github.com/Hmbown/Codewhale
| Skill | Added | Review |
|---|---|---|
batch crates/tui/assets/skills/batch/SKILL.md Break a large, parallelizable goal into bounded work units, coordinate existing agent/worktree machinery, integrate, and verify. Explicit-only. | 49 49 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 21282f1 | |
best-of-n crates/tui/assets/skills/best-of-n/SKILL.md Generate a small set of independent candidate solutions in worktrees, judge them against one explicit rubric, and apply the winner only after PASS verification. | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 21282f1 | |
codew-release-qa-sweep docs/skills/codew-release-qa-sweep/SKILL.md Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets. | 68 68 Impact — No eval scenarios have been run Securityby — The risk profile of this skill Version: 21282f1 | |
computer-use crates/tui/plugins/computer-use/skills/computer-use/SKILL.md Desktop control with accessibility-first observation and actions, pixel fallback, screenshots, zoom, screen recording, and switching between registered computers. Qualified on macOS; Windows, Linux and HarmonyOS backends are experimental. | — | |
contributor-onboarding crates/tui/assets/skills/contributor-onboarding/SKILL.md Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only. | 69 69 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 21282f1 | |
cw-dogfood docs/skills/cw-dogfood/SKILL.md Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover. | 73 73 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 21282f1 | |
cw-gates docs/skills/cw-gates/SKILL.md Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test. | 71 71 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 21282f1 | |
cw-handoff docs/skills/cw-handoff/SKILL.md Use when writing a Codewhale takeover prompt, continuation note, or end-of-session summary for another agent or a later session: a paste-ready handoff grounded in live state, with done/suspected/blocked kept separate. | 74 74 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 21282f1 | |
dataviz crates/tui/assets/skills/dataviz/SKILL.md Choose and produce an appropriate chart/dashboard/visual explanation from data, with legible encodings and source/assumption notes. | 59 59 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 21282f1 | |
debug crates/tui/assets/skills/debug/SKILL.md Reproduce, minimize, localize, identify root cause, and distinguish diagnosis from an authorized fix. Prefer root-cause over symptom patches. | 65 65 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 21282f1 | |
delegate crates/tui/assets/skills/delegate/SKILL.md Strategic delegation for multi-step coding, research, or verification work. Use when a task can be split into parent reasoning plus focused sub-agent execution through the agent tool. | 68 68 Impact — No eval scenarios have been run Securityby — The risk profile of this skill Version: 21282f1 | |
dependency-update crates/tui/assets/skills/dependency-update/SKILL.md Read release notes/changelogs, update a defined dependency scope, handle breaking changes, and verify. Explicit-only; no broad update-everything by inference. | 58 58 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 21282f1 | |
documents crates/tui/assets/skills/documents/SKILL.md Compatibility alias for the docx skill. Prefer loading docx. | 60 60 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 21282f1 | |
docx crates/tui/assets/skills/docx/SKILL.md Create/edit/inspect Word documents using available managed or host capabilities. | 54 54 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 21282f1 | |
feishu crates/tui/assets/skills/feishu/SKILL.md Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials. | 68 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 21282f1 | |
fleet-manager crates/tui/assets/skills/fleet-manager/SKILL.md Use when managing, triaging, restarting, escalating, or summarizing Codewhale fleet runs and workers. | 75 75 Impact — No eval scenarios have been run Securityby — The risk profile of this skill Version: 21282f1 | |
frontend-design crates/tui/assets/skills/frontend-design/SKILL.md Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly. | 55 55 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 21282f1 | |
gh-assign-issues docs/skills/gh-assign-issues/SKILL.md Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each. | 66 66 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 21282f1 | |
gh-close-issues docs/skills/gh-close-issues/SKILL.md Close resolved Codewhale issues only after verifying the landed commit/behavior, with a positive crediting comment; never from title alone. | 64 64 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 21282f1 | |
gh-compile-issues docs/skills/gh-compile-issues/SKILL.md Triage N GitHub issues into a coverage matrix: fetch each, check current code, classify already-done/quick-fix/design/defer with cited evidence. | 68 68 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 21282f1 |