Index of every page on this site: llms.txt
All skills
prefecthq avatar

/triage

@12a2db1
by Prefectprefecthq/fastmcp29k stars
2,631
Run it yourself

Find worthwhile FastMCP issues to work on in a backlog or release window, verify promising candidates, and present concrete picks with existing PR links.

Use this Skill: https://skilld.dev/gh/prefecthq/fastmcp/triage

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈40 tokens for metadata: the name and description. ≈831 when used: this file.

Description uses 2.0% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈162 characters, or 2.0%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Find worthwhile work

Read AGENTS.md and the contribution policy in the development guide. Honor the requested scope. For "since the last patch," identify the release timestamp, then look for open issues created or substantively updated afterward. Use a bounded inventory internally; report truncation if it affects coverage.

Start from an inventory, then link each candidate to the PRs that mention it:

gh release list --repo PrefectHQ/fastmcp --limit 1
gh issue list --repo PrefectHQ/fastmcp --state open --limit 30 \
  --json number,title,author,createdAt,updatedAt,labels,comments
gh pr list --repo PrefectHQ/fastmcp --state all --search "<issue-number> in:body" \
  --json number,title,state,author

Where search, GraphQL or --paginate are blocked (cloud sessions), page repo-scoped REST by hand (gh api "repos/PrefectHQ/fastmcp/pulls?state=all&per_page=100&page=N"), dump it once, and join locally.

Pick work with concrete user impact, a supported contract being violated, a tractable causal fix, and a change FastMCP wants to carry. Apply triage and merge decisions before ranking anything: labels and confident diagnoses are claims, and the behavior may already be fixed or decided. Mark each pick want / marginal / don't want. Do not rank solely by recency, comment count, or how small a proposed patch looks. Automated dashboard churn is not itself useful work.

For promising candidates:

  • Read the report, comments, maintainer decisions, and prior bot investigation.
  • Search related issues and PRs in all states, including gate-closed contributions. Closure alone says nothing about a fix's merit.
  • Trace the relevant code and git history. Distinguish fixed on main, released on the affected line, and merely proposed.
  • Verify the claimed contract and enough evidence to explain the cause. A proposed solution is a lead, not a diagnosis. Consider compatibility before calling a fix straightforward.

For a cleanup pass, the mechanical wins are open PRs whose linked issue is already closed, issues still open after a merged "fixes #N" (check for a revert first), and competing PRs for one issue.

Lead with the strongest pick as soon as evidence supports it: link, what breaks, why it matters, where the cause is, and the next action. Include a few alternatives when useful. Do not turn selection into an exhaustive audit or a full review of every linked PR. Save continuation notes only when needed.

When the user chooses implementation, use fix-issue. For an assignment decision on an external contribution, use review-issue. Triage alone does not authorize public mutations or implementation.

For a batch of maintainer decisions, save a self-contained proposal naming each target, exact action or patch, pinned revisions, evidence and executed checks, remaining questions, and dependencies between items. Include contributor ownership and the canonical issue or PR for proposed closures. Use upstream EGM in the maintainer session when independent batch review is requested. A Cloud node returns its assigned stage's declared output; the maintainer-facing session assembles the proposal and obtains sign-off.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    The triage skill helps identify and analyze development issues by processing external GitHub data. While this involves an inherent risk of indirect prompt injection from untrusted issue or pull request content, the skill restricts itself to information gathering and reporting, minimizing potential impact.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: MEDIUM · 1 issue

Signed by skilld at 12a2db1. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last week

README badge

README badge for prefecthq/fastmcp/triage