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.

A lean, well-structured instruction skill: every token earns its place, the rules are concrete and project-specific, and the procedure is clearly sequenced with genuine checkpoints. It sits just below top marks on actionability and workflow clarity only for unspecified timebox limits and the absence of a recovery path for inconclusive spikes.

DimensionReasoningScore

Conciseness

Every rule carries project-specific constraints (scratchpad dir, `docs/diary.md`, `constitution/local-engineering.md`, timebox, no-promotion) with no explanation of concepts Claude already knows; the one justificatory parenthetical in rule 4 is load-bearing, not padding.

5 / 5

Actionability

Concrete, executable guidance for an instruction-only skill: "use the session scratchpad directory (or `$TMPDIR`)", a worked example of a falsifiable question, "Write the answer (question, verdict, evidence, surprises) into `docs/diary.md` as a dated entry", and a report format. Minor gaps: the timebox ("a spike that runs long") and step 2's "smallest program" leave scope and limits unspecified.

4 / 5

Workflow Clarity

The Procedure is a clear four-step sequence with real checkpoints — the question-phrasing gate ("If you can't phrase the question, you're not ready to spike"), the docs-first check, and the timebox stop rule. Not a 5 because there is no recovery path for ambiguous or inconclusive spike results, and no explicit validation of the captured evidence before recording it.

4 / 5

Progressive Disclosure

A sub-50-line, single-purpose skill with two well-organized sections (Rules, Procedure) and no need for external references — no references/, scripts/, or assets/ bundle exists, and the files mentioned (`docs/diary.md`, `constitution/local-engineering.md`) are project artifacts, not skill bundle paths, so the simple-skill exception applies.

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.

A tight, third-person description that concretely states what the skill does, when to trigger it, and what it is not for. Minor gaps in keyword synonyms (e.g., "proof of concept") keep trigger-term coverage and action breadth just below the top anchors.

DimensionReasoningScore

Specificity

"Answer a design or feasibility question with explicitly throwaway spike code — never committed, findings recorded in the diary or an ADR draft" names several concrete actions (run a throwaway spike, keep it out of the repo, record findings in diary/ADR), but coverage is a single workflow rather than the comprehensive multi-action list of the 5 anchor.

4 / 5

Completeness

Both halves are explicit: the "what" ("Answer a design or feasibility question with explicitly throwaway spike code — never committed, findings recorded") and the "when" with a concrete trigger phrase ("Use when a decision is blocked on 'would X even work?'").

5 / 5

Trigger Term Quality

"Use when a decision is blocked on 'would X even work?' (library capability, API behavior, performance shape)" gives natural phrases users would say, plus "feasibility", but misses common synonyms like "proof of concept", "POC", or "can we use X".

4 / 5

Distinctiveness Conflict Risk

A clear niche (feasibility spikes) with an explicit exclusion boundary — "Not for building features — that's /tdd via /implement" — plus "never committed" separating it from production-code skills, so conflict risk is minimal.

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-haskell

Path

.agents/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.