|
| 1 | +# Skill Registry — lazysql |
| 2 | + |
| 3 | +<!-- Auto-generated by gentle-ai skill-registry refresh. Run `gentle-ai skill-registry refresh --force` to regenerate. --> |
| 4 | + |
| 5 | +Last updated: 2026-05-25 |
| 6 | + |
| 7 | +## Sources scanned |
| 8 | + |
| 9 | +- /Users/jorgerojas/.config/agents/skills |
| 10 | +- /Users/jorgerojas/.agents/skills |
| 11 | +- /Users/jorgerojas/.config/opencode/skills |
| 12 | +- /Users/jorgerojas/.gemini/skills |
| 13 | +- /Users/jorgerojas/.copilot/skills |
| 14 | +- /Users/jorgerojas/.codex/skills |
| 15 | + |
| 16 | +## Contract |
| 17 | + |
| 18 | +**Delegator use only.** This registry is an index, not a summary. Any agent that launches subagents reads it to select relevant skills, then passes exact `SKILL.md` paths for the subagent to read before work. |
| 19 | + |
| 20 | +`SKILL.md` remains the source of truth. Do not inject generated summaries or compact rules by default; pass paths so subagents load the full runtime contract and preserve author intent. |
| 21 | + |
| 22 | +## Skills |
| 23 | + |
| 24 | +| Skill | Trigger / description | Scope | Path | |
| 25 | +| --- | --- | --- | --- | |
| 26 | +| `branch-pr` | Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review. | user | `/Users/jorgerojas/.config/opencode/skills/branch-pr/SKILL.md` | |
| 27 | +| `caveman` | Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested. | user | `/Users/jorgerojas/.agents/skills/caveman/SKILL.md` | |
| 28 | +| `chained-pr` | Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus. | user | `/Users/jorgerojas/.config/opencode/skills/chained-pr/SKILL.md` | |
| 29 | +| `cognitive-doc-design` | Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs. | user | `/Users/jorgerojas/.config/opencode/skills/cognitive-doc-design/SKILL.md` | |
| 30 | +| `comment-writer` | Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments. | user | `/Users/jorgerojas/.config/opencode/skills/comment-writer/SKILL.md` | |
| 31 | +| `go-testing` | Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns. | user | `/Users/jorgerojas/.config/opencode/skills/go-testing/SKILL.md` | |
| 32 | +| `grill-with-docs` | Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions. | user | `/Users/jorgerojas/.agents/skills/grill-with-docs/SKILL.md` | |
| 33 | +| `issue-creation` | Create Gentle AI issues with issue-first checks. Trigger: creating GitHub issues, bug reports, or feature requests. | user | `/Users/jorgerojas/.config/opencode/skills/issue-creation/SKILL.md` | |
| 34 | +| `judgment-day` | Trigger: judgment day, dual review, adversarial review, juzgar. Run blind dual review, fix confirmed issues, then re-judge. | user | `/Users/jorgerojas/.config/opencode/skills/judgment-day/SKILL.md` | |
| 35 | +| `skill-creator` | Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter. | user | `/Users/jorgerojas/.config/opencode/skills/skill-creator/SKILL.md` | |
| 36 | +| `skill-improver` | Trigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills. | user | `/Users/jorgerojas/.config/opencode/skills/skill-improver/SKILL.md` | |
| 37 | +| `to-prd` | Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context. | user | `/Users/jorgerojas/.agents/skills/to-prd/SKILL.md` | |
| 38 | +| `work-unit-commits` | Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code. | user | `/Users/jorgerojas/.config/opencode/skills/work-unit-commits/SKILL.md` | |
| 39 | + |
| 40 | +## Loading protocol |
| 41 | + |
| 42 | +1. Match task context and target files against the `Trigger / description` column. |
| 43 | +2. Pass only the matching `Path` values to the subagent under `## Skills to load before work`. |
| 44 | +3. Instruct the subagent to read those exact `SKILL.md` files before reading, writing, reviewing, testing, or creating artifacts. |
| 45 | +4. If no matching skill exists, proceed without project skill injection and report `skill_resolution: none`. |
0 commit comments