Skills

pr-blocker-summarizer

pr-blocker-summarizer is a skill in FrancyJGLisboa/agent-skills-platform, last changed 3 Sept 2026. It can run shell commands, reach the network, name web addresses and bundle scripts — read the findings before installing. Our pattern check flagged nothing at commit 0c6900a on 27 Oct 2026.

Pattern check: nothing flagged · commit 0c6900a · 27 Oct 2026

Install
From the author
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.
Licence
MIT
Repo stars
2.4k
Folder last changed
3 Sept 2026 (opens in a new tab)
Publisher
FrancyJGLisboa
Files
22 files
Checked
0c6900a (opens in a new tab) · 27 Oct 2026

Install

Each tab says whether it installs commit 0c6900a, the one we checked, or the latest version.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.

Pinned to commit 0c6900a, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/FrancyJGLisboa/agent-skills-platform.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 0c6900a0597622791d1daaafc1c19b2fead0e8d4 &&
  git -C "$tmp" sparse-checkout set -- references/examples/pr-blocker-summarizer &&
  git -C "$tmp" checkout -q 0c6900a0597622791d1daaafc1c19b2fead0e8d4 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/pr-blocker-summarizer &&
  cp -R "$tmp"/references/examples/pr-blocker-summarizer/. .claude/skills/pr-blocker-summarizer/ &&
  rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs (opens in a new tab)

What it can touch

From the files and frontmatter at commit 0c6900a. This is how much a skill can do, not whether it is risky.

What it can touch: Shell, network or credentials

  • Runs shell commands

    Its instructions or files give the agent commands to run on your computer.

  • Reaches the network

    It sends or fetches data over the internet, for example with curl, an HTTP library or a package install.

  • Names web addresses

    It mentions outside web addresses the agent may visit. We list them but don't follow them.

  • Bundles scripts

    The folder holds code files the agent may run.

    contracts/data_contract_pull_request_reviews/code/contract_health.py · scripts/dependency_health.py · scripts/evolve.py and 6 more

Pattern check

Pattern check: nothing flagged · commit 0c6900a · 27 Oct 2026

We checked every text file in this skill, at commit 0c6900a on 27 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Outside links we did not follow

  • https://api.anthropic.com/v1/messages

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses with warnings

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • Warning

      metadata values should be text; review_interval_days (a number) is not. The spec's validator turns them into text; other readers may not. O4

      Fix: Quote each value, for example version: "1.0".

    • Note

      Anthropic's packaging script leaves these out: evals/. F8

      Fix: Delete them, or list them in .gitignore.

    • Note

      Reference files that SKILL.md doesn't link: VERIFICATION.md and evals/pr-blocker-summarizer.eval.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

  • Claude CodePasses

    Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

    • Note

      Anthropic's packaging script leaves these out: evals/. F8

      Fix: Delete them, or list them in .gitignore.

    • Note

      Reference files that SKILL.md doesn't link: VERIFICATION.md and evals/pr-blocker-summarizer.eval.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

  • Claude apps & API uploadPasses

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Note

      Anthropic's packaging script leaves these out: evals/. F8

      Fix: Delete them, or list them in .gitignore.

    • Note

      The description is 213 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

      Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

    • Note

      metadata values should be text; review_interval_days (a number) is not. The spec defines metadata as text to text. O4

      Fix: Quote each value, for example version: "1.0".

    • Note

      Reference files that SKILL.md doesn't link: VERIFICATION.md and evals/pr-blocker-summarizer.eval.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

  • OpenAI (Codex & API)Passes with warnings

    Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.

    • Warning

      metadata values should be text; review_interval_days (a number) is not. OpenAI's upload follows the spec's text-to-text rule. O4

      Fix: Quote each value, for example version: "1.0".

    • Note

      Anthropic's packaging script leaves these out: evals/. F8

      Fix: Delete them, or list them in .gitignore.

  • VS Code & CopilotPasses

    VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.

    • Note

      Anthropic's packaging script leaves these out: evals/. F8

      Fix: Delete them, or list them in .gitignore.

SKILL.md

Files

22 files

PathSize
README.md (opens in a new tab)1.9 KB
SKILL.md (opens in a new tab)2.7 KB
VERIFICATION.md (opens in a new tab)849 B
contracts/data_contract_pull_request_reviews/.contract_id (opens in a new tab)20 B
contracts/data_contract_pull_request_reviews/code/contract_health.py (opens in a new tab)402 B
discovery.json (opens in a new tab)2.2 KB
evals/golden/case-1/expected.json (opens in a new tab)396 B
evals/golden/case-1/input.json (opens in a new tab)339 B
evals/golden/case-2/expected.json (opens in a new tab)152 B
evals/golden/case-2/input.json (opens in a new tab)209 B
evals/golden/case-3/expected.json (opens in a new tab)233 B
evals/golden/case-3/input.json (opens in a new tab)106 B
evals/pr-blocker-summarizer.eval.md (opens in a new tab)1.8 KB
scripts/dependency_health.py (opens in a new tab)3.9 KB
scripts/evolve.py (opens in a new tab)10.2 KB
scripts/review_staleness.py (opens in a new tab)6.2 KB
scripts/run_evals.py (opens in a new tab)49.4 KB
scripts/run_pipeline.py (opens in a new tab)2.7 KB
scripts/schema_drift.py (opens in a new tab)7.3 KB
scripts/skill_document.py (opens in a new tab)9.8 KB
Show 2 more
PathSize
scripts/staleness_check.py (opens in a new tab)7.5 KB
scripts/success_ledger.py (opens in a new tab)16.5 KB

More from FrancyJGLisboa/agent-skills-platform

  • github-release-briefing-skill

    FrancyJGLisboa/agent-skills-platform

    Create a source-linked briefing for the latest published GitHub release of a public repository. Use for engineering teams tracking a dependency release; do not use it to publish releases or change repositories.

    • Runs shell commands
    • Reaches the network
    • +2 more
    Pattern check: Nothing flagged

    MIT · 2.4k repo stars · Updated 15 Sept 2026

  • live-weather-briefing-skill

    FrancyJGLisboa/agent-skills-platform

    Create a current, source-linked weather briefing for a named city using the Open-Meteo geocoding and forecast APIs. Activate for requests such as "what is the weather in Sao Paulo?", "prepare a current weather briefing for Tokyo", or "get today's live conditions for New York". Do not use for travel booking, weather alerts, historical climatology, or safety-critical decisions.

    • Runs shell commands
    • Reaches the network
    • +2 more
    Pattern check: Nothing flagged

    MIT · 2.4k repo stars · Updated 3 Sept 2026

  • stock-analyzer

    FrancyJGLisboa/agent-skills-platform

    Provides comprehensive technical analysis for stocks and ETFs using RSI, MACD, Bollinger Bands, and other indicators. Activates when user requests stock analysis, technical indicators, trading signals, or market data for specific ticker symbols.

    • Changes agent settings
    • Runs shell commands
    • +3 more
    Pattern check: Nothing flagged

    MIT · 2.4k repo stars · Updated 15 Sept 2026

  • weekly-crm-report

    FrancyJGLisboa/agent-skills-platform

    Cleans a weekly CRM export and produces a regional sales summary. Activates when the user asks to clean a CRM export, deduplicate sales rows, calculate regional totals, or generate a weekly sales report from a CSV.

    • Runs shell commands
    • Reaches the network
    • +2 more
    Pattern check: Nothing flagged

    MIT · 2.4k repo stars · Updated 3 Sept 2026