perf-code-paths

Use when mapping code paths, entrypoints, and likely hot files before profiling.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./perf/skills/code-paths/SKILL.md

Quality

Content

72%

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

The content is concise and well-organized with a clear output template and shallow references, suiting a simple analysis skill. Its weaknesses are actionability and workflow clarity, where steps are abstract and lack an explicit verification step against the canonical contract.

Suggestions

Make steps more actionable by giving concrete commands or query examples (e.g., a sample repo-map invocation or a grep pattern for finding handlers/entrypoints).

Add an explicit verification step that confirms the candidate paths and symbols align with docs/perf-requirements.md before producing the final output, establishing a validation checkpoint in the workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean at roughly 30 lines with no padding or explanation of concepts Claude already knows; every section (Required Steps, Output Format, Constraints) earns its place, matching the score-3 anchor for lean, efficient content.	3 / 3
Actionability	Steps give some concrete direction (repo-map or grep, list candidate files, a structured output template) but no executable commands, and some steps like "List top candidate files/symbols" remain abstract, fitting the score-2 anchor of incomplete concrete guidance.	2 / 3
Workflow Clarity	The three steps form a clear sequence (map, list candidates, add call chains) with an output template, but there is no explicit validation or verification step against the perf-requirements contract, matching the score-2 anchor of steps present with implicit or missing checkpoints.	2 / 3
Progressive Disclosure	The body is under 50 lines with well-organized sections and a single one-level-deep, clearly signaled reference (docs/perf-requirements.md as the canonical contract), matching the score-3 anchor and the guideline allowing simple skills to score 3 on organization alone.	3 / 3
	Total	10 / 12 Passed

Description

77%

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 concise and explicitly covers both capability and trigger conditions, with concrete actions and a clear "Use when" clause. Its main weakness is trigger-term breadth and a modest overlap risk with general code-navigation skills.

Suggestions

Broaden trigger terms to include natural user phrasings like "find bottlenecks," "where does this code run," or "performance hotspot" to improve trigger_term_quality.

Sharpen distinctiveness by tying the trigger more tightly to the pre-profiling context (e.g., "Use when preparing to profile or benchmark, before running profiling tools") to reduce overlap with generic code-search skills.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete actions — "mapping code paths, entrypoints, and likely hot files" — rather than naming only a domain, matching the score-3 anchor for listing several specific concrete actions.	3 / 3
Completeness	It states both what it does (mapping code paths/entrypoints/hot files) and an explicit "Use when ... before profiling" trigger clause, satisfying the score-3 anchor that both what and when are clearly present.	3 / 3
Trigger Term Quality	Terms like "code paths," "entrypoints," "hot files," and "profiling" are reasonably natural, but common user variations such as "find bottlenecks" or "where does X run" are missing, fitting the score-2 anchor of some relevant keywords without broad coverage.	2 / 3
Distinctiveness Conflict Risk	The pre-profiling mapping niche is fairly specific, but "mapping code paths" overlaps with generic code-search/repo-map skills enough that it could trigger for the wrong skill, matching the score-2 anchor of somewhat specific but overlapping.	2 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: composio-community/awesome-claude-plugins
Path: perf/skills/code-paths/SKILL.md
Commit: e521f7a

Reviewed: about 13 hours 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.