메뉴
Bridge from /slang-maintain workflow steps to concrete slang-mcp tool calls. Read-only except an optional, user-confirmed post of the generated daily report to Slack. Task recipes live in sibling files.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/shader-slang/slang-skills --skill slang-maintainer-tools명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Use whenever output will name a specific person: release notes, changelogs, contributor lists, commit or PR attribution, code comments, issue and review replies, docs credits, or any prose referring to a human. Governs where a name may come from and how to choose pronouns, so stale names from git history and gender guesses from model priors never reach the output.
Surface the open shader-slang PRs needing human attention with a bundled gh-only Python script (scripts/pr_report.py): an assignee-grouped escalation report computed entirely from live GitHub state (read-only; no writes; optional Discord/Slack mentions). Use for PR triage, the reviewer-attention report, stale-PR follow-up, or a scheduled report run.
Reproduces the shader-slang/slang production PR-review bot (anthropics/claude-code-action@v1 + .github/workflows/claude-pr-review.yml) locally. Same claude CLI, same user prompt, same system-prompt append, same model, same six .claude/agents/* subagents, same deepwiki MCP. The inner CLI produces final-review.md; the wrapping workflow optionally posts it back to GitHub as a COMMENT-state review (event=COMMENT only, never APPROVE/REQUEST_CHANGES) when the orchestrator authorizes (via webhook trigger). Mirrors production's pre-cleanup (minimize prior bot reviews, resolve threads) and post-safety-net (dismiss any non-COMMENT bot reviews). Helper scripts: cleanup.sh (pre), post-review.sh (post). Used by the /slang-pr-review workflow.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | slang-maintainer-tools |
| license | MIT |
| description | Bridge from /slang-maintain workflow steps to concrete slang-mcp tool calls. Read-only except an optional, user-confirmed post of the generated daily report to Slack. Task recipes live in sibling files. |
| provides | [] |
| argument-hint | [task: daily-report|release-notes|issue-prioritization|review-messages] [time-range: 24h|7d] [output: file|terminal|both] |
| allowed-tools | Read Write Edit Grep Glob AskUserQuestion mcp__slang-mcp__github_list_pull_requests mcp__slang-mcp__github_get_pull_request mcp__slang-mcp__github_get_pull_request_comments mcp__slang-mcp__github_get_pull_request_reviews mcp__slang-mcp__github_list_issues mcp__slang-mcp__github_search_issues mcp__slang-mcp__github_get_issue mcp__slang-mcp__github_get_discussions mcp__slang-mcp__gitlab_list_merge_requests mcp__slang-mcp__gitlab_list_issues mcp__slang-mcp__gitlab_get_file_contents mcp__slang-mcp__discord_read_messages mcp__slang-mcp__slack_get_channel_history mcp__slang-mcp__slack_get_user_profile mcp__slang-mcp__slack_post_message mcp__slang-mcp__slack_reply_to_thread |
Bridges /slang-maintain (WHAT) to concrete slang-mcp calls (HOW). Read-only, except daily-report may optionally post its finished report to Slack after explicit user confirmation.
| Task | Recipe |
|---|---|
daily-report | daily-report.md |
release-notes | release-notes.md |
issue-prioritization | issue-prioritization.md |
review-messages | review-messages.md |
Each recipe is self-contained: data sources, pagination rules, output template.
/slang-maintain step | Where to look |
|---|---|
| Collect | the task's recipe file — "Data Collection" section |
| Synthesize | the task's recipe file — categorization / dedup rules |
| Deliver | the task's recipe file — "Report Structure" or "Output Format" |
Cross-cutting pitfalls (rate limits, pagination, user-id resolution, squash-merge quirks): gotchas.md.
