — | ~230 | Automated safety check: Pass | MIT | 4 mo ago |
| 2 | A skill your agent uses when implementing any endpoint, form handler, CLI tool, or function that accepts external input. | aiming-lab/ | 3.5k | — | ~251 | Automated safety check: Pass | MIT | 4 mo ago |
| 3 | A skill your agent uses when writing shell scripts, Python automation, or any unattended batch job. | aiming-lab/ | 3.5k | — | ~225 | Automated safety check: Pass | MIT | 4 mo ago |
| 4 | A skill your agent uses when building production services, pipelines, or automation that needs to be debugged, monitored, or audited. | aiming-lab/ | 3.5k | — | ~247 | Automated safety check: Pass | MIT | 4 mo ago |
| 5 | A skill your agent uses when delegating a subtask to a sub-agent, spawning a parallel worker, or handing off work across sessions. | aiming-lab/ | 3.5k | — | ~258 | Automated safety check: Pass | MIT | 4 mo ago |
| 6 | A skill your agent uses when writing messages in async channels (Slack, GitHub issues, email threads) where the reader may not have context and cannot ask follow-up questions immediately. | aiming-lab/ | 3.5k | — | ~224 | Automated safety check: Pass | MIT | 4 mo ago |
| 7 | A skill your agent uses when writing any explanation, documentation, or response that will be read by someone else. | aiming-lab/ | 3.5k | — | ~227 | Automated safety check: Pass | MIT | 4 mo ago |
| 8 | A skill your agent uses when implementing authentication (login, token issuance) or authorization (access control, permissions). | aiming-lab/ | 3.5k | — | ~285 | Automated safety check: Pass | MIT | 4 mo ago |
| 9 | A skill your agent uses when exploring an unfamiliar codebase, tracing code paths, or answering questions about how the system works. | aiming-lab/ | 3.5k | — | ~286 | Automated safety check: Pass | MIT | 4 mo ago |
| 10 | Use this skill in long conversations or multi-turn agentic sessions where context may be lost or the conversation is approaching token limits. | aiming-lab/ | 3.5k | — | ~250 | Automated safety check: Pass | MIT | 4 mo ago |
| 11 | A skill your agent uses when diagnosing a bug, unexpected behavior, test failure, or any situation where code does not behave as expected. | aiming-lab/ | 3.5k | — | ~234 | Automated safety check: Pass | MIT | 4 mo ago |
| 12 | 12.Git Workflow A skill your agent uses when working with git — making commits, creating branches, resolving merge conflicts, opening pull requests, or reviewing diffs. | aiming-lab/ | 3.5k | — | ~234 | Automated safety check: Pass | MIT | 4 mo ago |
| 13 | A skill your agent uses when writing scripts, cron jobs, data pipelines, or any automated process that may be run multiple times. | aiming-lab/ | 3.5k | — | ~249 | Automated safety check: Pass | MIT | 4 mo ago |
| 14 | Use this skill before executing a sequence of 3 or more steps, especially when steps are irreversible or depend on each other. | aiming-lab/ | 3.5k | — | ~227 | Automated safety check: Pass | MIT | 4 mo ago |
| 15 | A skill your agent uses when drafting emails, Slack messages, announcements, or any external/internal communication. | aiming-lab/ | 3.5k | — | ~236 | Automated safety check: Pass | MIT | 4 mo ago |
| 16 | A skill your agent uses when handling API keys, passwords, tokens, private keys, or any sensitive credential. | aiming-lab/ | 3.5k | — | ~246 | Automated safety check: Notes | MIT | 4 mo ago |
| 17 | A skill your agent uses when reviewing or writing code that handles user input, authentication, file I/O, network requests, or database queries. | aiming-lab/ | 3.5k | — | ~249 | Automated safety check: Pass | MIT | 4 mo ago |
| 18 | A skill your agent uses when presenting information from external sources, citing research, or answering factual questions. | aiming-lab/ | 3.5k | — | ~220 | Automated safety check: Pass | MIT | 4 mo ago |
| 19 | A skill your agent uses when writing SQL queries — selects, joins, aggregations, window functions, or schema modifications. | aiming-lab/ | 3.5k | — | ~234 | Automated safety check: Pass | MIT | 4 mo ago |
