agent-pseudocode

Agent skill for pseudocode - invoke with $agent-pseudocode

1.61x

Quality

Does it follow best practices?

Impact

84%

1.61x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-pseudocode/SKILL.md

Quality

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an extremely weak description that provides almost no useful information for skill selection. It fails on all dimensions: no concrete actions, no trigger guidance, no 'when to use' clause, and no distinguishing characteristics. It reads more like a label than a description.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Generates pseudocode from natural language descriptions, converts code to pseudocode, and formats algorithm logic in structured pseudocode notation.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks for pseudocode, algorithm outlines, logic flow descriptions, or wants to convert code into language-agnostic pseudocode.'

Remove the invocation syntax '$agent-pseudocode' from the description as it wastes space and doesn't help Claude decide when to select this skill.

Dimension	Reasoning	Score
Specificity	The description provides no concrete actions whatsoever. 'Agent skill for pseudocode' is extremely vague and does not describe what the skill actually does (e.g., generate, convert, analyze pseudocode).	1 / 3
Completeness	The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no 'Use when...' clause and no meaningful explanation of capabilities.	1 / 3
Trigger Term Quality	The only keyword is 'pseudocode', which is relevant but insufficient. The invocation syntax '$agent-pseudocode' is not a natural user term. There are no variations or related terms like 'algorithm design', 'code outline', 'logic flow', etc.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it's unclear what domain it occupies beyond 'pseudocode'. It could easily conflict with general coding, algorithm, or documentation skills since no specific niche is carved out.	1 / 3
	Total	4 / 12 Passed

Implementation

14%

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

This skill is excessively verbose, spending most of its token budget on generic pseudocode examples and well-known design patterns that Claude already understands. It lacks a clear actionable workflow for how to actually execute the pseudocode phase of SPARC, and all content is packed into a single monolithic file with no progressive disclosure. The content reads more like a textbook chapter on pseudocode than an operational skill for an AI agent.

Suggestions

Reduce content by 70%+ by removing generic examples Claude already knows (Strategy pattern, Observer pattern, basic pseudocode syntax) and focus on SPARC-specific pseudocode requirements and format templates.

Add a clear step-by-step workflow with validation checkpoints, e.g., 'Step 1: Review specification from memory → Step 2: Identify core algorithms → Step 3: Write pseudocode using template → Step 4: Validate complexity analysis → Step 5: Store deliverables.'

Split detailed examples (design patterns, data structure templates, complexity analysis templates) into separate reference files and link to them from a concise overview.

Add concrete guidance on how to interact with the memory system (memory_store/memory_search) to retrieve specs and store pseudocode outputs, since the hooks reference these but the body ignores them.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~200+ lines. Most content is generic pseudocode examples and design pattern explanations that Claude already knows well. The SPARC methodology explanation, design patterns (Strategy, Observer), and best practices like 'use meaningful names' add no value for Claude. The entire skill could be reduced to a concise template and format specification.	1 / 3
Actionability	The examples are concrete and well-structured pseudocode, but they are illustrative rather than executable. The skill describes what pseudocode should look like with examples but doesn't give Claude clear instructions on how to apply this to an actual user request — it's more of a reference document than an actionable workflow.	2 / 3
Workflow Clarity	The five SPARC Pseudocode phase steps (designing solutions, selecting data structures, analyzing complexity, identifying patterns, creating roadmap) are listed but not sequenced into a clear workflow with validation checkpoints. There's no guidance on when to proceed between steps, how to validate outputs, or how to handle issues. The deliverables section is a checklist but lacks process flow.	1 / 3
Progressive Disclosure	This is a monolithic wall of text with all content inline. Lengthy pseudocode examples, design patterns, complexity analysis templates, and best practices are all crammed into a single file with no references to external files. The data structure examples and design pattern sections could easily be split into separate reference files.	1 / 3
	Total	5 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: f547cec

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.