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 merely names the domain ('pseudocode') without describing any concrete capabilities, use cases, or trigger conditions. It reads more like a label than a functional description.

Suggestions

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

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to write pseudocode, outline an algorithm, draft logic steps, or convert code to pseudocode.'

Remove the invocation syntax ('invoke with $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 description lacks natural variations users might say (e.g., 'algorithm design', 'pseudo code', 'logic outline'). The invocation syntax '$agent-pseudocode' is not a natural user trigger term.	1 / 3
Distinctiveness Conflict Risk	While 'pseudocode' is a somewhat specific domain, the description is so vague that it's unclear what this skill does versus any other coding or algorithm-related skill. It could easily conflict with general coding assistance skills.	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 a verbose, textbook-style reference on pseudocode writing that explains many concepts Claude already knows (design patterns, data structures, complexity analysis). It lacks a clear workflow for the SPARC pseudocode phase, has no validation steps, and dumps all content into a single monolithic file. The examples, while well-formatted, are generic and don't provide unique value beyond what Claude can already produce.

Suggestions

Reduce content by 70%+: Remove generic examples (strategy pattern, observer pattern, LRU cache) and best practices Claude already knows. Focus only on the specific SPARC pseudocode format and conventions unique to this workflow.

Add a clear step-by-step workflow: Define how to receive specification input, what questions to validate before designing algorithms, and explicit checkpoints (e.g., 'verify all spec requirements are covered before proceeding').

Split detailed examples into a separate reference file (e.g., EXAMPLES.md) and keep SKILL.md as a concise overview with links.

Add concrete guidance on how to integrate with other SPARC phases—how to read specification output from memory, what format to store pseudocode results in, and what signals readiness for the next phase.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~250+ lines. Explains basic concepts Claude already knows (what pseudocode is, what design patterns are, what LRU caches are). The extensive examples of authentication flows, search algorithms, strategy/observer patterns are generic textbook material that don't add unique value. The 'best practices' section states obvious principles like 'use meaningful names.'	1 / 3
Actionability	Provides concrete pseudocode examples and complexity analysis templates, which give Claude a clear format to follow. However, these are illustrative examples rather than executable code or specific commands. The skill describes what pseudocode should look like but doesn't provide actionable steps for how to approach a new problem (e.g., how to gather inputs from the specification phase, what questions to ask).	2 / 3
Workflow Clarity	The five-step SPARC Pseudocode phase list (designing solutions, selecting data structures, etc.) is vague and lacks sequencing detail. There are no validation checkpoints, no feedback loops for verifying algorithm correctness, and no clear process for how to move from specification input to pseudocode output. The deliverables section is a checklist but not a workflow.	1 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files. All content—examples, patterns, analysis templates—is inlined in a single massive document. No bundle files are provided, and the content would benefit greatly from splitting examples and pattern references into separate 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/ruflo
Commit: 619b263

Reviewed: about 11 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.