CtrlK
BlogDocsLog inGet started
Tessl Logo

performance-testing-review-ai-review

You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C

44

Quality

47%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/performance-testing-review-ai-review/SKILL.md

The canonical home for this skill is performance-testing-review-ai-review in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

46%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 rich, code-heavy reference with strong actionability, but it is over-long, padded with concepts Claude already knows, organized as a monolithic wall rather than progressively disclosed, and contains a broken reference. Splitting it into reference files and trimming the filler would materially improve it.

Suggestions

Move the architecture, security (OWASP), performance, and CI/CD reference blocks into separate files under references/ and link to them one level deep from a concise overview in SKILL.md.

Delete the generic 'Use this skill when / Do not use this skill when' boilerplate and the recap of SOLID/OWASP/anti-patterns that Claude already knows.

Resolve the dangling reference: either create resources/implementation-playbook.md or remove the pointer to it.

DimensionReasoningScore

Conciseness

The ~445-line body is noticeably verbose: generic 'Use/Do not use this skill when' boilerplate, filler 'Instructions', and enumeration of concepts Claude already knows (SOLID principles, OWASP Top 10, Singleton/God-object anti-patterns), despite dense code blocks elsewhere.

2 / 5

Actionability

Provides many concrete, mostly-executable code blocks across Python, TypeScript, Go, JavaScript, and GitHub Actions YAML, with minor gaps from placeholder classes (HumanReviewRequired, ReviewEngine) and undefined helper methods (get_pr_diff, to_github_comment).

4 / 5

Workflow Clarity

A numbered 'Initial Triage' sequence and a CI/CD quality-gate checkpoint exist, but the bulk is reference architecture rather than a guided procedure, with no explicit validate->fix->retry loop in the main flow.

3 / 5

Progressive Disclosure

No bundle files exist, yet the monolithic body inlines architecture/security/performance/CI-CD reference that belongs in separate files, and the single referenced file (resources/implementation-playbook.md) is dangling/absent.

2 / 5

Total

11

/

20

Passed

Description

48%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 identifies a clear niche and lists relevant tools, but is truncated, uses second-person voice, leans on buzzwords, and lacks any explicit 'Use when...' trigger clause. It is serviceable but needs tightening and a trigger phrase to rise above mid-range.

Suggestions

Add an explicit trigger clause, e.g. 'Use when reviewing pull requests, auditing diffs for bugs/vulnerabilities, or setting up automated CI/CD code review.'

Rewrite in third person and drop generic buzzwords ('intelligent pattern recognition', 'modern DevOps practices') in favor of concrete actions like 'identify bugs, vulnerabilities, and performance issues in pull-request diffs'.

Fix the truncated text so the description is a complete sentence ending with natural trigger terms users would actually say.

DimensionReasoningScore

Specificity

Names the domain and a few concrete-sounding capabilities ('automated static analysis, intelligent pattern recognition, and modern DevOps practices') plus tools, but actions are generic/buzzword-heavy and the description is truncated mid-word; reduced by 1 for second-person voice ('You are an expert...').

2 / 5

Completeness

Provides a vague-ish 'what' (AI-powered code review combining static analysis, pattern recognition, DevOps) but entirely omits any 'when'/'Use when...' trigger guidance, capping completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

'code review' and 'static analysis' are natural terms, but the description leans on tool names (Copilot, Qodo, GPT-5) users would not say as triggers and misses common variations like 'pull request', 'PR review', or 'code review' synonyms.

3 / 5

Distinctiveness Conflict Risk

'AI-powered code review specialist' carves a fairly distinct niche with minimal conflict against unrelated skills, though it overlaps modestly with general code-review and security-review skills.

4 / 5

Total

12

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.