CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

design-ask

Turn open design questions into a paste-ready prompt for Claude Design, log them with Q-IDs and copy the prompt to the clipboard. Use for "/design-ask", "ask the designer", "questions for design".

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 procedural skill: exact commands, a concrete JSON payload format, a complete paste-text template, and explicit validation checkpoints (user approval gate, duplicate reporting, missing-prefix recovery, pbcopy fallback, empty-case guard) across a clearly numbered workflow. Setup and spec details are properly deferred to one-level-deep external references.

DimensionReasoningScore

Conciseness

The body is lean procedural instruction with zero padding — no concept explanations, just rules like "Never edit questions.md by hand; only the helper changes it" and exact commands. Every token earns its place; the only rationale sentence ("so several people or worktrees can ask questions about the same project without colliding") is brief and load-bearing, so this is not a 4.

5 / 5

Actionability

Everything is executable: the exact invocation "yarn tsx .claude/skills/design-pull/design.ts <command> ...", concrete subcommands (`list-folders`, `set-prefix '<folder>' '<PREFIX>'`, `ask-add '<folder>' '<scratchpad>/ask-items.json'`, `ask-open '<folder>'`), a complete JSON template for ask-items.json, a full paste-text template, and `pbcopy < '<scratchpad>/ask-paste.txt'` with a stated fallback. Not a 4: there are no gaps — edge cases (single question vs. range, pbcopy unavailable) are covered.

5 / 5

Workflow Clarity

Seven numbered steps with explicit checkpoints and error recovery: "If a command reports no question_prefix, ask the user for one... and run set-prefix", "Show the list and wait for the user to approve or edit it", "report the duplicates", "If pbcopy is not available, show the text and say it was not copied", and the step-7 no-op guard "If nothing was added or resent, say so and do not touch the clipboard". This matches the anchor-5 feedback-loop pattern; a 4 would lack some of these checkpoints.

5 / 5

Progressive Disclosure

No bundle files exist, and none are needed: the ~58-line body is appropriately self-contained with well-organized sections (Arguments, Rules, Steps). External material is deferred via clearly signaled one-level-deep pointers — "Spec: docs/.bruno/specs/2026-10-07-design-pull-ask-skills-design.md" and "Setup ... is in the Prerequisites section of .claude/skills/design-pull/SKILL.md" — matching the anchor-5 pattern of well-signaled single-level references. Not a 4: nothing that belongs in a separate file is inlined, and navigation is trivial.

5 / 5

Total

20

/

20

Passed

Description

92%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 strong description: it states three concrete actions in imperative voice and closes with an explicit 'Use for' clause containing natural trigger phrases. The only weakness is that the trigger list could include a few more synonyms such as 'design questions'.

DimensionReasoningScore

Specificity

The description lists three concrete actions covering the full workflow — "Turn open design questions into a paste-ready prompt for Claude Design", "log them with Q-IDs", "copy the prompt to the clipboard" — which comprehensively covers what the skill does. Not a 4 because the actions are specific and complete rather than having minor coverage gaps; not below 5 because no part of the skill's behavior is left abstract.

5 / 5

Completeness

Both parts are explicit: the "what" is the three concrete actions (turn questions into a prompt, log with Q-IDs, copy to clipboard), and the "when" is the explicit "Use for '/design-ask', 'ask the designer', 'questions for design'" clause with concrete trigger phrases. This matches the anchor-5 example structure exactly; a 4 would require the when-clause to be less explicit than it is.

5 / 5

Trigger Term Quality

Triggers "ask the designer" and "questions for design" are natural phrases a user would say, plus the explicit "/design-ask" command. Not a 5 because a few natural variants are missing (e.g., "design questions", "question for the designer", "message the designer"); not a 3 because the given terms are natural rather than jargon and cover the main phrasings.

4 / 5

Distinctiveness Conflict Risk

The niche is narrow and distinct — routing design questions to Claude Design with Q-ID logging — and the triggers ('/design-ask', 'ask the designer', 'questions for design') would not fire for unrelated skills. Not a 4: even the sibling design-pull skill is clearly differentiated (ask = send questions, pull = fetch answers), so overlap risk is minimal.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

webiny/webiny-js

Path

.claude/skills/design-ask/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.