code-search-assistant

Search code repositories for code related to a given code snippet, ranking results by call chain similarity, textual similarity, and functional similarity. Use when finding related code, locating similar implementations, discovering code dependencies, or identifying code that performs similar operations. Outputs ranked file lists with matching code snippets and relevance scores.

1.27x

Quality

74%

Does it follow best practices?

Impact

87%

1.27x

Average score across 3 eval scenarios

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/code-search-assistant/SKILL.md

Quality

Content

46%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 presents a clear, well-structured multi-step search workflow but is notably verbose, explaining basic programming concepts and repeating tips across two sections, and lacks executable scoring detail and validation checkpoints. Tightening and adding verification steps would most improve it.

Suggestions

Remove explanations of basic concepts Claude already knows (loop patterns, if-else chains, definitions of data transformation/auth/error handling) and collapse the two tips sections into one to cut tokens.

Make the scoring actionable: provide a concrete formula or small script mapping shared-call counts and textual/functional matches to 0–1 sub-scores rather than listing abstract percentage weights.

Add validation checkpoints to the workflow, e.g., confirm search scope before running, handle empty/low-confidence results explicitly, and sanity-check the top-ranked matches before presenting them.

Dimension	Reasoning	Score
Conciseness	The ~230-line body explains concepts Claude already knows (e.g., 'Same loop patterns (for, while, forEach, map)', 'Authentication/Authorization: Login, permission checks, token handling') and carries two redundant tips sections ('Search Optimization Tips' and 'Tips') that pad rather than inform.	2 / 5
Actionability	Concrete tool guidance is present (use Glob with */.js, use Grep for calls, Read matching files), but the scoring is described abstractly ('weight: 40%') without an executable way to turn shared-call counts into 0–1 scores, leaving key details unspecified.	3 / 5
Workflow Clarity	A clear 7-step sequence is laid out, but there are no validation or verification checkpoints (e.g., confirming scope, handling empty results, sanity-checking top scores), which the rubric caps at 3 for batch search operations.	3 / 5
Progressive Disclosure	Internal section structure is good and well-organized (Overview, numbered workflow steps, examples), and the self-contained single-file layout is acceptable, though the duplicated tips sections are a minor organization gap.	4 / 5
	Total	12 / 20 Passed

Description

88%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 specific, complete, and uses natural third-person trigger language covering both capabilities and use cases. It is a strong, low-conflict description with only minor room to add synonyms for trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — searching repositories, ranking by three named similarity dimensions (call chain, textual, functional), and outputting ranked file lists with snippets and scores — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (search, rank by similarity, output ranked lists) and 'when' with a concrete 'Use when...' clause enumerating distinct trigger scenarios.	5 / 5
Trigger Term Quality	Includes natural user phrases like 'finding related code', 'locating similar implementations', 'discovering code dependencies', and 'similar operations', but lacks synonyms or file-extension-style triggers that would round out coverage.	4 / 5
Distinctiveness Conflict Risk	The similarity-based code-search niche is clearly distinct with specific triggers, though there is minor overlap risk with generic grep/search or code-navigation skills.	4 / 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: ArabelaTso/Skills-4-SE
Path: skills/code-search-assistant/SKILL.md
Commit: 4f38503

Reviewed: 12 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.