CtrlK
BlogDocsLog inGet started
Tessl Logo

fix-contribution

Fix common issues in geographic data contributions to the CSC database. Use this skill whenever you need to fix, correct, repair, patch, or resolve issues in a data contribution or PR. Trigger on: "@copilot fix this", "auto-fix" label on issues, "can you fix", "please correct", "help me fix", "what's wrong with my PR", removing auto-managed fields, correcting country codes, fixing mismatched foreign keys, or formatting JSON. Also use when a PR has validation errors and you need to commit fixes directly. Read common-fixes.md in this directory for fix patterns and examples.

67

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/fix-contribution/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

A clear, actionable skill body with good sequencing and concrete file/field references, weakened by a missing re-validation feedback loop before commit and a referenced common-fixes.md file that is not present in the bundle.

Suggestions

Add a re-validation step between applying fixes and committing (e.g., re-run the PR Validator / re-check the contribution against the schema) so the workflow has an explicit validate→fix→retry loop for this batch operation.

Either create common-fixes.md with the promised before/after fix patterns or remove the references to it from both the frontmatter and body so navigation is not broken.

Collapse the "Common Fix Patterns" section into Step 2 (or replace Step 2's prose with the numbered patterns) to remove the duplication and tighten the token budget.

DimensionReasoningScore

Conciseness

The body is well organized and free of padding about concepts Claude already knows, though the "Common Fix Patterns" section re-packages steps already covered in Step 2 and "When to Use" re-states frontmatter triggers, creating minor redundancy.

4 / 5

Actionability

Concrete instructional guidance with specific files (countries.json, states.json), exact field names, and commit-message templates; falls just short of fully executable because no actual commands (e.g., a jq/shell snippet to look up a record) are shown.

4 / 5

Workflow Clarity

Four steps are clearly sequenced (Identify → Apply → Commit → Explain), but this batch/destructive workflow commits fixes directly with no re-validation checkpoint before committing, so the missing feedback loop caps the score at 3 per the rubric.

3 / 5

Progressive Disclosure

Section structure is good and the lone reference (common-fixes.md) is one level deep and clearly signaled, but no bundle files exist so the referenced file is missing, breaking navigation and preventing a higher score.

3 / 5

Total

14

/

20

Passed

Description

95%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 strong description that concretely states capabilities, gives rich natural trigger phrases, and clearly separates what from when. The only flaw is second-person voice ("you need to"), which costs one specificity point per the rubric guideline.

DimensionReasoningScore

Specificity

Names multiple concrete actions ("removing auto-managed fields, correcting country codes, fixing mismatched foreign keys, or formatting JSON", "commit fixes directly") for comprehensive coverage, but the second-person phrasing ("Use this skill whenever you need to fix") triggers the voice penalty, reducing the score by one.

4 / 5

Completeness

Explicitly answers both what ("Fix common issues in geographic data contributions to the CSC database") and when ("Use this skill whenever...", "Trigger on:", "Also use when a PR has validation errors") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including synonyms and exact user phrases: "@copilot fix this", "can you fix", "please correct", "help me fix", "what's wrong with my PR", plus the "auto-fix" label.

5 / 5

Distinctiveness Conflict Risk

Clear niche (geographic data contributions to the CSC database, PR validation-error fixes) with distinct triggers and minimal overlap risk with unrelated skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
dr5hn/countries-states-cities-database
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.