performance

Review performance lanes with GitHub-scale tactics not owned by Vercel React rules: cohort segmentation, repeated-unit budgets, interaction-level INP, memory tagging, degradation contracts, browser trace proof, and production dashboards.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/performance/SKILL.md

Quality

Content

92%

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

The content is an exemplar of lean, actionable, well-sequenced performance-review guidance with strong validation checkpoints. Its only real weakness is that the bundled detail files it links to are absent, leaving the reference structure partially broken.

Suggestions

Provide the ./rules/*.md files referenced in the Extra Rules table so the one-level-deep progressive disclosure actually resolves.

If the rule files are intentionally omitted from this distribution, note inline that they are external/optional so broken links are not mistaken for missing content.

Keep the current table-driven structure; no changes needed to the overview's conciseness or sequencing.

Dimension	Reasoning	Score
Conciseness	The body is table-driven and tightly written with no tutorial padding — e.g. 'Rule: if the plan only says "use React best practices", "avoid O(n)", or "seems fast locally", it is not done.' — assuming Claude's competence and earning every token.	3 / 3
Actionability	It gives a sequenced Quick Pass, a filled output template, and a concrete worked example with exact budgets ('per block <= 1 element component, 0 per-block global listeners, 0 per-block effects unless scoped by id/range'), making the guidance copy-paste ready.	3 / 3
Workflow Clarity	A 9-step Quick Pass is paired with an explicit Blockers table acting as validation gates ('Stop the performance claim or mark the plan incomplete when any required answer is missing') and a checklist-style Required Output, giving clear sequence with checkpoints and error-recovery feedback.	3 / 3
Progressive Disclosure	Reference links are well-signaled and one level deep with clear 'Use when' triggers in the Extra Rules table, but the referenced ./rules/*.md files do not exist in the bundle, so the progressive-disclosure promise of detail files is unfulfilled.	2 / 3
	Total	11 / 12 Passed

Description

67%

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 well-differentiated but misses an explicit 'Use when' trigger and leans on internal jargon over natural user phrasing. These two gaps keep it solidly mid-range rather than top-tier.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when a Plate plan claims speed, responsiveness, large-document readiness, or production performance.'

Swap some internal taxonomy ('repeated-unit budgets', 'degradation contracts') for user-recognizable terms like 'slow scrolling', 'input lag', 'Core Web Vitals', or 'p95 latency' to broaden trigger coverage.

Keep the tactic list but front-load the most common user phrasing so the description reads as a trigger, not just a capability inventory.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete tactics — 'cohort segmentation, repeated-unit budgets, interaction-level INP, memory tagging, degradation contracts, browser trace proof, and production dashboards' — matching the score-3 anchor for naming several specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does ('Review performance lanes with...tactics') but lacks any explicit 'Use when...' trigger clause, so the 'when' is only implied — capping completeness at 2 per the judging guideline.	2 / 3
Trigger Term Quality	'Performance', 'INP', and 'production dashboards' are recognizable, but most terms ('repeated-unit budgets', 'degradation contracts', 'cohort segmentation', 'memory tagging') are the skill's internal taxonomy rather than phrases users naturally say, and common variations like 'Core Web Vitals', 'responsiveness', and 'p95 latency' are absent.	2 / 3
Distinctiveness Conflict Risk	'not owned by Vercel React rules' and the precise tactic list carve a clear niche and explicitly demarcate ownership from the vercel-react-best-practices skill, making conflict unlikely.	3 / 3
	Total	10 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
relative_links	Relative link issues: 14 missing	Warning

	Total	12 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/performance/SKILL.md
Commit: 45116fd

Reviewed: about 14 hours 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.