notque/vexjoy-agent / skills/process/pr-workflow
pr-workflow
FlaggedPull request lifecycle: commit, codex review, sync, review, fix, status, cleanup, and PR mining. Use when user wants to commit changes, get a second-opinion code review from Codex, push changes, create a PR, check PR status, fix review comments, clean up branches after merge, or mine tribal knowledge from PR reviews. Use for "commit my changes", "codex review", "push my changes", "create a PR", "pr status", "fix PR comments", "clean up branches", "mine PRs", or "address feedback".
references/mining-commands.md
View on GitHub# PR Mining Command Reference
## Basic Mining Patterns
### Mine Last 100 PRs from Single Repo
```bash
fish -c "set -x GITHUB_TOKEN (security find-internet-password -s github.com -w 2>/dev/null) && \
cd ~/.claude/skills/pr-workflow && \
./venv/bin/python3 scripts/miner.py \
your-org/go-libs \
mined_data/go_bits_all_2025-11-29.json \
--limit 100 --summary" &
```
### Mine Specific Reviewer
```bash
fish -c "set -x GITHUB_TOKEN (security find-internet-password -s github.com -w 2>/dev/null) && \
cd ~/.claude/skills/pr-workflow && \
./venv/bin/python3 scripts/miner.py \
your-org/go-libs \
mined_data/senior-reviewer_go_bits_2025-11-29.json \
--reviewer senior-reviewer --all-comments --limit 100 --summary" &
```
### Mine Multiple Repos
```bash
fish -c "set -x GITHUB_TOKEN (security find-internet-password -s github.com -w 2>/dev/null) && \
cd ~/.claude/skills/pr-workflow && \
./venv/bin/python3 scripts/miner.py \
your-org/go-libs,your-org/service-a,your-org/service-b \
mined_data/go_repos_all_2025-11-29.json \
--limit 100 --summary" &
```
## Advanced Mining Patterns
### Date Range Mining
```bash
fish -c "set -x GITHUB_TOKEN (security find-internet-password -s github.com -w 2>/dev/null) && \
cd ~/.claude/skills/pr-workflow && \
./venv/bin/python3 scripts/miner.py \
your-org/service-a \
mined_data/api_server_2025_q4.json \
--since 2025-10-01 --until 2025-12-31 --limit 200 --summary" &
```
### Comprehensive Team Analysis (All Reviewers, Multiple Repos)
```bash
fish -c "set -x GITHUB_TOKEN (security find-internet-password -s github.com -w 2>/dev/null) && \
cd ~/.claude/skills/pr-workflow && \
./venv/bin/python3 scripts/miner.py \
your-org/go-libs,your-org/service-a,your-org/service-b,your-org/service-c \
mined_data/go_team_2025-11-29.json \
--limit 150 --summary" &
```
### Senior Reviewer Deep Dive (All Comments, Multiple Repos)
```bash
fish -c "set -x GITHUB_TOKEN (security find-internet-password -s github.com -w 2>/dev/null) && \
cd ~/.claude/skills/pr-workflow && \
./venv/bin/python3 scripts/miner.py \
your-org/go-libs,your-org/service-a \
mined_data/senior-reviewer_patterns_2025-11-29.json \
--reviewer senior-reviewer --all-comments --limit 200 --summary" &
```
## Command Flag Reference
### Required Arguments
- `repos`: Repository list (comma-separated, format: `owner/repo`)
- `output`: Output JSON file path (relative to pr-miner directory)
### Optional Flags
| Flag | Description | Default |
|------|-------------|---------|
| `--reviewer {username}` | Filter to specific reviewer's comments | All reviewers |
| `--all-comments` | Include all comment types (not just imperative) | Imperative only |
| `--limit {number}` | Maximum PRs to analyze | 100 |
| `--since {YYYY-MM-DD}` | Start date for PR range | No limit |
| `--until {YYYY-MM-DD}` | End date for PR range | No limit |
| `--summary` | Print mining summary statistics | Off |
## Output Naming Conventions
### Reviewer-Specific Mining
Format: `{reviewer}_{repos}_{date}.json`
Examples:
- `senior-reviewer_go_libs_2025-11-29.json`
- `senior-reviewer_go_all_2025-11-29.json`
### Team/All Reviewers Mining
Format: `{repos}_all_{date}.json`
Examples:
- `go_libs_all_2025-11-29.json`
- `api_server_metrics_service_all_2025-11-29.json`
### Multiple Repos Naming
Use underscores to separate repo names:
- `go_libs_api_server` for go-libs + api-server
- `go_libs_api_server_metrics_service` for three repos
### Date Ranges
Use descriptive date names for periodic analysis:
- `go_libs_2025_q1.json` for Q1 2025
- `api_server_2025_q4.json` for Q4 2025
## Directory Structure
All mining operations use fixed paths under `~/.claude/skills/pr-workflow/`:
```
~/.claude/skills/pr-workflow/
scripts/miner.py # Mining tool
venv/ # Python virtual environment
mined_data/ # Mining output (JSON)
rules/ # Generated coding rules (markdown)
```
## Concurrent Mining Management
**Strategy**: Run jobs sequentially to avoid GitHub API rate limits (5000 requests/hour shared).
**Pattern**:
1. Start job 1, wait for completion
2. Start job 2, wait for completion
3. Generate combined rules from all results
**Never**: Run 3+ mining jobs in parallel (causes rate limit exhaustion).
## Typical Mining Session Workflow
1. Validate prerequisites (token, miner script, reviewer username)
2. Start mining job in background
3. Track progress with BashOutput (every 30-60 seconds)
4. When complete, verify output file has valid interactions
5. Generate categorized coding rules from mined data
6. Save rules to rules/ directory
7. Report results to user
Total time: 2-5 minutes for 100 PRs (depending on repo size and API response time).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |