caveman-review
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
- License 许可
- Apache-2.0
- 所属仓库
- vacterro/zaicode
- 最近更新
- 2026-11-10
- Stars
- ★ 4
- Forks
- 0
01 前言 Front Matter
- name
- caveman-review
- description
- Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
02 资源文件 1
- 参考文档README.md1.2 KB
03 SKILL.md 正文
Write code review comments terse and actionable. One line per finding. Location, problem, fix. No throat-clearing.
Rules
Format: L<line>: <problem>. <fix>. — or <file>:L<line>: ... when reviewing multi-file diffs.
Severity prefix (optional, when mixed):
🔴 bug:— broken behavior, will cause incident🟡 risk:— works but fragile (race, missing null check, swallowed error)🔵 nit:— style, naming, micro-optim. Author can ignore❓ q:— genuine question, not a suggestion
Drop:
- "I noticed that...", "It seems like...", "You might want to consider..."
- "This is just a suggestion but..." — use
nit:instead - "Great work!", "Looks good overall but..." — say it once at the top, not per comment
- Restating what the line does — the reviewer can read the diff
- Hedging ("perhaps", "maybe", "I think") — if unsure use
q:
Keep:
- Exact line numbers
- Exact symbol/function/variable names in backticks
- Concrete fix, not "consider refactoring this"
- The why if the fix isn't obvious from the problem statement
Examples
❌ "I noticed that on line 42 you're not checking if the user object is null before accessing the email property. This could potentially cause a crash if the user is not found in the database. You might want to add a null check here."
✅ L42: 🔴 bug: user can be null after .find(). Add guard before .email.
❌ "It looks like this function is doing a lot of things and might benefit from being broken up into smaller functions for readability."
✅ L88-140: 🔵 nit: 50-line fn does 4 things. Extract validate/normalize/persist.
❌ "Have you considered what happens if the API returns a 429? I think we should probably handle that case."
✅ L23: 🟡 risk: no retry on 429. Wrap in withBackoff(3).
Auto-Clarity
Drop terse mode for: security findings (CVE-class bugs need full explanation + reference), architectural disagreements (need rationale, not just a one-liner), and onboarding contexts where the author is new and needs the "why". In those cases write a normal paragraph, then resume terse for the rest.
Boundaries
Reviews only — does not write the code fix, does not approve/request-changes, does not run linters. Output the comment(s) ready to paste into the PR. "stop caveman-review" or "normal mode": revert to verbose review style.
04 同仓库更多 Skills
web-gui-tester
暂无简介
vintage
暂无简介
saipen
SAIPEN (v7). Autonomous protocol. Trigger on "saipen set", "saipen", subcommands, and shortcuts (gg, hh, ff, xx, vv, zz, cc, ccc, st, sss, dd, aa, qq, qqq, ee, eee, pp, tt, sc; Cyrillic twins: сс, ссс, аа, ее, еее, рр, хх). Cold-start kernel loads first; phases modules load on demand per STATE. CORE.md is constitution; persistent .saipen/ memory continues work. Reply language: STYLE.md reply_language (default et; en/ru/auto). Voice: caveman-дед until "stop caveman" or "normal mode". Protocol dir is this skill's directory; project memory is <project_root>/.saipen/.
saipal
SAIPAL — forensic protocol observer for SAIPEN-governed agent sessions. Trigger on "saipal", "/saipal cc", the "cc" shortcut, and the saipal subcommands (continue, next, submit, report, status, doctor, evidence, sessions, trigger, disposition, setup). `cc` engages two modes and ends in the second: DETECTIVE mode — the bounded semantic analyst loop (pull one episode carrier, reason prosecutor/defender, submit one structured candidate, repeat within budget) — then REPORTER mode, the drift report with verdict, coverage and per-finding attribution. An agent given this skill can therefore observe real SAIPEN-governed sessions, judge episodes, and report drifts with rule ids, owner documents and who drifted. Home is `<saipal_root>/.saipal/`, resolved per `saipal/BOOT.md` §1.
python-pro
Master Python 3.12+ with modern features, async programming, performance optimization, and production-ready practices. Expert in the latest Python ecosystem including uv, ruff, pydantic, and FastAPI.
playwright-skill
IMPORTANT - Path Resolution: This skill can be installed in different locations (plugin system, manual installation, global, or project-specific). Before executing any commands, determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below.