Tessl • The management layer for AI agent skills

SkillPublic

github-code-search

Searches GitHub repositories for real-world code usage and implementation patterns, including private repositories accessible to the authenticated user. Use when the user asks how other projects use an API or library, wants examples from actual repositories, or explicitly requests GitHub code search rather than authoritative or version-specific documentation.

Quality

90%

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

Quality

Content

93%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 an efficient, highly actionable guide with a complete executable command and a built-in verification step. Its only minor gap is the absence of an explicit numbered workflow with error-recovery feedback, which is not strictly required for a simple search skill.

Dimension	Reasoning	Score
Conciseness	Every section is lean and assumes Claude's competence; no tokens are spent explaining what GitHub or code search is, and each line earns its place.	5 / 5
Actionability	Provides a fully executable, copy-paste-ready `gh search code` command complete with flags, JSON output, and a jq transform, plus concrete filter options covering the common cases.	5 / 5
Workflow Clarity	Sections are sequenced (search, refine, respect budget, verify results) and "Using Results" gives an explicit verification checkpoint, but there is no numbered workflow or error-recovery loop.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no external references needed, with well-organized section headers (Flow, Query Guidance, Budget, Using Results) that make navigation trivial.	5 / 5
	Total	19 / 20 Passed

Description

82%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 strong: it states a concrete capability, gives explicit trigger guidance, and distinguishes itself from documentation skills. Its only real gap is that it names a single action rather than enumerating several specific operations.

Suggestions

Enumerate a few more concrete actions (e.g., "find import patterns, locate usages of an identifier, browse real-world call sites") to lift specificity from one action to several.

Add one or two natural synonyms users might say (e.g., "find code examples," "see how others use") to round out trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ("Searches GitHub repositories for real-world code usage and implementation patterns") but lists only a single core action rather than several distinct ones, so it is not comprehensive.	3 / 5
Completeness	Clearly states what the skill does and provides an explicit "Use when..." clause with concrete trigger phrases, satisfying both what and when.	5 / 5
Trigger Term Quality	Captures natural user phrases like "how other projects use an API or library," "examples from actual repositories," and "GitHub code search," with good coverage though a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (GitHub code search) and explicitly distinguishes it from "authoritative or version-specific documentation," minimizing overlap with documentation skills.	5 / 5
	Total	17 / 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: shillem/cc-marketplace
Path: plugins/code-swiss-knife/skills/github-code-search/SKILL.md
Revision: a05ddbb

Reviewed: 26 days ago

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.

github-code-search

Table of Contents

Is this your skill?