Fix a selected issue
SkillMonitoring & opsThis skill lets an agent carry a selected FastMCP bug from reproduction through a scoped fix, compatibility review, validation, and a monitored pull request. It is a skill for people who want an agent to take a reported bug and work it end to end instead of stopping at a diagnosis. The agent confirms the failure, makes the smallest causal fix, tests nearby paths, and watches the pull request until it is resolved.
Use Fix a selected issue in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Fix a selected issue and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Fix a selected issue skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
No other account needed.
Have a FastMCP repository checked out with the reported bug selected.
What your AI can do with it
- Reproduce a reported FastMCP bug and confirm the expected behavior is broken
- Make the smallest causal fix for the failure
- Test nearby affected paths after the change
- Run dependency sync, full tests, and static checks
- Self-review the change and open or update a pull request
- Monitor CI and review on the pull request until resolved
Getting started
- Have a FastMCP repository checked out with the reported bug selected.
- Make sure the agent can run the project's tests, dependency sync, and static checks.
- Give the agent the bug report and the expected behavior.
- Let the agent reproduce the failure before it changes any code.
- Review the pull request the agent opens or updates and its monitored CI results.
What this skill tells your AI
The instructions your AI receives, as published by prefecthq/fastmcp in .agents/skills/fix-issue/SKILL.md and read by ahel’s review.
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, full tests, and static checks before committing. 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.
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.
Signals
- GitHub stars
- 28k
- Forks
- 2k
- Last commit
- Oct 2026
Questions
- What does the skill do?
- It guides an agent through fixing a selected FastMCP bug: reproducing the failure, making the smallest causal fix, testing nearby paths, running checks, and opening a monitored pull request.
- Does it open a pull request?
- Yes. After validation and self-review, it opens or updates a pull request following repo conventions and monitors its CI and review until resolved.
- What checks does it run?
- It runs dependency sync, full tests, and static checks, and tests nearby affected paths after the fix.
Advanced
- Item type
- skill
- Key
fix-issue-prefecthq- Source
- github.com/prefecthq/fastmcp
Related picks
Skill · wshobson
The pick for Pythonpython-pro
Skill · jeffallan
The pick for Pythoninternal-comms
Skill · anthropics
More in Monitoring & opsagent-eval
Skill · affaan-m
More in Monitoring & opsdashboard-builder
Skill · affaan-m
More in Monitoring & opsbabysit
Skill · thedotmack
More in Monitoring & ops