FrancyJGLisboa/agent-skills-platform / references/examples/pr-blocker-summarizer
pr-blocker-summarizer
UnverifiedSummarizes open pull requests into a blockers-first standup digest. Activates when the user asks to summarize open PRs, find blocked pull requests, generate a PR standup, or triage review backlog from a PR export.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 1.9 KB |
| SKILL.md | skill md | 2.7 KB |
| VERIFICATION.md | markdown | 849 B |
| contracts/data_contract_pull_request_reviews/.contract_id | other | 20 B |
| contracts/data_contract_pull_request_reviews/code/contract_health.py | script | 402 B |
| discovery.json | config | 2.2 KB |
| evals/golden/case-1/expected.json | config | 396 B |
| evals/golden/case-1/input.json | config | 339 B |
| evals/golden/case-2/expected.json | config | 152 B |
| evals/golden/case-2/input.json | config | 209 B |
| evals/golden/case-3/expected.json | config | 233 B |
| evals/golden/case-3/input.json | config | 106 B |
| evals/pr-blocker-summarizer.eval.md | markdown | 1.8 KB |
| scripts/dependency_health.py | script | 3.9 KB |
| scripts/evolve.pyexecutable | script | 10.2 KB |
| scripts/review_staleness.py | script | 6.2 KB |
| scripts/run_evals.pyexecutable | script | 49.4 KB |
| scripts/run_pipeline.pyexecutable | script | 2.7 KB |
| scripts/schema_drift.py | script | 7.3 KB |
| scripts/skill_document.py | script | 9.8 KB |
| scripts/staleness_check.py | script | 7.5 KB |
| scripts/success_ledger.py | script | 16.5 KB |
README.md
View on GitHub# pr-blocker-summarizer
A bundled example skill: turns a JSON export of open pull requests into a
blockers-first digest — which PRs are blocked (failing checks, requested
changes, or stale), which are ready to merge, and a one-line standup count.
It is small but real, and demonstrates the creator's full machinery end to
end: SKILL.md activation, a `run_pipeline.py` orchestrator, and a bundled
eval spec with golden cases.
## Requirements
Python 3.10+ only — the pipeline uses the standard library (no third-party
dependencies, no requirements.txt needed).
## Run it
```bash
python3 scripts/run_pipeline.py \
--input evals/golden/case-1/input.json \
--output /tmp/pr-digest.json
cat /tmp/pr-digest.json
```
Input: a JSON array of PRs, each with `title`, `state`, `checks`
(`passing`/`failing`), `review` (`approved`/`changes_requested`/`pending`),
and `age_days`. Missing fields are treated conservatively.
## Run the evals
```bash
python3 scripts/run_evals.py . --validate # check the eval spec is well-formed
python3 scripts/run_evals.py . --rollout # execute the skill on golden inputs
python3 scripts/run_evals.py . --rollout --promote # capture first baselines
python3 scripts/success_ledger.py summary # inspect local durable-use metrics
```
The eval spec lives in `evals/pr-blocker-summarizer.eval.md` with three
golden cases under `evals/golden/`.
## Layout
```
pr-blocker-summarizer/
├── SKILL.md # activation + usage contract
├── scripts/run_pipeline.py # PR JSON → blocked/ready triage → digest JSON
├── scripts/run_evals.py # eval runner (validate / rollout / promote)
├── scripts/success_ledger.py # private local lifecycle metrics
└── evals/ # eval spec + golden cases
```
## Verification
[VERIFICATION.md](VERIFICATION.md) records the latest generation-time gate and eval evidence.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |