GitHub user
Agent skills by hex
- skills
- 10
- repository
- 1
Repositories by hex
Skills by hex, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Runs a local council when no external AI providers are configured. | hex/ | 848 | — | ~1.6k | Automated safety check: Pass | MIT | yesterday |
| 2 | Executes council queries by running the query pipeline across selected AI providers (Gemini, OpenAI, Grok, Perplexity), displaying formatted responses verbatim, and generating a synthesis of… | hex/ | 848 | — | ~824 | Automated safety check: Pass | MIT | yesterday |
| 3 | Executes agent-enhanced council queries as one Workflow of parallel Claude analyst agents that each query a provider, evaluate response quality, ask follow-up questions, and return a schema-enforced… | hex/ | 848 | — | ~2.5k | Automated safety check: Pass | MIT | yesterday |
| 4 | Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface. | hex/ | 848 | — | ~635 | Automated safety check: Pass | MIT | yesterday |
| 5 | A bug reproduces, the expected behaviour is clear, and the fix stands apart from the current work. | hex/ | 848 | — | ~991 | Automated safety check: Pass | MIT | yesterday |
| 6 | 6.CI Fixer A CI job fails on a named revision and the fix belongs in code, config or tests, not in the CI provider. | hex/ | 848 | — | ~941 | Automated safety check: Pass | MIT | yesterday |
| 7 | Docs must be updated or restructured to match code that already changed: README, reference pages, CLI help or config docs. | hex/ | 848 | — | ~930 | Automated safety check: Pass | MIT | yesterday |
| 8 | A behaviour-preserving restructure is named: extract, rename, move, split a module, or remove duplication across three or more sites. | hex/ | 848 | — | ~984 | Automated safety check: Pass | MIT | yesterday |
| 9 | Tests in a named area duplicate stronger tests, re-assert the implementation, or keep test-only seams alive, and need pruning. | hex/ | 848 | — | ~1.1k | Automated safety check: Pass | MIT | yesterday |
| 10 | 10.Test Writer The task is to add or extend tests for existing behaviour that has a spec, a documented contract, or a confirmed expected output. | hex/ | 848 | — | ~1.1k | Automated safety check: Pass | MIT | yesterday |
Questions, answered from the data.
What is the best skill by hex?
Local Council Execution from hex/claude-council ranks first of the 10 skills by hex listed here, with the highest score: its repository has 848 GitHub stars, its SKILL.md loads about 1.6k tokens and it passes the automated safety check with no findings. Next come Council Execution and Deep Execution.
Are hex's skills official?
None yet. All 10 skills by hex listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
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.