| 20 | A skill your agent uses when conducting research on a topic from scratch — literature review, competitive analysis, technical due diligence, or fact-finding. | aiming-lab/ | 3.5k | — | ~249 | Automated safety check: Pass | MIT | 4 mo ago |
| 21 | A skill your agent uses when writing documentation, READMEs, technical specs, runbooks, or any text that explains a system or process to other engineers. | aiming-lab/ | 3.5k | — | ~244 | Automated safety check: Pass | MIT | 4 mo ago |
| 22 | A skill your agent uses when implementing a new feature or fixing a bug. | aiming-lab/ | 3.5k | — | ~232 | Automated safety check: Pass | MIT | 4 mo ago |
| 23 | A skill your agent uses when deciding which tools to call in an agentic workflow. | aiming-lab/ | 3.5k | — | ~257 | Automated safety check: Pass | MIT | 4 mo ago |
| 24 | Use this skill before taking any action that is hard to reverse — deleting files, overwriting data, sending messages, pushing to remote, modifying production systems. | aiming-lab/ | 3.5k | — | ~232 | Automated safety check: Pass | MIT | 4 mo ago |
| 25 | A skill your agent uses when creating charts, plots, or dashboards. | aiming-lab/ | 3.5k | — | ~213 | Automated safety check: Pass | MIT | 4 mo ago |
| 26 | Common mistake — stating specific facts (API endpoints, library versions, config options, function signatures) with false confidence when uncertain. | aiming-lab/ | 3.5k | — | ~227 | Automated safety check: Pass | MIT | 4 mo ago |
| 27 | Common mistake — doing unrequested work (refactoring, adding extra features, cleaning up style) when the user asked for a specific, targeted change. | aiming-lab/ | 3.5k | — | ~209 | Automated safety check: Pass | MIT | 4 mo ago |
| 28 | A skill your agent uses when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways. | aiming-lab/ | 3.5k | — | ~216 | Automated safety check: Pass | MIT | 4 mo ago |
| 29 | A skill your agent uses when a tool call, command, or API request fails. | aiming-lab/ | 3.5k | — | ~221 | Automated safety check: Pass | MIT | 4 mo ago |
| 30 | A skill your agent uses when the user has a list of tasks and needs help deciding what to do first. | aiming-lab/ | 3.5k | — | ~199 | Automated safety check: Pass | MIT | 4 mo ago |
| 31 | A skill your agent uses when summarizing progress on an ongoing project or multi-step task. | aiming-lab/ | 3.5k | — | ~206 | Automated safety check: Pass | MIT | 4 mo ago |
| 32 | A skill your agent uses for any problem that involves multiple steps, tradeoffs, or non-trivial logic. | aiming-lab/ | 3.5k | — | ~212 | Automated safety check: Pass | MIT | 4 mo ago |
| 33 | A skill your agent uses when a user presents a large, vague goal. | aiming-lab/ | 3.5k | — | ~185 | Automated safety check: Pass | MIT | 4 mo ago |
| 34 | A skill your agent uses when you are not sure about a fact, have outdated knowledge, or the question is contested. | aiming-lab/ | 3.5k | — | ~208 | Automated safety check: Pass | MIT | 4 mo ago |
| 35 | Common mistake — proceeding with assumptions about ambiguous requirements instead of asking a clarifying question first. | aiming-lab/ | 3.5k | — | ~214 | Automated safety check: Pass | MIT | 4 mo ago |
| 36 | Common mistake — retrying the same failing command or API call without understanding why it failed. | aiming-lab/ | 3.5k | — | ~189 | Automated safety check: Pass | MIT | 4 mo ago |
Questions, answered from the data.
What is the best skill in aiming-lab/MetaClaw?
Data Validation First from aiming-lab/MetaClaw ranks first of the 36 skills in aiming-lab/MetaClaw listed here, with the highest score: its repository has 3.5k GitHub stars, its SKILL.md loads about 230 tokens and it passes the automated safety check with no findings. Next come Input Validation And Sanitization and Robust Error Handling In Scripts.
Are the skills in aiming-lab/MetaClaw official?
None yet. All 36 skills in aiming-lab/MetaClaw listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from aiming-lab/MetaClaw?
Run npx skills add aiming-lab/MetaClaw in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.