CtrlK
BlogDocsLog inGet started
Tessl Logo

perf-profile

Structured performance profiling workflow. Identifies bottlenecks, measures against budgets, and generates optimization recommendations with priority rankings.

62

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/perf-profile/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is concise, clearly sequenced with explicit gating and next-step routing, and well-organized without external reference sprawl; its main weakness is that the deliverable report is a placeholder template rather than a complete worked example.

Suggestions

Provide one fully worked example of the profiling report (with realistic sample values filled into the budget table and hotspot table) so the output format is unambiguous.

Optionally include one concrete example of estimating a hotspot's impact (e.g., a sample cost calculation) to raise the actionability of the 'Estimated Impact' column beyond placeholders.

Clarify how 'Estimated Current' values are to be derived (e.g., from static analysis heuristics vs. requiring runtime profiling) so the budget table is fillable without ambiguity.

DimensionReasoningScore

Conciseness

Lean, well-organized bullet lists with no over-explanation of concepts Claude already knows; every line (budget examples, profiling targets, report template) earns its place, matching the 'lean and efficient' anchor.

3 / 3

Actionability

Provides concrete profiling targets (e.g. '_process() / Update() / Tick()', nested loops, raycasts) and a structured report template, but the report is placeholder-driven markdown rather than copy-paste-ready executable commands; not score 1 because the guidance is specific and actionable, not score 3 because key deliverables remain template placeholders rather than complete examples.

2 / 3

Workflow Clarity

Clear six-phase sequence with an explicit gated trigger ('Activate this phase only if any hotspot has Fix Effort rated M or L'), enumerated A-D choices, deferred-item recording, and explicit next-step routing in Phase 6, matching the anchor for clear sequencing with explicit checkpoints.

3 / 3

Progressive Disclosure

A single self-contained file with well-organized sections and no nested or deeply-referenced materials; no bundle files exist, and the content is appropriately split into phases without requiring external references, satisfying the simple-skill allowance.

3 / 3

Total

11

/

12

Passed

Description

65%

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 and clearly bounded, using proper third-person voice, but it omits any explicit 'when to use it' trigger clause, which caps its completeness and limits the natural trigger terms a user would say.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when investigating performance bottlenecks, frame-rate drops, or when a system exceeds its performance budget.'

Incorporate natural user-facing trigger terms such as 'fps drops', 'frame rate', 'game runs slow', or 'over budget' alongside the technical 'profiling' language.

Mirror the phrasing pattern of the good examples (concrete actions + 'Use when...') to lift completeness and trigger-term quality together.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Identifies bottlenecks, measures against budgets, and generates optimization recommendations with priority rankings' — matching the anchor for listing several specific concrete actions; not score 2 because it goes beyond naming only a domain and a few actions.

3 / 3

Completeness

Clearly answers 'what' the skill does but provides no explicit 'when to use it' guidance; the rubric caps completeness at 2 when a 'Use when...' clause or equivalent trigger guidance is missing.

2 / 3

Trigger Term Quality

Contains relevant terms like 'performance profiling' and 'bottlenecks' but lacks the natural user phrasing and common variations (e.g., 'when the game runs slow', 'fps drops', 'frame rate'); not score 3 because coverage of terms users would actually say is incomplete, not score 1 because some relevant keywords are present.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (performance profiling against budgets) with distinct triggers unlikely to collide with other skills; not score 2 because it is more than 'somewhat specific' — its scope is sharply bounded.

3 / 3

Total

10

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
Donchitos/Claude-Code-Game-Studios
Reviewed

Table of Contents

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.