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 minimal description that fails on all dimensions. It provides no concrete actions, no trigger guidance, and no clarity on when or why Claude should select this skill. 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 outlines algorithm logic step-by-step.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks for pseudocode, algorithm outlines, logic planning, or step-by-step procedure descriptions.'

Remove the invocation syntax ('invoke with $agent-pseudocode') from the description as it wastes space that should be used for capability and trigger information.

Dimension	Reasoning	Score
Specificity	The description provides no concrete actions whatsoever. 'Agent skill for pseudocode' is extremely vague—it doesn't describe what the skill does with pseudocode (generate it, convert it, analyze it, etc.).	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 explanation of capabilities beyond the word 'pseudocode'.	1 / 3
Trigger Term Quality	The only keyword is 'pseudocode', which is relevant but insufficient. There are no natural variations or related terms users might say (e.g., 'algorithm outline', 'logic sketch', 'code planning'). The invocation syntax '$agent-pseudocode' is not a natural user trigger term.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it could overlap with any coding, algorithm, or documentation skill. There are no distinct triggers or clear niche boundaries to differentiate it.	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 reads more like a textbook chapter on pseudocode writing than an actionable agent instruction set. It is extremely verbose with generic algorithm design examples that Claude already knows, while lacking the critical operational details: what to do when invoked, how to process inputs from the specification phase, what format to output, and how to validate results. The content needs a fundamental restructuring to focus on the agent's actual workflow rather than teaching pseudocode concepts.

Suggestions

Replace the bulk of generic pseudocode examples with a concise workflow: what inputs the agent receives (from spec phase), what steps to follow, what output format to produce, and how to validate the result before passing to the next SPARC phase.

Remove or move to a separate reference file the lengthy examples of common patterns (Strategy, Observer, rate limiting, search) that Claude already knows—keep only a single short example showing the expected pseudocode format/style.

Add explicit validation checkpoints, e.g., 'Verify all spec requirements are covered by at least one algorithm' and 'Confirm complexity analysis is included for each algorithm before marking phase complete.'

Add a concrete example of a complete phase execution: given a sample specification input, show the expected pseudocode deliverable output, so Claude knows exactly what 'done' looks like.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~250+ lines, mostly consisting of lengthy pseudocode examples that illustrate general algorithm design concepts Claude already knows (LRU caches, token bucket rate limiting, search scoring, observer pattern, strategy pattern). The best practices section states obvious principles like 'use meaningful names' and 'handle edge cases.' Very little here is novel information that Claude couldn't generate on its own.	1 / 3
Actionability	The pseudocode examples are concrete and well-structured, providing clear templates for how to write pseudocode. However, none of this is executable code—it's pseudocode about writing pseudocode. The skill lacks specific instructions on what Claude should actually do when invoked (e.g., what inputs to expect, what output format to produce, how to interact with the user or other SPARC phases).	2 / 3
Workflow Clarity	There is no clear workflow for what the agent should do when invoked. The SPARC Pseudocode Phase section lists 5 high-level goals but provides no sequenced steps, no validation checkpoints, and no feedback loops. The 'Deliverables' section lists outputs but doesn't explain how to produce them or verify their quality.	1 / 3
Progressive Disclosure	The content is a monolithic wall of text with no references to external files and no layered structure. All examples are inline regardless of their relevance. The lengthy design pattern examples (Strategy, Observer) and multiple full algorithm examples could easily be split into referenced files, keeping the main skill focused on the actual workflow.	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: 9d4a9ea

Reviewed: 6 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.