CtrlK
BlogDocsLog inGet started
Tessl Logo

github-fix-issue

Fix GitHub issues end-to-end — analysis, branch creation, implementation, testing, and PR submission. Use whenever the user mentions fixing a GitHub issue, says "fix issue

70

Quality

86%

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

72%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.

The body is well-structured and actionable with concrete gh/git commands, but carries minor motivational padding and leaves key validation checkpoints (before commit, before push) implicit rather than explicit. Progressive disclosure is excellent for a skill of this size.

Suggestions

Trim justifying sentences like 'Thorough testing prevents the fix from introducing new problems' and 'small commits are easier to review and revert' — keep only the imperative instruction.

Add explicit validation checkpoints before risky steps, e.g., 'Run the test suite; only commit when all tests pass' and 'Verify the branch builds before pushing'.

Replace abstract test guidance ('Run the full test suite') with the concrete command (e.g., 'npm test' or 'pytest') or instruct Claude to detect and run the project's test command.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands, but includes a few motivational sentences ('Thorough testing prevents the fix from introducing new problems', 'small commits are easier to review and revert') that explain why rather than instruct; matches the score-4 anchor of minor over-explanation that could be trimmed.

4 / 5

Actionability

Provides concrete, executable gh/git commands (e.g., 'gh issue view <number>', 'gh pr create --title "..." --body "Fixes #123"') with a copy-paste reference block, but test guidance remains abstract ('Run the full test suite') without the specific command, matching the score-4 anchor of mostly executable with minor gaps.

4 / 5

Workflow Clarity

Six clearly numbered steps give a clear sequence with one explicit checkpoint ('Fix any failing tests before moving on'), but other validation checkpoints (before commit, before push/PR) are only implicit; matches the score-3 anchor of steps present with implicit or missing checkpoints.

3 / 5

Progressive Disclosure

A focused single-purpose skill under 50 lines with clean section organization (numbered Workflow steps plus a gh Command Reference block) and no need for external bundle files, qualifying for the score-5 simple-skill exception.

5 / 5

Total

16

/

20

Passed

Description

100%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.

The description is exemplary: it concisely states the full scope of the skill, lists concrete capabilities, and provides rich natural-language triggers including a non-English synonym. It clearly answers both 'what' and 'when' with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists five distinct concrete capabilities — 'analysis, branch creation, implementation, testing, and PR submission' — giving comprehensive coverage of the fix lifecycle, matching the score-5 anchor.

5 / 5

Completeness

Explicitly answers both 'what' (end-to-end fix with listed phases) and 'when' ('Use whenever the user mentions fixing a GitHub issue...') with concrete trigger phrases, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Includes natural phrases users would say — 'fix issue #123', 'work on this issue', '修复 issue', and references to issue numbers or URLs — covering synonyms and variants, matching the score-5 anchor.

5 / 5

Distinctiveness Conflict Risk

GitHub issue fixing is a clear, narrow niche with distinct triggers (issue numbers, URLs, 'fix issue #123') and minimal overlap with other skills, matching the score-5 anchor.

5 / 5

Total

20

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
feiskyer/claude-code-settings
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.