Agent Skills Platform turns documented work and supporting evidence into tested, installable skills for coding agents. Teams use it to review, publish, maintain, and safely reuse agent workflows, with the catalogue entries serving as skills and plugins built for that ecosystem.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add FrancyJGLisboa/agent-skill-creator --skill pr-blocker-summarizergit clone --depth 1 https://github.com/FrancyJGLisboa/agent-skill-creatorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/francyjglisboa/agent-skill-creator/pr-blocker-summarizer)<a href="https://agentmods.dev/skills/francyjglisboa/agent-skill-creator/pr-blocker-summarizer"><img src="https://agentmods.dev/badge/skills/francyjglisboa/agent-skill-creator/pr-blocker-summarizer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/francyjglisboa/agent-skill-creator/pr-blocker-summarizer"><img src="https://agentmods.dev/badge/skills/francyjglisboa/agent-skill-creator/pr-blocker-summarizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.00728 |
| Opus 5 | $0.00027 | $0.00364 |
| Sonnet 5 | $0.00011 | $0.00146 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
pr-blocker-summarizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Blocker Summarizer
Turn 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 count an agent can post to standup.
A bundled example skill — small but real, used to demonstrate the creator's validation, pipeline, and eval-rollout machinery.
Activation
Activates on "summarize open PRs", "what's blocking my PRs", "PR standup", "review backlog". Do not activate on general git/GitHub questions unrelated to triaging a set of PRs.
Input
A JSON array of PRs, each with title, state (open), checks
(passing/failing), review (approved/changes_requested/pending), and
age_days. Missing fields are treated conservatively (counted as not-blocked only
when clearly ready).
Run
python3 scripts/run_pipeline.py --input prs.json --output digest.json
Output JSON shape:
{
"total": 7,
"blocked": [{"title": "...", "reasons": ["failing checks"]}],
"ready": ["..."],
"summary": "7 open · 3 blocked · 2 ready to merge"
}
Gotchas
blocked+readydoes not equaltotal. A PR isreadyonly whenchecksis explicitlypassingandreviewis explicitlyapproved. A PR with no blockers but a missingchecksfield lands in neither list and vanishes from both counts. Never narrate the summary line as if the two numbers account for every PR — say "N blocked, M ready" and leave the remainder unclaimed.stateis read from the input but never filtered on. A closed or merged PR left in the export is counted intotaland classified like any open one. Filter the export before running if it may contain non-open PRs.review: pendingcounts as blocked ("awaiting review"). A PR opened five minutes ago is reported as a blocker. This is intentional for standup triage, but it inflates the blocked count on teams that open PRs early.- A non-numeric
age_dayssilently skips the stale check rather than erroring. An export with"age_days": "unknown"will never flag anything stale, and the digest gives no sign that the check did not run.
What ships with it
18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- discovery.json 2.0 KB
- evals/golden/case-1/expected.json 396 B
- evals/golden/case-1/input.json 339 B
- evals/golden/case-2/expected.json 152 B
- evals/golden/case-2/input.json 209 B
- evals/golden/case-3/expected.json 233 B
- evals/golden/case-3/input.json 106 B
- evals/pr-blocker-summarizer.eval.md 1.8 KB
- README.md 1.8 KB
- scripts/dependency_health.py 3.9 KB runs code
- scripts/evolve.py 8.2 KB runs code
- scripts/review_staleness.py 6.2 KB runs code
- scripts/run_evals.py 47 KB runs code
- scripts/run_pipeline.py 2.7 KB runs code
- scripts/schema_drift.py 7.3 KB runs code
- scripts/skill_document.py 9.8 KB runs code
- scripts/staleness_check.py 7.5 KB runs code
- scripts/success_ledger.py 16 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 73 lines · 54 tokens per session scan A 28f62d89f723
pr-blocker-summarizer is a skill published in the GitHub repository FrancyJGLisboa/agent-skill-creator (2,378 stars, last pushed 6d ago), licensed MIT. It adds 54 tokens to every session and 728 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sdd-apply
Skill "sdd-apply" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, purpose, what you receive and execution and persistence contract.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
sdd-verify
Skill "sdd-verify" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, activation contract, hard rules and decision gates.
sdd-spec
Write SDD delta specs with requirements and scenarios. Trigger: orchestrator launches spec work for a change.