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

/fix-issue

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

Carry a selected FastMCP bug from reproduction through a scoped fix, compatibility review, validation, and a monitored pull request.

Use this Skill: https://skilld.dev/gh/prefecthq/fastmcp/fix-issue

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈36 tokens for metadata: the name and description. ≈807 when used: this file.

Description uses 1.8% 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 ≈144 characters, or 1.8%.

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.

Fix a selected issue

Read AGENTS.md and the contribution policy in the development guide. Read the issue's full discussion, relevant history, and associated PRs in all states. Evaluate existing contributions before writing a competing fix; use review-issue when assignment is the next decision. Preserve contributor authorship when carrying existing work forward.

Establish the contract

Trace the public request to the failing operation. Confirm supported behavior is broken, not merely surprising. State the scope and compatibility boundary before implementation: which inputs must change, which adjacent behavior must remain, and any migration needed. If the intended contract is unresolved, bring that precise question to the maintainer.

Red, green, review

Use python-tests. Reproduce the failure on unchanged code, confirm it fails for the right reason, then make the smallest causal fix. Test explicit overrides and neighboring supported paths that share the changed branch. Avoid expanding the fix to unrelated standards gaps.

Self-review the full change with review-pr, including docs and dependency bounds. Separate necessary compatibility changes from accidental regressions and say whether a breaking change remains. Do not infer compatibility from passing tests.

Run the repository's required dependency sync, the relevant tests, and applicable static checks before committing, per AGENTS.md. Honor branch and attribution conventions. If a required check fails, investigate and report evidence rather than hiding the failure.

Publish and follow through

Within existing authorization, update the existing PR or open a focused one, using draft status when appropriate. Follow repository PR-body conventions and the user's pr-body skill when available. Describe the actual user-visible change and any migration, not the development diary.

For a maintainer implementation of a community issue, apply Contributor credit before committing and publishing. Read the issue author's GitHub profile to establish their account identity; prefer the GitHub-provided noreply address, and ask if identity is unclear. Add their Co-authored-by: Name <email> trailer to the implementation commit and at the end of the PR description, alongside existing contributor attribution. Reporting the problem is enough; do not require code or root-cause analysis. Honor opt-outs and do not credit bot accounts as human issue contributors.

Maintainers are generally exempt from supplemental credit checks. For maintainer reports and routine backports, preserve existing community attribution and proceed; do not add a maintainer merely because they opened the original PR or ask for guidance on that basis. A backport does not need a fresh credit audit.

Start review-pr monitoring after publication. CI completion and review completion are distinct. Resolve real findings and report material compatibility decisions; a green check does not settle them. Do not merge or mark ready without authorization.

Source: SKILL.md on GitHub

No rule matched.

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

    This skill defines a standard development workflow for agents to handle bug reproduction, fixing, and pull request management. The instructions involve typical repository maintenance and testing tasks without any detected malicious patterns or security risks.

  • 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/fix-issue