performance

Profiling methodology and optimization strategy for performance work. Use when the user asks to "make this faster", "optimize", "profile", "reduce latency", "fix slow", "improve throughput", or when investigating performance regressions.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

78%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, lean framework skill with clear progressive disclosure to a real reference file; the main body would benefit from surfacing an explicit validation/revert feedback loop inline rather than only in the reference.

Suggestions

Promote the explicit 'revert immediately if it made things worse' feedback loop from profiling-checklist.md into the Performance Loop so the body's workflow_clarity is self-contained.

Trim the 'Knuth's Reminder' section or fold its 3%/97% point into the existing 'Premature optimization' anti-pattern to reduce decorative tokens.

Add one or two concrete profiler commands inline (e.g. `py-spy record` / `go tool pprof`) so the body is executable without requiring the reference for the most common cases.

Dimension	Reasoning	Score
Conciseness	The body is dense and token-efficient — tables, lists, and short sections — with only minor decorative padding such as the 'Knuth's Reminder' quote, so it sits above the 'mostly efficient but could be tightened' anchor and just below fully lean.	4 / 5
Actionability	As an instruction skill it gives concrete remedies ('Batch operations, add caching, use async I/O, pool connections'), a profiling strategy, and an output template; executable commands live in the clearly-linked reference, leaving only a minor gap in the body itself.	4 / 5
Workflow Clarity	The 6-step Performance Loop is clearly sequenced with a 'Measure again' validation checkpoint and a 'Never skip from step 1 to step 5' guard, but the explicit revert-on-regression feedback loop lives in the reference rather than the body.	4 / 5
Progressive Disclosure	The body is a well-organized overview that clearly signals a single one-level-deep reference (references/profiling-checklist.md, which exists), keeping methodology inline and offloading commands appropriately — matching the top anchor.	5 / 5
	Total	17 / 20 Passed

Description

90%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 description with excellent trigger coverage and explicit what/when guidance; its only weakness is that the capability statement is phrased abstractly rather than as a list of concrete actions.

Suggestions

Replace 'Profiling methodology and optimization strategy' with concrete verbs, e.g. 'Profiles bottlenecks, identifies hot paths, and applies targeted optimizations for performance work.'

Dimension	Reasoning	Score
Specificity	The description names the performance domain and two abstract activities ('profiling methodology', 'optimization strategy') rather than a list of concrete actions, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor and falling short of the 'lists several specific actions' level above.	3 / 5
Completeness	It explicitly states what the skill does ('Profiling methodology and optimization strategy for performance work') and when to use it via concrete trigger phrases plus regression investigation, satisfying both halves of the top anchor.	5 / 5
Trigger Term Quality	It includes numerous natural user phrases with synonyms — 'make this faster', 'optimize', 'profile', 'reduce latency', 'fix slow', 'improve throughput' — giving comprehensive coverage of what a user would actually say, matching the top anchor.	5 / 5
Distinctiveness Conflict Risk	Performance profiling is a clear niche with distinct, domain-specific triggers, and minimal conflict risk with other skills (only mild adjacency to debugging, which is cross-referenced rather than overlapped).	5 / 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: tslateman/duet
Path: skills/performance/SKILL.md
Commit: 5647baf

Reviewed: 3 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.