CtrlK
BlogDocsLog inGet started
Tessl Logo

performance-review

Performance-focused code review for identifying bottlenecks and optimization opportunities

52

Quality

58%

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 ./templates/template-github-review-agent/workspace/skills/performance-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

The body is a compact, well-organized pattern checklist that respects Claude's intelligence and points to a real, one-level-deep reference. Its weaknesses are actionability (no detection, measurement, or reporting guidance) and an unclear division of labor with the referenced checklist.

Suggestions

Deduplicate the body against references/performance-checklist.md — keep the body as a short category overview plus when-to-use-the-checklist, and let the reference hold the full pattern list.

Add concrete detection/verification guidance, e.g. example profiling commands, or how to confirm a suspected N+1 (query logging, EXPLAIN) before flagging it.

Specify what to do with findings: an output format and explicit criteria for assigning CRITICAL/HIGH/MEDIUM/LOW severities.

DimensionReasoningScore

Conciseness

The body is a lean checklist of concrete patterns with no padded explanations of concepts Claude already knows, matching 'Efficient; minor instances of over-explanation that could be trimmed'. It is not a 5 because several bullets restate knowledge Claude already has (e.g. 'SELECT * instead of selecting only needed columns', 'String concatenation in loops') and the body substantially duplicates the categories in references/performance-checklist.md.

4 / 5

Actionability

The bullets name concrete patterns to look for (N+1 queries, missing indexes, unbounded caches), but there is no guidance on how to detect or verify them, how to measure impact, or how to report findings. This fits 'Some concrete guidance but incomplete... missing key details' rather than score 4's mostly-executable guidance with minor gaps.

3 / 5

Workflow Clarity

As a simple, single-purpose skill, the instruction 'check each category below' followed by a severity rubric is unambiguous, matching 'Clear sequence with most checkpoints present; minor validation gaps'. It is not a 5 because the workflow stops short of saying what to do with findings — no reporting format, no criteria for choosing between severity levels, and no guidance on how the inline checklist relates to the referenced checklist.

4 / 5

Progressive Disclosure

The body is well organized into sections and clearly signals a one-level-deep reference ('Reference the detailed checklist in references/performance-checklist.md'), which is a real file, fitting 'Good structure; most content appropriately placed; references mostly clear; minor organization gaps'. It falls short of 5 because the body and the referenced checklist largely duplicate each other's categories, so the content is not cleanly split between overview and reference.

4 / 5

Total

15

/

20

Passed

Description

50%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.

The description communicates a clear domain and purpose in third person without fluff, but it lacks any 'Use when...' trigger guidance and offers only generic capability language. Adding explicit trigger phrases and concrete capabilities would lift most dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to speed up code, reports slowness/latency, or asks for a performance or optimization review of a codebase.'

Replace generic capability language with concrete actions, e.g. 'Detects N+1 queries, memory leaks, unnecessary re-renders, and O(n²) hot paths; ranks findings by severity.'

Include natural synonyms and user phrasings (slow, latency, profiling, throughput) to improve trigger-term coverage and distinctiveness.

DimensionReasoningScore

Specificity

The description names the domain ("Performance-focused code review") and two actions ("identifying bottlenecks and optimization opportunities"), but these are generic capabilities rather than a list of several concrete actions. It matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' and falls short of score 4, which requires several specific listed actions.

3 / 5

Completeness

The 'what' is clear (performance-focused code review to identify bottlenecks), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is clearly stated, and not a 4 because no 'when' guidance exists at all, even weakly implied.

3 / 5

Trigger Term Quality

Relevant keywords like "performance", "code review", "bottlenecks", and "optimization" are present, but common user phrasings such as "slow", "latency", "profiling", "speed up", or "laggy" are missing. This fits 'Some relevant keywords but missing common variations or synonyms' and does not reach score 4's 'a few natural terms missing' coverage.

3 / 5

Distinctiveness Conflict Risk

"Performance-focused" narrows the niche relative to a general code-review skill, but the description still overlaps broadly with any review/refactoring skill since no distinct trigger phrases or unique capabilities are named. It fits 'Somewhat specific but could still overlap with similar skills' rather than score 4's 'minor overlap risk with closely related skills'.

3 / 5

Total

12

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
mastra-ai/mastra
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.