CtrlK
BlogDocsLog inGet started
Tessl Logo

private-github-search

Full-text search across all of the user's GitHub repos (including private ones) using a local mirror and ripgrep. Use for "where did I put X", "which repo has X", or any search spanning the user's repos - gh search code / the REST API cannot reliably search private repos.

76

Quality

95%

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

100%

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

An exemplar short-form skill body: lean, concrete, well-structured, with executable commands and a clear workflow. No bundle files were present to verify referenced paths against, but the content stands well on its own.

DimensionReasoningScore

Conciseness

Lean and efficient; the opening context (modern search is web-only, 'gh search code' uses the legacy engine) is non-obvious justification Claude would not already know, and every other token is concrete guidance with no concept padding.

3 / 3

Actionability

Provides fully executable commands (find for the sync script, bash to run it, rg -il / rg -in with specific flags and paths) that are copy-paste ready aside from the expected 'pattern' placeholder.

3 / 3

Workflow Clarity

Clear sequencing (refresh-first, then search) with a built-in freshness gate, plus a distinct first-time-setup flow; as a simple, non-destructive skill the scoring note allows a 3 despite no explicit post-sync validation.

3 / 3

Progressive Disclosure

Under 50 lines with well-organized sections (Searching, First-time setup, Caveats) and a single-level reference to the sync script found via find; per the scoring note a short skill with no need for external reference files can score 3 on organization alone.

3 / 3

Total

12

/

12

Passed

Description

90%

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 well-crafted description: concise, third-person, with explicit 'Use for' triggers and natural user phrasings. The only soft spot is specificity, which lists one primary action rather than multiple concrete actions.

DimensionReasoningScore

Specificity

Names the domain and concrete mechanism ('Full-text search across all of the user's GitHub repos... using a local mirror and ripgrep'), but describes a single primary action rather than listing multiple specific concrete actions like the level-3 anchor.

2 / 3

Completeness

Clearly answers 'what' (full-text search via local mirror and ripgrep) and 'when' with an explicit 'Use for...' trigger clause, satisfying both halves.

3 / 3

Trigger Term Quality

Includes natural user phrasings ('where did I put X', 'which repo has X', 'any search spanning the user's repos') that a user would naturally say, giving good coverage of natural trigger terms.

3 / 3

Distinctiveness Conflict Risk

Has a clear niche (searching private GitHub repos via a local mirror) with distinct triggers, making it unlikely to fire for the wrong skill.

3 / 3

Total

11

/

12

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
ykdojo/claude-code-tips
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.