Repository
av/mi agent skills
- skills
- 20
- GitHub stars
- 102
GitHub description: “self-extending sandboxed agentic harness. a loop, two tools and an llm”
- Stars
- 102 (8 forks)
- Licence
- No licence
- Last push
- Sep 2026
- Created
- Apr 2026
- Source
- github.com/av/mi
- agentic-ai
- agentic-coding
- ai
- cli
- codegolf
- harness
- llm
- repl
- autonomous-agent
- coding-agent
- developer-tools
- sandbox
Install all skills
npx skills add av/miAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in av/mi, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Writes plain-English integration test specs with verifiable steps and expectations, then runs each one through a subagent that reports pass or fail with logs. | av/ | 102 | — | ~908 | Automated safety check: Pass | No licence | 11 days ago |
| 2 | 2.Anneal A skill your agent uses when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult patterns, and other… | av/ | 102 | — | ~3.8k | Automated safety check: Pass | No licence | 11 days ago |
| 3 | Scans a codebase to tag every fact as draft, spec or implemented based on what the code actually shows, adding missing facts and fixing or removing wrong ones. | av/ | 102 | — | ~2.8k | Automated safety check: Pass | No licence | 11 days ago |
| 4 | Implements every @spec fact from a project's fact sheet in code, tags each one @implemented once done, and reports exactly what is left if it cannot finish. | av/ | 102 | — | ~1.3k | Automated safety check: Pass | No licence | 11 days ago |
| 5 | Works with you to turn draft behavioral facts into precise, implementable spec facts, resolving vague labels, gaps and contradictions one at a time through discussion. | av/ | 102 | — | ~1.5k | Automated safety check: Pass | No licence | 11 days ago |
| 6 | 6.Ideate Timeboxed ideation on a topic using propose-and-critique subagent pairs. | av/ | 102 | — | ~2.8k | Automated safety check: Pass | No licence | 11 days ago |
| 7 | 7.Self Answer questions about how 'mi' works, write new tools, or modify the harness. | av/ | 102 | — | ~1.4k | Automated safety check: Pass | No licence | 11 days ago |
| 8 | Runs a task for a fixed duration by dispatching subagents in a loop, with the clock, not the agent, deciding when to stop. | av/ | 102 | — | ~2.3k | Automated safety check: Pass | No licence | 11 days ago |
| 9 | Autonomous software production with continuous runtime verification. | av/ | 102 | — | ~6.8k | Automated safety check: Pass | No licence | 11 days ago |
| 10 | 10.Debug Fix bugs, crashes, errors, or failing tests. An agent skill from av/mi. | av/ | 102 | — | ~871 | Automated safety check: Pass | No licence | 11 days ago |
| 11 | 11.Plan Write a strategy doc before starting multi-step, multi-file, or unclear work. | av/ | 102 | — | ~484 | Automated safety check: Pass | No licence | 11 days ago |
| 12 | 12.Review Review code, a PR, branch, or staged diff. An agent skill from av/mi. | av/ | 102 | — | ~865 | Automated safety check: Pass | No licence | 11 days ago |
| 13 | 13.Tasks Track a numbered list of steps to completion. An agent skill from av/mi. | av/ | 102 | — | ~701 | Automated safety check: Pass | No licence | 11 days ago |
| 14 | 14.Bugbash Systematically explores a CLI, API, backend or library to find bugs and edge cases, then writes a report with reproduction evidence for each issue. | av/ | 102 | — | ~1.4k | Automated safety check: Pass | No licence | 11 days ago |
| 15 | 15.Discipline Bulletproof agent operating protocol. An agent skill from av/mi. | av/ | 102 | — | ~3.4k | Automated safety check: Pass | No licence | 11 days ago |
| 16 | 16.Refactor Restructure code without changing behavior. An agent skill from av/mi. | av/ | 102 | — | ~1.2k | Automated safety check: Pass | No licence | 11 days ago |
| 17 | 17.Verify Run lint, typecheck, tests, or build — and fix any failures found. | av/ | 102 | — | ~1.2k | Automated safety check: Pass | No licence | 11 days ago |
| 18 | 18.Delegate Run parallel or isolated subagents for independent subtasks (research, parallel analysis, one-shot transforms) to avoid bloating the main context. | av/ | 102 | — | ~599 | Automated safety check: Pass | No licence | 11 days ago |
| 19 | 19.Explore Answer "how does X work", "where is X defined", or "trace through Y" questions about a codebase using parallel subagent searches with cited summaries. | av/ | 102 | — | ~958 | Automated safety check: Pass | No licence | 11 days ago |
| 20 | 20.TDD Add new behavior test-first (write failing test → make it pass → refactor). | av/ | 102 | — | ~972 | Automated safety check: Pass | No licence | 11 days ago |
Questions, answered from the data.
What is the best skill in av/mi?
Agent Integration Testing from av/mi ranks first of the 20 skills in av/mi listed here, with the highest score: its repository has 102 GitHub stars, its SKILL.md loads about 908 tokens and it passes the automated safety check with no findings. Next come Anneal and Fact Sheet Discovery and Sync.
Are the skills in av/mi official?
None yet. All 20 skills in av/mi 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 av/mi?
Run npx skills add av/mi 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.