heg-wtf/src/abyss/builtin_skills/code_review
src/abyss/builtin_skills/code_review/SKILL.md
# code_review Run a Claude Code `ultrareview` on a pull request or local target and summarize findings back to the user. Use this when the user asks for a code review, asks you to "ultrareview", drops a PR link, or otherwise wants a multi-aspect review of code rather than a free-form chat about a diff. ## When to use Trigger this skill when the message is clearly a review request: - A GitHub / GitLab / Bitbucket PR URL. - A bare PR number (e.g. `#123`). - A local path (`src/auth/`) plus the
$ install --global
skillsauthnpx skillsauth add heg-wtf/cclaw src/abyss/builtin_skills/code_reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 30, 2026, 2:39 AM6.7s2 files scanned
SKILL.md
code_review
Run a Claude Code ultrareview on a pull request or local target and summarize
findings back to the user. Use this when the user asks for a code review, asks
you to "ultrareview", drops a PR link, or otherwise wants a multi-aspect review
of code rather than a free-form chat about a diff.
When to use
Trigger this skill when the message is clearly a review request:
- A GitHub / GitLab / Bitbucket PR URL.
- A bare PR number (e.g.
#123). - A local path (
src/auth/) plus the word "review". - An explicit
/reviewor "review this" instruction.
Skip it for casual code questions ("what does this function do?"), small code edits, or pure search tasks.
How to invoke
Call the Claude Code ultrareview subcommand via Bash. It runs the same
parallel review pipeline used by the human-side /ultrareview slash
command and prints a structured JSON payload to stdout:
claude ultrareview <target> --json
<target> is whatever the user provided (PR URL, PR number, or local
path). The default review timeout is 30 minutes; ultrareview manages its
own progress, so do not wrap it in a shorter timeout.
If the review is exploratory, prefer --json so you can extract
findings programmatically. Drop --json only when the user explicitly
asks for prose.
Effort
Match the review depth to the bot's session effort level: ${CLAUDE_EFFORT}.
At low keep the summary tight (top 3 issues only). At high / xhigh /
max, walk through every finding with file path and one-line rationale.
At medium, group findings by category and surface the top 5.
How to summarize
After ultrareview returns, write the user a short report:
- Lead with the headline severity — block / fix-required / nitpick / lgtm.
- List findings as bullet points:
path:line — one-line summary. - End with a one-sentence recommendation (merge, request changes, needs discussion).
Keep the message under ~30 lines. If there are more findings than that,
say "+N more — paste again with verbose: for the full report" and
truncate.
Failure modes
ultrareviewexits 1 → relay the stderr message to the user and stop. Do not retry without their say-so.- Timeout (30 min) → tell the user the review didn't complete, suggest they re-run with a smaller scope.
- Target ambiguous (e.g. multiple PRs match a branch name) → ask the user to disambiguate before running.
Related Skills
heg-wtf/src/abyss/builtin_skills/linear
tools
VerifiedTrustedCommunity
# Linear Linear 이슈 트래커 MCP (stdio, personal API token). 이슈 검색·생성·수정·코멘트, 팀/프로젝트/사이클 조회, 우선순위/라벨/할당자 관리. **Always confirm before creating/updating issues or posting comments.** 생성 전 team·project·title·assignee 확인 후 승인. 상태 전환 전 현재→목표 확인 후 승인. 일괄 수정 금지. 삭제는 사용 안 함 (status를 cancelled / done으로 전환 제안). ## Auth 서버: [`@tacticlaunch/mcp-linear`](https://www.npmjs.com/package/@tacticlaunch/mcp-linear) (stdio, `npx -y`). 인증: 환경변수 **`LINEAR_API_TOKEN`** (Linear → Settings → API → "Create new personal AP
4SKILL.mdUpdated Jun 5, 2026
heg-wtf/src/abyss/builtin_skills/about_me
tools
VerifiedTrustedCommunity
# About Me (Shared User Knowledge Base) You have a structured, shared knowledge base about the user across seven categories: `identity`, `relationships`, `preferences`, `routines`, `current_focus`, `health`, `values`. A short index of confirmed facts is already in your CLAUDE.md system prompt under the **About Me (Shared, Read-Only)** section. You have **four tools** to interact with this knowledge base: - `about_me_propose` — propose a new fact you have just learned - `about_me_get` — read e
4SKILL.mdUpdated May 19, 2026
heg-wtf/src/abyss/builtin_skills/conversation_search
tools
VerifiedTrustedCommunity
# Conversation Search You have a tool that searches your **own past conversations with the user**. Use it when you need to recall something specific that the user mentioned earlier and is no longer in the visible context window. ## When to call `search_conversations` Call this tool when **any** of the following is true: - The user asks about something they previously told you ("지난주에 추천한 책 뭐였지?", "what was the cafe name I mentioned?"). - They reference a past plan, decision, or commitment t
4SKILL.mdUpdated Apr 26, 2026
heg-wtf/src/abyss/builtin_skills/twitter
tools
VerifiedTrustedCommunity
# Twitter Twitter/X MCP. 트윗 게시 및 검색. **Always confirm before posting.** Show full tweet text and get user approval. 280자 제한. 민감정보(비밀번호, API키, 개인정보) 게시 금지. 스팸성 반복 게시 금지. ## Operations ### Post Tweet - 텍스트 작성 → 사용자에게 보여주기 → 승인 후 게시 - 280자 초과 시 트리밍 또는 스레드 분할 제안 ### Search Tweets - 검색 문법: `from:username`, `to:username`, `keyword`, `#hashtag`, `keyword lang:ko` - 결과: 작성자, 텍스트, 날짜 형식으로 정리 ## Notes - Free tier: 500 posts/month - Rate limit 발생 시 사용자에게 안내
4SKILL.mdUpdated Apr 25, 2026