CtrlK
BlogDocsLog inGet started
Tessl Logo

review-performance

Use when reviewing a branch diff for performance defects — redundant database round trips, N+1 queries, unbounded reads, per-request layer rebuilds, wasted client fetches, and build steps that ship a broken artefact — and reporting findings with P-C/W/I IDs in the four-field format.

72

Quality

90%

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

The canonical home for this skill is review-performance in englishstreetventures/osn

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exceptionally actionable skill body: exact commands, a routing table that gates mandatory sections, explicit validation checkpoints with recovery loops, and a clean one-level reference split. The only weakness is repetition of the skeleton-preservation warning, which costs tokens without adding instruction.

DimensionReasoningScore

Conciseness

The body is dense and prescriptive, assumes competence (never explains git, Drizzle, Effect, or SolidJS) and cites repo-specific files like 'cire/api/src/services/directory.ts', but the skeleton-preservation warning is repeated roughly four times (Step 0, the bold 'never rewritten' paragraph, the Step 2 shape check, and the final check) — emphatic prose that could be trimmed, matching the 4 anchor rather than the 5 anchor's every-token-earns-its-place.

4 / 5

Actionability

Guidance is fully executable throughout: a verbatim heredoc that writes the report skeleton, 'BASE=$(git config --get branch.$(git branch --show-current).gh-merge-base || echo main)', an exact grep routing table with concrete patterns, 'grep -c' shape-check commands, 'grep -rn \'<gateName>('\'', and a copy-paste finding template — matching the 5 anchor's copy-paste-ready coverage of common cases.

5 / 5

Workflow Clarity

Steps 0→1→2 are clearly sequenced, with an explicit mid-run validation checkpoint ('Check the shape once, as soon as the first finding is in the file'), a feedback loop for recovery ('If it prints less... restore the 4 headings, put the finding back under the right one, and edit from then on'), and a final two-count check — the 5 anchor's explicit validation with error-recovery loops, not merely the 4 anchor's 'most checkpoints'.

5 / 5

Progressive Disclosure

The single reference file 'references/checklists.md' exists, is one level deep, and is clearly signaled both by the routing table's '(references)' markers and a dedicated section explaining when to open it and why the split exists ('no scenario in this repository's eval suite exercises them'), with the core defect class kept inline — matching the 5 anchor's well-signaled, appropriately split structure.

5 / 5

Total

19

/

20

Passed

Description

88%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: it names a specific trigger scenario, enumerates concrete defect classes, and defines the output format. The only gaps are a few missing natural synonyms ('slow', 'latency', 'perf') and slight overlap risk with generic diff-review skills.

DimensionReasoningScore

Specificity

The description enumerates concrete defect classes ('redundant database round trips, N+1 queries, unbounded reads, per-request layer rebuilds, wasted client fetches, and build steps that ship a broken artefact') and specifies the output format ('P-C/W/I IDs in the four-field format'), giving comprehensive concrete actions with no coverage gaps — the 5 anchor, not 4.

5 / 5

Completeness

It opens with an explicit 'Use when reviewing a branch diff for performance defects' trigger clause and concretely states what it does (detect the named defect classes, report findings with tiered P-C/W/I IDs in a four-field format), clearly answering both what and when — matching the 5 anchor rather than 4, where the 'when' would be less explicit.

5 / 5

Trigger Term Quality

'reviewing a branch diff', 'performance defects', and 'N+1 queries' are phrases users would naturally say, giving good keyword coverage, but common synonyms such as 'slow', 'latency', 'perf', or 'optimize' are missing — above the 3 anchor's partial coverage, short of the 5 anchor's synonym completeness.

4 / 5

Distinctiveness Conflict Risk

The performance-review niche with tiered P-C/W/I findings is mostly distinct, but the trigger 'reviewing a branch diff' overlaps with general code-review and PR-review skills, so it is minor overlap risk (4) rather than the 5 anchor's minimal conflict risk.

4 / 5

Total

18

/

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
englishstreetventures/englishstreetventures.com
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.