CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

repo-state-sync

Scan codebase and design docs to update the Session Onboarding section in copilot-instructions.md. Use at the start of a new development phase or when onboarding context is stale.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

Highly actionable content with a complete output specification and a sound, verified workflow. The main weakness is redundancy: the scan process is described twice and the invocation/usage guidance repeats what the frontmatter already states.

Suggestions

Merge 'Execution Steps' with the 'Scan Process' sections so each scan location is described once, eliminating the steps 2-7 restatement.

Trim 'When to Use This Skill' and 'Sample Invocation Phrases', or fold the invocation phrases into the description where they aid triggering.

Add an explicit error-recovery checkpoint: what to do if the 'Session Onboarding (Read First)' section or its closing '---' boundary is not found in copilot-instructions.md.

DimensionReasoningScore

Conciseness

The body is mostly lean lists and templates with no padding of known concepts, but 'When to Use This Skill' duplicates the frontmatter description, 'Execution Steps' (steps 2-7) restates the 'Scan Process' sections 1-4, and 'Sample Invocation Phrases' adds redundant content.

3 / 5

Actionability

Fully concrete and executable: exact directories and file patterns to scan, a specific counting command (`wc -l catalog/*.jsonl`), a complete output template with all required subsections, and named edit/verify operations.

5 / 5

Workflow Clarity

A clear 10-step sequence with a final verification step ('Confirm the update with file read') and an existence-check rule before marking features ✅, but there is no explicit feedback loop if section boundaries are not found or the replacement fails.

4 / 5

Progressive Disclosure

A single-file skill with no bundle files (references/scripts/assets are absent; all paths named are repo scan targets, not skill references), well-organized with headers and the essential output template inline. At ~174 lines with internal redundancy it is solid but not maximally tight.

4 / 5

Total

16

/

20

Passed

Description

87%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: third-person, concise, with an explicit 'Use when...' clause and a highly specific target artifact. Minor room to surface the natural invocation phrases ('sync repo state', 'refresh copilot instructions') that users actually say.

DimensionReasoningScore

Specificity

Concrete actions ('Scan codebase and design docs', 'update the Session Onboarding section') target a precisely named artifact (copilot-instructions.md), going beyond the 1-2 generic actions of anchor 3, though it lists only two actions rather than anchor 5's comprehensive multi-action coverage.

4 / 5

Completeness

Explicitly answers both what (scan codebase and design docs to update a named section in a named file) and when ('Use at the start of a new development phase or when onboarding context is stale') with concrete trigger conditions.

5 / 5

Trigger Term Quality

Good keyword coverage ('Session Onboarding', 'copilot-instructions.md', 'development phase', 'onboarding context is stale'), but natural user phrases like 'sync repo state' or 'refresh copilot instructions' appear only in the body, not the description.

4 / 5

Distinctiveness Conflict Risk

A clear niche — regenerating one specific section of one specific file — with triggers that would not plausibly collide with other skills.

5 / 5

Total

18

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

0xRabbidfly/Eric-Cartman

Path

.github/skills/repo-state-sync/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.