GitHub user
Agent skills by raine
- skills
- 13
- repositories
- 2
Repositories by raine
Skills by raine, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Non-interactive hunk-level git staging, unstaging, discarding, undoing, fold, amend, squash, commit splitting, and commit reordering. | raine/ | 171 | — | ~2.3k | Automated safety check: Pass | MIT | 2 mo ago |
| 2 | Explicit workflow for one bounded implementation using source-grounded discovery, a walking slice, evidence-gated review, validation, and commit. | raine/ | 139 | — | ~2.9k | Automated safety check: Notes | MIT | yesterday |
| 3 | 3.Collab Multiple LLMs collaboratively brainstorm solutions, building on each other's ideas across rounds. | raine/ | 139 | — | ~1.8k | Automated safety check: Pass | MIT | yesterday |
| 4 | The agent brainstorms with a partner LLM in alternating turns, building on each other's ideas. | raine/ | 139 | — | ~1.8k | Automated safety check: Pass | MIT | yesterday |
| 5 | 5.Consult Consult an external LLM with the user's query. An agent skill from raine/consult-llm. | raine/ | 139 | — | ~963 | Automated safety check: Notes | MIT | yesterday |
| 6 | How to invoke the consult-llm CLI. An agent skill from raine/consult-llm. | raine/ | 139 | — | ~2.9k | Automated safety check: Notes | MIT | yesterday |
| 7 | 7.Debate LLMs propose and critique approaches, agent moderates the debate and synthesizes the best solution, then implements. | raine/ | 139 | — | ~2.5k | Automated safety check: Pass | MIT | yesterday |
| 8 | The agent debates an opponent LLM through a multi-turn conversation, then synthesizes the best approach and implements. | raine/ | 139 | — | ~2.5k | Automated safety check: Pass | MIT | yesterday |
| 9 | 9.Panel Role-specialized LLM panel analyzes a task from asymmetric expert lenses (architect, security, maintainability, test-strategist by default). | raine/ | 139 | — | ~3.1k | Automated safety check: Notes | MIT | yesterday |
| 10 | Coordinator workflow for multi-phase implementation across workmux worktrees. | raine/ | 139 | — | ~4.2k | Automated safety check: Notes | MIT | yesterday |
| 11 | 11.Review Collect critical feedback from all registered LLMs on an artifact (architecture doc, implementation, plan). | raine/ | 139 | — | ~2.4k | Automated safety check: Notes | MIT | yesterday |
| 12 | 12.Review Panel Standalone multi-model code review of an existing diff. An agent skill from raine/consult-llm. | raine/ | 139 | — | ~2.8k | Automated safety check: Notes | MIT | yesterday |
| 13 | 13.Workshop Interactive design session — agent facilitates a clarifying dialogue with the user, fans out to multiple LLMs in parallel for divergent approach generation, lets the user pick one, then co-designs… | raine/ | 139 | — | ~3.7k | Automated safety check: Notes | MIT | yesterday |
Questions, answered from the data.
What is the best skill by raine?
Git Surgeon from raine/git-surgeon ranks first of the 13 skills by raine listed here, with the highest score: its repository has 171 GitHub stars, its SKILL.md loads about 2.3k tokens and it passes the automated safety check with no findings. Next come Implement and Collab.
Are raine's skills official?
None yet. All 13 skills by raine 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.