agent-pseudocode

Agent skill for pseudocode - invoke with $agent-pseudocode

1.61x

Quality

48%

Does it follow best practices?

Impact

84%

1.61x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-pseudocode/SKILL.md

Quality

Content

57%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 content is a well-structured, concrete reference for pseudocode design with usable templates and complexity examples, but it is verbose in places and presented as a single monolithic file with no progressive disclosure or external references. The phase "workflow" is a list of parallel activities rather than a sequenced process with validation checkpoints.

Suggestions

Replace the five parallel activities with an explicit sequenced workflow that includes a validation checkpoint (e.g., verify the pseudocode covers every spec requirement and that complexity targets are met before finalizing deliverables).

Move the extended example library (data structures, algorithm patterns, design patterns) into separate files under references/ and link to them from SKILL.md, turning the body into a lean overview and lifting progressive disclosure.

Trim the "Pseudocode Best Practices" section and remove the redundant second YAML agent-definition block, both of which restate knowledge Claude already has.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient reference material (pseudocode templates, complexity tables) but is padded by the "Pseudocode Best Practices" section restating obvious principles ("Use Meaningful Names", "Language Agnostic") and a redundant second YAML agent-definition block; it fits the score-3 anchor "Mostly efficient but includes some unnecessary explanation," falling short of 4 due to these trimmable passages and above 2 because the core examples earn their place.	3 / 5
Actionability	It provides concrete, reusable templates — the ALGORITHM/INPUT/OUTPUT/BEGIN format, DATA STRUCTURES block, and complexity-analysis layout are copy-adaptable scaffolding, matching the score-4 anchor "Mostly executable guidance; concrete code with minor gaps"; pseudocode is the skill's actual deliverable format, justifying the non-executable form, though minor typos ("Email$password logic", "time$space complexity") keep it from 5.	4 / 5
Workflow Clarity	The "SPARC Pseudocode Phase" lists five activities (design, select, analyze, identify, roadmap) as a rough sequence but with no validation checkpoints or feedback loops, fitting the score-3 anchor "Steps listed but validation gaps; checkpoints missing or implicit"; it cannot reach 4 because there is no explicit verify/validate step, and stays above 2 because a recognizable sequence exists.	3 / 5
Progressive Disclosure	The ~320-line body is well-headed (Structure/Syntax, Data Structures, Patterns, Complexity, Design Patterns) but is a monolithic single file with no references split out and no bundle files present, matching the score-3 anchor "Some structure but content that should be separate is inline"; the under-50-line simple-skill exception does not apply, and the lack of any one-level-deep reference files keeps it below 4, while clear headers keep it above 2.	3 / 5
	Total	13 / 20 Passed

Description

40%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 is a sparse label rather than a capability statement: it names the pseudocode domain but lists no concrete actions and provides no "Use when" trigger guidance. It is distinct enough to avoid most conflicts but fails to tell Claude what it does or when to invoke it.

Suggestions

Add concrete actions the skill performs, e.g., "Designs algorithms, selects optimal data structures, analyzes time/space complexity, and identifies design patterns from a specification."

Add an explicit "Use when..." trigger clause, e.g., "Use when translating a specification into algorithmic logic, selecting data structures, or planning implementation flow."

Include natural trigger synonyms users might say ("algorithm design", "logic flow", "complexity analysis") alongside "pseudocode" for broader keyword coverage.

Dimension	Reasoning	Score
Specificity	The text names the domain ("pseudocode") but states no concrete actions — "Agent skill for pseudocode - invoke with $agent-pseudocode" only labels the skill, mirroring the score-2 anchor "Processes PDF files"; it does not reach 3 because no concrete actions (design, analyze, select) are listed, and it stays above 1 because the domain is specifically named rather than abstract.	2 / 5
Completeness	It offers only a vague "what" ("Agent skill for pseudocode") and no "when" — "invoke with $agent-pseudocode" describes invocation mechanics, not a trigger condition, matching the score-2 anchor "Has a vague 'what' and no 'when'"; it cannot reach 3 because there is no explicit "Use when..." guidance, and is above 1 because a domain is at least named.	2 / 5
Trigger Term Quality	"pseudocode" is a relevant, natural keyword a user might say, matching the score-3 anchor "Works with PDF files" (one specific keyword); it falls short of 4 because coverage is a single term with no synonyms or variations (e.g., "algorithm design", "logic flow"), and stays above 2 since "pseudocode" is specific rather than generic like "Works with files".	3 / 5
Distinctiveness Conflict Risk	"pseudocode" carves a clear niche with minor overlap risk against closely related algorithm/code skills, fitting the score-4 anchor; it does not reach 5 because there are no distinct trigger phrases to disambiguate usage, and stays above 3 because the domain is specific rather than broadly overlapping.	4 / 5
	Total	11 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Path: .agents/skills/agent-pseudocode/SKILL.md
Commit: fa13ee4

Reviewed: about 4 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.