Skip to content

FrancyJGLisboa/agent-skills-platform / references/examples/pr-blocker-summarizer

pr-blocker-summarizer

Unverified

Summarizes 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.

# 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.
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: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
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: 115kUpdated Claude CodeCodexVerifiedInstall
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: 115kUpdated Claude CodeCodexVerifiedInstall