similar-code

Find similar implementations and prior art for a code pattern across internal repositories — use when checking whether something already exists internally before building it, or looking for reference implementations to follow.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

A well-structured, actionable process skill with concrete search commands, a rigorous vetting framework, and ready-to-use output templates, all written concisely without over-explaining basics. The main gaps are placeholder-only search examples and the absence of an explicit validate/retry feedback loop.

Suggestions

Include at least one fully worked search example with a real topic substituted in (e.g. 'rate limiting') so the command pattern is copy-paste ready, not just a template.

Add an explicit feedback checkpoint after vetting — e.g. 'if no Recommended implementations, loop back to Phase 2 with new synonyms before reporting none found' — to close the workflow loop.

Consider extracting the large output templates into a referenced file (e.g. templates.md) so the main body stays a lean overview, which would also raise progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean: core principles, phased search commands, a vetting table, and output templates with no padding or explanation of concepts Claude already knows; the two full output templates are somewhat long but earn their place, leaving only minor trimming opportunities.	4 / 5
Actionability	Concrete guidance is provided via real `code_search` command syntax, a detailed vetting criteria table, and copy-pasteable output templates; the search commands still rely on placeholder substitution ([topic], [synonym]) rather than fully worked examples, which is the minor gap keeping it from 5.	4 / 5
Workflow Clarity	Six phases are clearly sequenced and Phase 5 ('Vet Each Implementation') acts as an explicit validation gate with reject criteria and anti-pattern signals, plus a fallback path when nothing is found; it lacks an explicit validate-and-retry feedback loop, so it sits just below 5.	4 / 5
Progressive Disclosure	The single file is well organized into Core Principles, a numbered Process, and a fallback section with no nested references and no bundle files to navigate; structure is solid, though no overview-to-detail split exists, keeping it at 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Description

78%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 clearly answers both what the skill does and when to invoke it, with natural trigger phrasing. Its main limitation is that the capability list is essentially a single action stated as synonyms rather than multiple distinct concrete actions.

Suggestions

Add 1-2 more distinct concrete actions (e.g. 'compare approaches and tradeoffs', 'identify shared libraries to reuse') to lift specificity from a single-action cluster to comprehensive coverage.

Include common user synonyms like 'reuse existing code', 'duplicate detection', or 'don't reinvent' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('code pattern across internal repositories') and one concrete action cluster ('Find similar implementations and prior art'), but these are near-synonyms rather than several distinct actions, so it is not comprehensive enough for a 4.	3 / 5
Completeness	It explicitly states both what ('Find similar implementations and prior art...') and when via a concrete 'use when' clause with multiple trigger scenarios, matching the anchor for clearly answering both.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'checking whether something already exists internally', 'before building it', and 'reference implementations to follow' read like what a user would actually say; a few common synonyms (e.g. 'reuse', 'duplicate code') are missing, keeping it just below 5.	4 / 5
Distinctiveness Conflict Risk	The 'across internal repositories' / 'prior art' niche is fairly distinct from generic code-search skills, but it could still overlap with broad code-search or duplicate-detection skills, leaving minor conflict risk.	4 / 5
	Total	16 / 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: gleanwork/claude-plugins
Path: plugins/glean/skills/similar-code/SKILL.md
Commit: a549de6

Reviewed: 5 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.