perf-profiler

Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.

Quality

82%

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

65%

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

The body is commendably concise and well-organized, but its guidance stays at the level of rules and placeholder templates rather than executable commands, lacks a sequenced workflow with validation checkpoints, and points to a referenced file that is absent from the bundle.

Suggestions

Add at least one concrete, copy-paste-ready profiling example (e.g., `perf record -F 99 -g -- ./app` or an `async-profiler` invocation) so actionability reaches executable guidance rather than placeholders.

Sequence the work as explicit numbered steps with a validation checkpoint before producing artifacts (e.g., verify debug symbols resolved and the flame graph is non-empty), giving a clear feedback loop.

Either create `docs/perf-requirements.md` in the bundle or remove the dangling reference so the canonical-contract link actually resolves.

Dimension	Reasoning	Score
Conciseness	The ~25-line body is lean and assumes Claude's competence, with no concept-explaining padding; every section earns its place (rules, output format, constraints).	3 / 3
Actionability	The "Required Rules" are guidance rather than executable commands, and the output format uses placeholders like "<profiler>" and "file:line - reason"; there is no copy-paste-ready profiling command or code example, so guidance is concrete but incomplete.	2 / 3
Workflow Clarity	The rules form an unordered checklist rather than a sequenced workflow, and there is no explicit validation/feedback checkpoint after profiling (e.g., confirm symbols resolved or the flame graph is non-empty), leaving checkpoints implicit.	2 / 3
Progressive Disclosure	The body is well-sectioned, but it references "docs/perf-requirements.md" as the canonical contract and no such file exists in the bundle, so the one-level reference does not resolve and navigation is broken.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 concise, well-constructed description that names concrete actions, includes an explicit "Use when" trigger, and occupies a distinctive niche. It avoids vague fluff and over-claims while covering the natural terms a user would say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence" — matching the anchor for listing several specific concrete actions rather than just naming a domain.	3 / 3
Completeness	The explicit "Use when…" clause answers when, and the enumerated actions answer what, satisfying the anchor for clearly answering both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	Natural domain terms a user would actually say ("profiling", "flame graphs", "JFR", "perf", "CPU/memory hot paths") with good coverage, and the explicit "Use when" clause signals the trigger clearly.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche (performance profiling via flame graphs/JFR/perf) with distinct triggers unlikely to overlap with unrelated skills.	3 / 3
	Total	12 / 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/profile/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.