skill-prototype

Prototype one risky assumption within a fixed budget, then keep or discard the result

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-prototype/SKILL.md

Quality

Content

78%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 is a tight, well-organized instruction skill with concrete fields, verdict values, and sensible safety checkpoints. Its chief weakness is broken bundle references: the script and notice file it points to do not exist, which undermines both actionability and progressive disclosure.

Suggestions

Provide the missing scripts/plan-storage.sh (or remove the reference and inline the storage steps) so the one executable command in the skill actually resolves.

Add the referenced THIRD_PARTY_NOTICES.md, or drop the attribution to a non-existent file and keep only a concise inline license note.

Make the workflow explicit with a short numbered sequence (agree on contract -> record source revision -> build prototype -> stop at deadline -> return verdict + disposition) to lift workflow clarity toward a 5.

Dimension	Reasoning	Score
Conciseness	The body is ~25 lines of lean, boundary-focused instruction with no padding or re-explanation of concepts Claude already knows; every section (contract fields, mode constraints, verdict, completion record) earns its place, matching the 'lean and efficient, assumes Claude's competence' anchor.	5 / 5
Actionability	Concrete guidance is given via explicit field lists (question, hypothesis, deadline, artifact_path, source_revision, etc.) and enumerated verdict values (keep/discard/inconclusive), but the one executable command reference (scripts/plan-storage.sh) does not resolve to a real file, leaving a minor gap that keeps it below a fully copy-paste-ready 5.	4 / 5
Workflow Clarity	The contract-then-execute-then-verdict flow is discernible with real checkpoints (deadline stop, ownership checks before cleanup, retain user-changed artifacts), so it avoids the destructive-operation cap; it is a 4 rather than 5 because the steps are implied rather than explicitly numbered with a validate-fix-retry feedback loop.	4 / 5
Progressive Disclosure	The in-body structure is clean with clear sections, but the body references scripts/plan-storage.sh and THIRD_PARTY_NOTICES.md while no scripts/, references/, or assets/ bundle directories exist, so the referenced paths are dangling and navigation does not resolve, fitting the 'references present but not clearly signaled / resolvable' anchor.	3 / 5
	Total	16 / 20 Passed

Description

53%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 concise, specific, and third-person, clearly stating what the skill does within a bounded prototyping niche. Its main weakness is the missing 'Use when...' trigger guidance, which caps completeness and leaves the 'when to use it' weakly implied.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. "Use when the user wants to test one risky assumption before committing to implementation, mentions a spike, proof of concept, or validating an assumption under a deadline."

Broaden trigger-term coverage with synonyms such as 'spike', 'proof of concept', or 'de-risk an assumption' so users' varied phrasings match.

Consider listing one more concrete action (e.g. 'record a keep/discard/inconclusive verdict') to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Prototype one risky assumption within a fixed budget, then keep or discard the result" names the prototyping domain plus two coupled actions (keep/discard), matching the anchor for 1-2 concrete actions without comprehensive coverage; it is not a 4 because the action list is thin rather than just having minor gaps.	3 / 5
Completeness	The 'what' is clear (prototype one risky assumption, keep/discard), but there is no 'Use when...' clause or equivalent trigger guidance, so per the judging guidelines completeness is capped at 3; it cannot be a 4 without an explicit 'when'.	3 / 5
Trigger Term Quality	Natural terms like "prototype", "risky assumption", and "fixed budget" are present, but there is no synonym or extension coverage (e.g. "spike", "proof of concept", "validate an assumption"), fitting the 'some relevant keywords but missing variations' anchor rather than the fuller coverage of a 4.	3 / 5
Distinctiveness Conflict Risk	"Prototype one risky assumption within a fixed budget" carves a distinct bounded-prototyping niche with low overlap risk, but the absence of explicit triggers leaves minor overlap with general build/prototype skills, so it is a 4 rather than the fully-distinct 5.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-prototype/SKILL.md
Commit: 0093dab

Reviewed: 5 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.