소스 정보
- 저장소
- cajias/claude-skills
- 최근 소스 활동
- 2026년 7월 20일 10:57
- 감지된 SKILL.md 언어
- 영어
- 스타
- 0
- 포크
- 0
설치 방법
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
소스 파일 검토
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
메뉴
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.
SOC 직업 분류 기준
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/cajias/claude-skills --skill pr-monitor명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
Research (as an internal step) a GitHub/GitLab milestone's open issues in order to PRINT a copy-paste autonomous-loop prompt that drives the milestone to completion — behavior-driven (BDD) scenarios, adversarial gap-checking, a per-iteration Definition-of-Done gate (build + all tests + zero lint + /code-review + /security-audit + /ponytail:ponytail findings all cleared), specialized-agent selection with model tier scaled to task complexity, and a root-cause→harness-hardening loop. Use this whenever the user says "generate a goal prompt", "goal-driven prompt", "milestone loop prompt", "prompt to finish/complete the milestone", "clear-and-paste prompt for milestone N", "make me a prompt to drive /autoresearch", or otherwise wants a ready-to-paste block that autonomously completes a milestone's remaining issues. The deliverable is the prompt itself, not a summary. NOT for actually executing the work (this only GENERATES and PRINTS the prompt — the loop does the work), NOT for merely summarizing or listing a mile
Eight APM-marketplace-authoring gotchas discovered during real migrations from hand-authored .claude-plugin/marketplace.json to APM-managed and from CC-native plugin authoring. Use when: (1) running APM's packaging step (with or without `--dry-run`) or its marketplace-check command in a repo with an `apm.yml`; (2) wiring CI for an APM marketplace; (3) the CI staleness check (repack, then `git diff --quiet`) fails despite a clean local; (4) prettier reformats `marketplace.json` after APM's packer writes it; (5) APM exit code 1 on local-path-only marketplaces; (6) confused by `packages:` in apm.yml vs `plugins:` in marketplace.json; (7) commitlint rejects a commit with `footer-leading-blank` despite no apparent footer; (8) `apm compile -t claude` exits 0 with zero output and no compiled plugin appears; (9) husky+lint-staged pre-commit blocks the FIRST marketplace commit with markdownlint `MD040/fenced-code-language` errors on a SKILL.md file copied verbatim from `~/.claude/skills/`. The gotchas form a chain — f
Canonical authoring layout for an APM (microsoft/apm) package, plus the decision matrix for whether you need a `marketplace:` block. Use when: (1) you've run `apm init` and are unsure where SKILL.md / agent .md / command .md files belong (answer: under `.apm/`, NOT at repo root); (2) you've authored CC-native files at `commands/agents/skills/` at repo root and wonder if that's "right" (it works as fallback layout #3 "Claude plugin", but it's not the canonical authoring path); (3) you're trying to choose between the three layouts APM recognizes (one-skill repo, multi-primitive `.apm/`, Claude plugin); (4) `apm targets` fails with "No such command" in CLI 0.12.1 (subcommand doesn't exist); (5) `apm validate` fails with "No such command" in CLI 0.12.1 (use APM's packaging command in dry-run mode instead); (6) wondering whether `apm compile -t claude` will generate output for a hand-authored CC-native plugin (it won't; it's a no-op for layout #3); (7) wondering if you need a `marketplace:` block in apm.yml (you d
| name | pr-monitor |
| description | Monitor GitHub pull requests and automatically resume when new commits are detected |
| version | 1.0.0 |
Set up automated monitoring of GitHub pull requests that triggers Claude Code to auto-resume and review changes when new commits are detected.
