CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

performance-review

Reviews model latency/cost, cache policies, duplicate query coalescing, and heavy asset load performance. Use during optimization or profiling.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/performance-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 lean, well-organized review checklist that respects token budget and avoids over-explanation, but it tells Claude what to verify without how to verify it. Adding concrete measurement commands and explicit validation checkpoints would substantially raise its usefulness.

Suggestions

Add concrete check methods: e.g., run EXPLAIN ANALYZE on suspect queries, use the platform's query timing/telemetry endpoint, or list the specific commands used to profile latency and detect duplicate queries.

Include a verification step after the checklist (e.g., confirm findings with measured numbers before posting the Review record comment) so the review has an explicit feedback loop.

For asset loading, name the lazy-loading controls or measurement tools (e.g., bundle analyzer command) so the 'Resource Streaming' bullet is executable rather than directional.

DimensionReasoningScore

Conciseness

The ~25-line body is a lean checklist with zero padding: each line gives a directive ('Verify that... leverage caching layers', 'Ensure queries leverage appropriate indices') without explaining concepts Claude already knows. Every token earns its place, matching the 5 anchor.

5 / 5

Actionability

Names concrete artifacts ('rag_response_cache', 'trigram/lexical text indexes', 'vector HNSW') but provides no commands, queries, or methods for how to actually measure latency, detect duplicate queries, or audit costs. This matches 'some concrete guidance but incomplete' rather than 4, which would require mostly executable guidance.

3 / 5

Workflow Clarity

A rough sequence is present (follow review protocol, run checklist by area, post one 'Review record' comment), but validation checkpoints are implicit and there are no verification or completion criteria. Not 4 because most checkpoints would need to be explicit; not 2 because the protocol section does define a coherent pre/post structure.

3 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files present and no need for external references; sections ('Repository Review Protocol', 'Review Checklist', two numbered subsections) are well-organized. Per the simple-skill guideline this earns a 5.

5 / 5

Total

16

/

20

Passed

Description

75%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 solid description that clearly states what the skill reviews and when to use it, with concrete domain-specific terms (coalescing, cache policies, asset load). Its main weakness is a generic 'when' clause and missing natural trigger variations that would push it to top scores.

DimensionReasoningScore

Specificity

Lists several concrete review targets ('model latency/cost', 'cache policies', 'duplicate query coalescing', 'heavy asset load performance') with only minor coverage gaps. Not 5 because it uses a single verb ('Reviews') and never states what outputs or actions the skill performs beyond reviewing.

4 / 5

Completeness

Has a clear 'what' (reviews latency/cost, cache policies, coalescing, asset load) and an explicit 'when' ('Use during optimization or profiling'). Not 5 because the 'when' clause is generic and does not name concrete user scenarios or trigger phrases, matching the 4 anchor exactly.

4 / 5

Trigger Term Quality

Includes natural terms users would say when needing this skill ('optimization', 'profiling', 'latency', 'cost', 'cache'). Not 5 because common variations like 'slow', 'speed up', or 'performance tuning' are missing; better than 3 since coverage goes beyond a couple of generic keywords.

4 / 5

Distinctiveness Conflict Risk

Specific items like 'duplicate query coalescing' and 'cache policies' carve a distinct performance-review niche with minimal trigger ambiguity. Not 5 because 'optimization or profiling' is broad enough to overlap with general optimization or code-review skills.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

BigSimmo/PsychSift

Path

.cursor/skills/performance-review/SKILL.md

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.