detecting-performance-regressions

Automatically detect performance regressions in CI/CD pipelines by comparing metrics against baselines. Use when validating builds or analyzing performance trends. Trigger with phrases like "detect performance regression", "compare performance metrics", or "analyze performance degradation".

Quality

58%

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 ./plugins/performance/performance-regression-detector/skills/detecting-performance-regressions/SKILL.md

Quality

Content

27%

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

The skill body is organized into clear sections but is largely descriptive rather than instructional: it gives no executable commands or code, ignores its own bundled scripts, and provides no validation feedback loops. It also fails to use progressive disclosure, leaving the bundle files unlinked and an inline monolithic structure.

Suggestions

Replace the abstract Instructions with concrete, executable steps that invoke the bundled scripts (e.g., `python scripts/analyze_metrics.py <metrics> --json` then `python scripts/generate_report.py`), so the guidance is copy-paste ready.

Add validation checkpoints and a feedback loop (run analysis -> review regressions -> re-run after fixes) to lift workflow clarity for this batch operation.

Link to the bundle files from the body (e.g., 'See scripts/analyze_metrics.py' and 'See assets/report_template.html') and remove or correct the non-existent ${CLAUDE_SKILL_DIR}/performance/baselines/ path so progressive disclosure works.

Dimension	Reasoning	Score
Conciseness	Sections like Overview, How It Works, When to Use, and Resources restate the description and list generic concepts; the body is mostly efficient but includes padding that could be tightened, and never explains concepts Claude doesn't already know, so it does not fall to level 1.	2 / 3
Actionability	The Instructions are abstract directives ('Collect performance metrics', 'Apply statistical analysis to detect significant changes') with no concrete commands or code, and the bundled scripts (analyze_metrics.py, generate_report.py, create_github_comment.py) are never referenced or invoked, so it describes rather than instructs.	1 / 3
Workflow Clarity	A six-step Instructions sequence exists, but there are no validation checkpoints or feedback loops for an automated batch operation, which per the rubric caps workflow clarity at 2.	2 / 3
Progressive Disclosure	The body is a monolithic wall of text with sections that should live in the bundled references/scripts, and it never links to or signals the existing scripts/, references/, or assets/ files, nor does the ${CLAUDE_SKILL_DIR}/performance/baselines/ path it cites exist in the bundle.	1 / 3
	Total	6 / 12 Passed

Description

90%

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 well-structured description that cleanly answers what and when with natural trigger phrases and a distinct niche. Its only weakness is that the listed capabilities stay somewhat abstract rather than enumerating concrete, specific actions.

Dimension	Reasoning	Score
Specificity	The description names the domain and several actions ('detect performance regressions', 'comparing metrics against baselines', 'validating builds', 'analyzing performance trends'), but the actions remain fairly high-level rather than the concrete, multi-action listing of the level-3 anchor.	2 / 3
Completeness	It explicitly answers both what ('detect performance regressions in CI/CD pipelines by comparing metrics against baselines') and when ('Use when validating builds or analyzing performance trends'), with explicit trigger phrases.	3 / 3
Trigger Term Quality	It provides natural phrases a user would actually say — 'detect performance regression', 'compare performance metrics', 'analyze performance degradation' — giving good coverage of likely trigger language.	3 / 3
Distinctiveness Conflict Risk	The CI/CD performance-regression niche with dedicated trigger phrases is clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/performance/performance-regression-detector/skills/detecting-performance-regressions/SKILL.md
Commit: 15940c5

Reviewed: 4 days 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.