CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fix-issue

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

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary instruction-only process skill: concise, densely actionable, and sequenced with real validation checkpoints and post-publication follow-through. Its only minor weakness is that concrete commands live in referenced documents rather than the body, which is appropriate delegation but leaves small execution gaps.

DimensionReasoningScore

Conciseness

The body is lean and imperative throughout — "Confirm supported behavior is broken, not merely surprising", "Do not infer compatibility from passing tests" — with no concept explanations Claude already knows and every sentence carrying instruction, matching the anchor for lean, token-efficient content.

5 / 5

Actionability

Guidance is mostly executable for an instruction-only skill: explicit reproduce-then-fix ordering, "smallest causal fix", the literal trailer format "Co-authored-by: Name <email>", and concrete PR conventions. It falls short of anchor 5 only because the actual commands (test invocation, dependency sync) are delegated to AGENTS.md and the python-tests skill rather than given inline.

4 / 5

Workflow Clarity

The three phases (establish contract, red/green/review, publish and follow through) are clearly sequenced with explicit validation checkpoints and an error-recovery loop: reproduce on unchanged code and confirm it fails for the right reason, run dependency sync/tests/static checks before committing, investigate and report failed checks rather than hiding them, and treat CI completion as distinct from review completion after publication.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files, organized into clear sections, and its cross-references (python-tests, review-pr, review-issue, contributing docs) are one level deep and clearly signaled with markdown links, satisfying the simple-skill criterion for full marks.

5 / 5

Total

19

/

20

Passed

Description

67%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, distinctive description that clearly states what the skill does across the whole fix lifecycle, but it entirely lacks "when to use" trigger guidance and omits natural terms like "issue" that users would most likely say. Adding an explicit "Use when..." clause with those synonyms would lift the two mid-range dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when asked to fix, resolve, or reproduce a selected FastMCP bug or GitHub issue, or to carry an assigned issue through to a pull request."

Include the natural synonyms users would say — "issue", "GitHub issue", "regression", "patch" — alongside "bug" and "fix".

Optionally signal the handoff contexts, such as "Use after review-issue when a fix (not just assignment) is the goal", to further reduce overlap with the sibling review-issue skill.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions spanning the full lifecycle — "reproduction", "scoped fix", "compatibility review", "validation", "monitored pull request" — with comprehensive coverage and no obvious gaps, matching the anchor-5 example's style of terse but complete action enumeration.

5 / 5

Completeness

The "what" is clear and explicit (reproduce, fix, review, validate, PR), but there is no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3; it is not 2 because the "what" is fully concrete rather than vague.

3 / 5

Trigger Term Quality

It contains some relevant keywords ("bug", "fix", "pull request") but misses the most natural user phrasings such as "issue", "GitHub issue", "regression", or "patch", fitting the anchor for relevant-but-incomplete keyword coverage rather than the broader coverage of anchor 4.

3 / 5

Distinctiveness Conflict Risk

"FastMCP bug" carves out a clear niche with distinct triggers, so the description is unlikely to fire for unrelated skills and has minimal conflict risk with generic fixing or review skills.

5 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 6 suspicious

Warning

Total

15

/

16

Passed

Repository

PrefectHQ/fastmcp

Path

.agents/skills/fix-issue/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.