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.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/private-github-search/SKILL.md

Quality

Content

68%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 compact, well-structured skill body that leads with non-obvious rationale and gives concrete ripgrep commands plus a sensible first-time setup flow. Its main weakness is the absence of an explicit validation checkpoint for the batch sync step, which caps workflow clarity.

Suggestions

Add an explicit verification step after the sync (e.g., check that `~/repo-mirror/repos` is non-empty or that the sync script exited 0) before running search commands, to satisfy the batch-operation validation expectation.

Replace the `bash <script-path>` placeholder with a concrete one-liner that captures the found path into a variable and reuses it, making the workflow copy-paste ready.

Confirm the referenced `private-github-search-sync.sh` is actually bundled (e.g., under `scripts/`) and reference it by a direct relative path so the bundle structure matches the body.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanation of what ripgrep or mirroring is); the opening paragraph justifies the approach with non-obvious facts about GitHub's search engines, which earns its place, with only minor wording that could be trimmed — efficient but not perfectly lean.	4 / 5
Actionability	Provides concrete, executable commands (`find ~/.claude ~/.codex -name ...`, `rg -il 'pattern' ~/repo-mirror/repos`) and a clear first-time setup sequence; falls short of score 5 because `bash <script-path>` and `'pattern'` are placeholders rather than fully copy-paste-ready examples.	4 / 5
Workflow Clarity	The refresh-then-search sequence and first-time setup are clearly ordered, but the batch sync operation (cloning all repos) lacks an explicit validation/verification checkpoint that it succeeded before searching; per the rubric's batch-operation cap, workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	Well-organized into clearly signaled sections (Searching, First-time setup, Caveats) with a single one-level-deep reference to a bundled sync script; not a 5 because the script is located dynamically via `find` and no bundle directory is present to confirm the referenced file, leaving a minor organization gap.	4 / 5
	Total	15 / 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, third-person description that conveys a concrete capability, a clear mechanism, and natural trigger phrases while explicitly contrasting itself with the unreliable built-in alternatives. It is concise yet complete.

Dimension	Reasoning	Score
Specificity	Names the concrete action ("Full-text search across all of the user's GitHub repos") and the specific mechanism ("using a local mirror and ripgrep"), plus scope ("including private ones") — several specific actions with only minor coverage gaps, fitting the score-4 anchor rather than the comprehensive score-5 list.	4 / 5
Completeness	Explicitly answers both what ("Full-text search across all of the user's GitHub repos ... using a local mirror and ripgrep") and when ("Use for 'where did I put X', 'which repo has X', or any search spanning the user's repos") with concrete trigger phrases, matching the score-5 anchor exactly.	5 / 5
Trigger Term Quality	Includes natural user phrases ("where did I put X", "which repo has X", "any search spanning the user's repos") that a user would actually say, giving good keyword coverage; falls short of score 5 only because it lacks file-extension or additional synonym variants.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (private-repo full-text search via a local ripgrep mirror) with distinctive triggers and an explicit contrast to `gh search code`, giving minimal conflict risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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: ykdojo/claude-code-tips
Path: skills/private-github-search/SKILL.md
Commit: 2da5305

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.