skill-prototype

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

Quality

64%

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 ./skills/skill-prototype/SKILL.md

Quality

Content

75%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 lean, well-structured contract for bounded prototyping with concrete field lists, verdict vocabulary, and meaningful validation checkpoints. Its main weaknesses are the missing numbered-step/feedback-loop framing and inline references pointing to bundle files that are not actually present.

Suggestions

Number the workflow steps and add an explicit fix-and-retry feedback loop around the cleanup/ownership check to push workflow clarity toward 5.

Provide a one-line example invocation of scripts/plan-storage.sh so the storage step is copy-paste ready.

Either ship the referenced bundle files (scripts/plan-storage.sh, skills/blocks/codex-host-adapter.md, THIRD_PARTY_NOTICES.md) or convert the inline references to brief inline explanations so navigation does not dead-end.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (e.g., "Use a prototype to answer one named question, not to start implementation by a different name"), with only the host-adapter blockquote at the top reading as minor boilerplate padding; it is not 5 because that blockquote is not strictly core instruction.	4 / 5
Actionability	It gives concrete, actionable guidance—a specific storage path ("scripts/plan-storage.sh"), an enumerated completion-record field list, and a fixed verdict vocabulary (keep/discard/inconclusive)—with only minor gaps such as no example invocation of the storage script; this fits mostly-executable guidance with minor gaps rather than fully copy-paste ready.	4 / 5
Workflow Clarity	A clear logical sequence is present (agree contract → record revision → store artifacts → wait for handoff → stop at deadline → return verdict/disposition) with validation checkpoints (explicit handoff wait, ownership checks before cleanup, retain user-changed artifacts); it is not 5 because the steps are not numbered and there is no explicit fix-and-retry feedback loop.	4 / 5
Progressive Disclosure	The short doc is well-organized with titled sections and clearly signaled inline references (plan-storage.sh, codex-host-adapter.md, THIRD_PARTY_NOTICES.md); it is not 5 because those referenced files are absent from the bundle (no references/, scripts/, or assets/ directories exist), so the one-level-deep reference structure is only partially realized.	4 / 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 concrete and third-person with a clear niche, but it omits any explicit "when to use" trigger guidance, which caps completeness and limits trigger-term quality. Adding a "Use when..." clause with natural synonyms would lift the weaker dimensions.

Suggestions

Add an explicit "Use when..." clause naming natural trigger phrases (e.g., "Use when validating one risky assumption, running a time-boxed spike, or testing a hypothesis before committing to implementation").

Include common synonyms users would say (spike, proof of concept, hypothesis test) to improve trigger-term coverage.

Optionally surface the bounded/disposable nature (fixed budget, keep-or-discard verdict) as a distinctiveness cue to reduce overlap with general prototyping skills.

Dimension	Reasoning	Score
Specificity	The description names the prototyping domain and two concrete actions ("Prototype one risky assumption" and "keep or discard the result"), matching the anchor for 1-2 concrete actions without comprehensive coverage; it is not score 4 because it does not list several specific actions.	3 / 5
Completeness	It clearly states what the skill does but has no "Use when..." clause or equivalent trigger guidance, so per the cap it cannot exceed 3; the clear "what" with missing "when" matches that anchor exactly.	3 / 5
Trigger Term Quality	"Prototype" and "risky assumption" are relevant, reasonably natural keywords, but common synonyms users would actually say (spike, proof of concept, validate an assumption) are missing, fitting the anchor for some relevant keywords lacking common variations.	3 / 5
Distinctiveness Conflict Risk	"Prototype one risky assumption within a fixed budget" carves a fairly distinct niche with only minor overlap risk against general build skills, fitting the mostly-distinct anchor; it is not 5 because the bare word "prototype" could still overlap with related skills.	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: 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.