CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agent-pseudocode

Agent skill for pseudocode - invoke with $agent-pseudocode

1.61x
Quality

56%

Does it follow best practices?

Impact

84%

1.61x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

50%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 contains genuinely useful, concrete pseudocode templates and complexity-analysis examples, but it is bloated: a redundant embedded frontmatter block, a design-patterns primer Claude doesn't need, and no progressive disclosure of the large example library. The workflow reads as a task list without validation checkpoints.

Suggestions

Remove the duplicate YAML agent-config block at the top of the body — it redundantly restates metadata and is not part of the instructions.

Move the extended worked examples (search algorithm, rate limiting, data structures) into a references/ file and keep one compact exemplar inline to cut the body by more than half.

Convert the phase steps into a sequenced workflow with an explicit validation checkpoint (e.g. review the spec from memory, then verify complexity analysis before marking the phase complete) and drop the Strategy/Observer pattern primer Claude already knows.

DimensionReasoningScore

Conciseness

The body opens with a redundant second YAML agent-config block duplicating metadata, then pads ~290 lines with five lengthy worked examples plus a 'Design Patterns in Pseudocode' section teaching Strategy/Observer patterns Claude already knows. Several padded sections place it at 'Noticeably verbose', not merely 'could be tightened' (3).

2 / 5

Actionability

For an instruction-only skill, the ALGORITHM / DATA STRUCTURES / COMPLEXITY ANALYSIS templates are concrete, adaptable models of the exact deliverable, backed by a Deliverables checklist — 'Mostly executable guidance … with minor gaps'. Not 5 because the procedure for consuming the retrieved specification is never explained and stray corruption ('Email$password logic', 'time$space complexity') degrades the templates.

4 / 5

Workflow Clarity

The five numbered phase steps are a task checklist rather than a sequenced workflow, and there are no validation checkpoints before the post-hook marks 'pseudo_complete' — 'Steps listed but validation gaps; checkpoints missing'. Not 4, since no verification or feedback loop is explicit.

3 / 5

Progressive Disclosure

Section headers give the ~290-line body some structure, but everything — including the extensive example library that clearly belongs in a references file — is inlined with no external files or navigation cues, matching 'content that should be separate is inline'. The <50-line simple-skill exception does not apply.

3 / 5

Total

12

/

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 identifies the skill's niche (pseudocode) but says nothing about what it actually does or when it should be used. It reads as a loader stub ("invoke with $agent-pseudocode") rather than a capability-and-trigger statement.

Suggestions

Add a 'Use when…' clause with concrete trigger phrases, e.g. 'Use when the user asks to design an algorithm, write pseudocode, or plan the logic before implementation.'

Enumerate the concrete capabilities already implied by the body: algorithm design, data structure selection, complexity analysis, and design pattern identification.

Mention the SPARC methodology context and natural synonyms (algorithm design, logic planning) to improve both trigger coverage and distinctiveness.

DimensionReasoningScore

Specificity

"Agent skill for pseudocode - invoke with $agent-pseudocode" names the domain but includes no concrete actions (e.g. designing algorithms, analyzing complexity), matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 1 since the domain is named, and not a 3 since no concrete capability verbs are listed.

2 / 5

Completeness

The 'what' is vague (it only says it is an "Agent skill for pseudocode") and the 'when' is entirely absent — no 'Use when…' clause or equivalent trigger guidance, which caps completeness. This matches 'Has a vague what and no when' rather than 3, whose what is clear.

2 / 5

Trigger Term Quality

"pseudocode" is a natural term a user would say, but there are no synonyms or variations (algorithm design, SPARC, pseudocode planning) and "invoke with $agent-pseudocode" is invocation syntax rather than a natural trigger phrase — 'Some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The pseudocode niche with its SPARC-phase framing is mostly distinct with only minor overlap risk against general coding or design skills; it lacks the sharper trigger phrases of a 5.

4 / 5

Total

11

/

20

Passed

Validation

100%

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

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.