Before starting, ensure:
gh) is installed and authenticatedUse this skill when:
Get PR information:
If user provides PR URL, extract repo and PR number:
# Example URL: https://github.com/owner/repo/pull/123
# Extract: owner/repo and PR number 123
If user provides repo and PR number, verify PR exists:
gh pr view PR_NUMBER --repo OWNER/REPO --json number,title,state,headRefOid
If in a git repository, list open PRs:
gh pr list --json number,title,headRefOid --limit 20
Create state file for the Stop hook to monitor:
Get repository path:
# If already in repo
REPO_PATH=$(pwd)
# If remote repo, clone first
gh repo clone OWNER/REPO
cd REPO
REPO_PATH=$(pwd)
Get current commit SHA:
CURRENT_SHA=$(gh pr view PR_NUMBER --json headRefOid --jq '.headRefOid')
Create monitoring state file:
# Format: ~/.claude/pr-monitor/claude_monitor_pr_<repo-name>_<pr-number>
# Extract repo name from path
REPO_NAME=$(basename "$REPO_PATH")
STATE_DIR="$HOME/.claude/pr-monitor"
mkdir -p -m 700 "$STATE_DIR"
STATE_FILE="$STATE_DIR/claude_monitor_pr_${REPO_NAME}_${PR_NUMBER}"
# Write state file with 3 lines: repo_path, pr_number, last_sha
cat > "$STATE_FILE" <<EOF
$REPO_PATH
$PR_NUMBER
$CURRENT_SHA
EOF
Confirm monitoring active:
echo "✓ Monitoring enabled for PR #$PR_NUMBER"
echo "✓ State file: $STATE_FILE"
echo "✓ Current commit: ${CURRENT_SHA:0:8}"
cat "$STATE_FILE"
If requested, perform initial review of current PR state:
Get PR details:
gh pr view PR_NUMBER --json title,body,commits,files
View recent changes:
gh pr diff PR_NUMBER
Provide initial feedback:
The Stop hook will now automatically monitor the PR:
When Claude Code would normally stop:
You can continue working on other tasks - monitoring happens automatically in the background.
When new commits are detected, Claude will automatically:
Resume with notification:
Review new changes:
# Get updated PR information
gh pr view PR_NUMBER --json commits,headRefOid,files
# Get diff of new changes
gh pr diff PR_NUMBER
# Compare with previous state if needed
git diff OLD_SHA NEW_SHA
Provide feedback:
# Comment on PR
gh pr comment PR_NUMBER --body "FEEDBACK_TEXT"
# Or request changes via review
gh pr review PR_NUMBER --comment --body "REVIEW_TEXT"
Update monitoring state:
When monitoring is no longer needed:
Remove state file:
rm ~/.claude/pr-monitor/claude_monitor_pr_${REPO_NAME}_${PR_NUMBER}
Confirm stopped:
echo "✓ Monitoring stopped for PR #$PR_NUMBER"
Monitoring will also auto-stop if:
Common issues and solutions:
Hook not triggering:
ls -la ~/.claude/pr-monitor/claude_monitor_pr_*echo '{"stop_hook_active": false}' | bash /path/to/Stop.shPR not accessible:
gh is authenticated: gh auth statusgh pr view PR_NUMBER --repo OWNER/REPOMultiple PRs monitored:
ls -la ~/.claude/pr-monitor/claude_monitor_pr_*cat ~/.claude/pr-monitor/claude_monitor_pr_REPO_PRrm ~/.claude/pr-monitor/claude_monitor_pr_REPO_PRPolling-based, not real-time:
Requires Claude Code running:
Persistent state files:
~/.claude/pr-monitor across rebootsGitHub API rate limits:
Monitor selectively:
Provide context in feedback:
Use with other tools:
# 1. User asks to monitor PR #2 in claude-skills repo
cd /path/to/claude-skills
# 2. Get current state
gh pr view 2 --json headRefOid,title,commits
# 3. Create monitoring state
REPO_PATH=$(pwd)
PR_NUMBER=2
CURRENT_SHA=$(gh pr view 2 --json headRefOid --jq '.headRefOid')
REPO_NAME=$(basename "$REPO_PATH")
cat > ~/.claude/pr-monitor/claude_monitor_pr_${REPO_NAME}_${PR_NUMBER} <<EOF
$REPO_PATH
$PR_NUMBER
$CURRENT_SHA
EOF
# 4. Confirm
echo "✓ Now monitoring PR #2 in claude-skills"
echo "✓ Current commit: ${CURRENT_SHA:0:8}"
# 5. Wait for updates (automatic via Stop hook)
# When Copilot pushes new commits, Claude auto-resumes and reviews
After enabling monitoring, verify:
State file created:
ls -la ~/.claude/pr-monitor/claude_monitor_pr_*
State file format correct:
cat ~/.claude/pr-monitor/claude_monitor_pr_REPO_PR
# Should show 3 lines: repo_path, pr_number, sha
PR accessible:
gh pr view PR_NUMBER --repo OWNER/REPO