CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ask-questions-if-underspecified

Clarify requirements before implementing. Use when serious doubts arise.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ask-questions-if-underspecified/SKILL.md

The canonical home for this skill is ask-questions-if-underspecified in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 content is a strong example of an instruction-only skill: a clearly sequenced workflow with explicit pause and confirmation checkpoints, concrete question templates with reply formats, and anti-patterns that prevent misuse. Its only weaknesses are minor over-prescription in formatting details and a body length that slightly exceeds ideal inline size.

DimensionReasoningScore

Conciseness

The body is lean and directive with no explanation of concepts Claude already knows, but a few spots are over-prescriptive — the defaults-marking bullet ('bold the recommended choice... put a bold "Recommended" line immediately above the block and also tag defaults inside the block') and the templates section repeating workflow ideas — keeping it just below the 'every token earns its place' anchor.

4 / 5

Actionability

For an instruction-only skill the guidance is fully executable: copy-paste-ready question templates, a complete example block with a concrete reply format ('Reply with: defaults (or 1a 2a)'), and specific limits like 'Ask 1-5 questions in the first pass'. These cover the common cases directly.

5 / 5

Workflow Clarity

The 4-step sequence (decide -> ask -> pause -> confirm) is clearly ordered with explicit gates and feedback loops: 'do not start implementing until the must-have questions are answered', an assumption-confirmation loop when the user forces proceeding, and a restatement checkpoint before work begins. This is not a destructive or batch operation, so no validation cap applies.

5 / 5

Progressive Disclosure

Sections are well organized (When to Use / When NOT / Goal / Workflow / templates / Anti-patterns) with all content appropriately inline for a skill of this size and no external references. The body runs ~80 lines — above the under-50-line simple-skill exception — so the question templates could arguably move to a reference file, leaving minor organization room at score 4.

4 / 5

Total

18

/

20

Passed

Description

46%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 answers both 'what' and 'when' but does so at a high level of abstraction: one generic capability and a vague internal-state trigger. It lacks the concrete actions (asking questions, pausing work, confirming assumptions) and natural user trigger phrases that would make it specific and reliably discoverable.

Suggestions

Enumerate the concrete actions in the description, e.g., 'Ask numbered clarifying questions, offer default choices, and pause implementation until must-have answers arrive' instead of the generic 'Clarify requirements'.

Replace 'Use when serious doubts arise' with natural user-facing trigger phrases such as 'Use when the request is ambiguous or underspecified, key requirements are unclear, or multiple interpretations exist'.

Add trigger synonyms users would actually say (unclear, ambiguous, vague, underspecified, missing details) to improve keyword coverage and distinguish the skill from generic planning/requirements-gathering skills.

DimensionReasoningScore

Specificity

"Clarify requirements before implementing" names the domain but offers only a single generic action, matching 'Processes PDF files' (score 2) rather than the 1-2 concrete actions required for score 3 (e.g., 'ask numbered clarifying questions', 'pause before implementing').

2 / 5

Completeness

Both parts are present: what = "Clarify requirements before implementing" and when = "Use when serious doubts arise". The 'when' clause is explicit but vague rather than concrete trigger phrases, so it sits at score 4 rather than 5, and is clearly above score 3 where 'when' is only weakly implied.

4 / 5

Trigger Term Quality

The only keywords are "requirements" and "doubts"; "Use when serious doubts arise" describes Claude's internal state rather than natural user phrasing like "unclear", "ambiguous", or "not sure what I want", fitting the score-2 anchor of one or two generic keywords missing natural phrases.

2 / 5

Distinctiveness Conflict Risk

"Clarify requirements" carves out a behavioral niche but overlaps with planning, scoping, and requirements-gathering skills; it is somewhat specific yet could still trigger for related skills, matching the score-3 anchor.

3 / 5

Total

11

/

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

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/ask-questions-if-underspecified/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.