Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

questioning

To ask targeted clarification questions only when high-impact unknowns block safe execution.

Quality

73%

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 ./instructions/r2/core/skills/questioning/SKILL.md

Quality

Content

72%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 exceptionally lean and well-organized for a simple, single-purpose skill, with explicit prioritization and stop conditions. Its main weaknesses are the absence of a concrete example question (with impact and safe default) and an explicit ordered workflow with validation checkpoints.

Suggestions

Add one example of a well-formed question, e.g. showing the question text, its impact rating, and an enterprise safe default, so the required output shape is unambiguous.

Convert the rules into an explicit ordered sequence (identify unknowns -> prioritize -> ask -> loop until clear -> stop when unresolved) so the workflow checkpoints are explicit rather than implicit.

Specify the expected output format (e.g. numbered questions grouped by impact level) to make the deliverable concrete.

Dimension	Reasoning	Score
Conciseness	The ~25-line body has zero padding and no explanations of concepts Claude already knows — every line is a directive ("Prioritize by impact: scope > security/privacy > UX > technical", "Keep one decision per question"). Lean and efficient; every token earns its place.	5 / 5
Actionability	Rules are specific directives ("Ask few independent questions at a time", "Include why it matters and enterprise safe defaults") but there is no example of a well-formed question or an output format. For a question-crafting skill, guidance is concrete yet incomplete — missing key details an example would supply, fitting anchor 3 rather than 4.	3 / 5
Workflow Clarity	A rough process is discernible (identify unknowns, prioritize, ask few, "Adjust and loop with questions until crystal clear", "STOP when critical blockers remain unresolved"), but the bullet list is not an ordered sequence and checkpoints like the loop-and-stop conditions are implicit rather than explicit validation gates. Steps present with implicit checkpoints fits anchor 3, not 4.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no bundle files and no need for external references; content is cleanly organized into <role>, <when_to_use_skill>, and <rules> sections. This squarely meets the simple-skill exception where well-organized sections alone merit a 5.	5 / 5
	Total	16 / 20 Passed

Description

62%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 concise, in third-person voice, and covers both what the skill does and when to use it via an explicit conditional. Its main gaps are missing natural trigger synonyms and only a single concrete action named.

Suggestions

Add 2-3 concrete trigger phrases users would naturally say, e.g. 'Use when requirements are ambiguous, scope is unclear, or critical assumptions could derail execution'.

Name one more concrete capability, such as the output it produces (targeted questions with impact ratings and safe defaults), to lift specificity.

Include common synonyms like 'clarifying questions', 'ambiguous requirements', or 'unresolved assumptions' for broader natural-language coverage.

Dimension	Reasoning	Score
Specificity	"ask targeted clarification questions" names the domain and one concrete action, but the description stops there — no mention of output format, prioritization, or safe defaults. Matches the anchor for 1-2 concrete actions without comprehensive coverage, not the several-action list of level 4.	3 / 5
Completeness	The "what" is explicit ("To ask targeted clarification questions") and the "when" is an explicit conditional ("only when high-impact unknowns block safe execution"), which is equivalent trigger guidance rather than merely implied. Not 5 because the when-clause names no concrete user situations or trigger phrases.	4 / 5
Trigger Term Quality	"clarification questions" and "high-impact unknowns" are relevant keywords, but common natural variations users would say ("unclear requirements", "ambiguous scope", "should I ask first") are missing. Some relevant keywords without synonym coverage fits anchor 3, not the good coverage of 4.	3 / 5
Distinctiveness Conflict Risk	Questioning-on-blockers is a distinct niche with its own triggers, distinguishable from most skills. Minor overlap risk remains with general planning or requirements-gathering skills, so not the minimal-conflict niche of level 5.	4 / 5
	Total	14 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: griddynamics/rosetta
Path: instructions/r2/core/skills/questioning/SKILL.md
Revision: ee7166a

Reviewed: 21 days ago

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.

questioning

Table of Contents

Is this your skill?