CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

prototype

Answer a design or feasibility question with explicitly throwaway spike code — never committed, findings recorded in the diary or an ADR draft. Use when a decision is blocked on "would X even work?" (library capability, API behavior, performance shape). Not for building features — that's /tdd via /implement.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is prototype in agranado2k/google-books-clojure

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 an exemplary lean instruction skill: dense, non-obvious rules, a crisp procedure with decision points, and no filler or concept re-teaching. The only improvement opportunities are a sample diary entry and an explicit verify-before-delete checkpoint, which hold actionability and workflow clarity at 4.

DimensionReasoningScore

Conciseness

The body is lean and efficient with zero padding — every rule ('Timebox it', 'No production standards apply', 'Never promote spike code') adds non-obvious, skill-specific constraints. It fully assumes Claude's competence and never explains concepts Claude already knows.

5 / 5

Actionability

Concrete, specific guidance throughout: an example falsifiable question, the exact spike location rule (session scratchpad or $TMPDIR, never under the project), the diary entry fields (question, verdict, evidence, surprises), and a version-citation requirement. As an instruction-only skill the absence of code is not penalized, but a one-line example diary entry would close the remaining gap.

4 / 5

Workflow Clarity

The Procedure is a clear 4-step sequence with an explicit decision checkpoint ('Confirm a spike is cheaper than reading the docs') and a built-in escape hatch in rule 3 ('A spike that runs long is answering a different, bigger question — stop and say so'). Steps are unambiguous and correctly ordered (record finding, then delete spike dir), but there is no explicit verification that the recorded entry is complete before deletion — a minor checkpoint gap.

4 / 5

Progressive Disclosure

A single-file skill under 50 lines with no need for external references: content is appropriately self-contained and organized into well-labeled sections ('Rules', 'Procedure') with clear navigation. Per the rubric's simple-skill guidance, this earns the top score.

5 / 5

Total

18

/

20

Passed

Description

87%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 strong example: concrete actions, an explicit 'Use when' trigger with a memorable natural phrase ('would X even work?'), and explicit conflict-avoidance boundaries against related implementation skills. Only trigger-synonym coverage and output concreteness keep specificity and trigger quality at 4 rather than 5.

DimensionReasoningScore

Specificity

Names several concrete actions — 'throwaway spike code', 'findings recorded in the diary or an ADR draft', answering a 'design or feasibility question' — with only minor abstraction gaps (no concrete output example). It lists multiple specific actions but is slightly less comprehensive than the top anchor.

4 / 5

Completeness

Explicitly answers both what ('Answer a design or feasibility question with explicitly throwaway spike code — never committed, findings recorded') and when ('Use when a decision is blocked on "would X even work?"'), with concrete trigger phrases. The negative boundary ('Not for building features — that's /tdd via /implement') further completes the guidance.

5 / 5

Trigger Term Quality

'would X even work?', 'library capability, API behavior, performance shape', and 'spike'/'feasibility' are natural phrases a user would say when needing this skill. Good coverage, though a few common synonyms (e.g. 'proof of concept', 'try before building') are missing, keeping it just below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Clear niche (throwaway feasibility spikes) with explicit disambiguation from neighboring skills ('Not for building features — that's /tdd via /implement'), making wrong-skill triggering unlikely.

5 / 5

Total

18

/

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

agranado2k/tic-tac-toe-with-agentic-sdlc

Path

.claude/skills/prototype/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.