CtrlK
BlogDocsLog inGet started
Tessl Logo

ask-user

Reusable pattern for presenting the user with explicit choices and gating execution until they respond. Used by other skills when a decision point requires human input before proceeding. Platform-agnostic — works on Telegram (inline buttons), Discord, CLI, or any agent with a message tool.

54

Quality

61%

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-user/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 well-structured and highly actionable with concrete templates and clear gating workflow, and progressive disclosure is clean for a single-file skill. The chief weakness is repetition: the core constraints are restated across four sections, which inflates token cost without adding value.

Suggestions

Consolidate the repeated constraints (2-4 options, escape hatch, stop-the-turn, one question) into a single canonical section and have other sections reference it rather than restating verbatim.

Add an explicit response-validation/retry loop (e.g. if response fuzzy-matches no option, re-present with 'I didn't catch that' before defaulting) to push workflow_clarity toward 5.

Trim the redundant 'What This Is' explanation that re-derives LLM gating behavior already implied by the Contract and When sections.

DimensionReasoningScore

Conciseness

Mostly efficient but several sections restate the same rules verbatim (the 2-4 options, escape hatch, stop-the-turn, and one-question constraints each appear in Contract, Constraints, How To Gate, and Anti-Patterns), adding padding without new information.

3 / 5

Actionability

Provides concrete, copy-paste-ready message/button/clarify templates and labeled examples covering common cases, with only minor gaps (no executable branch logic after the response).

4 / 5

Workflow Clarity

The gate sequence (present choices -> stop turn -> read response -> acknowledge -> branch) is clearly sequenced with explicit anti-drift checkpoints; minor gap is the lack of an explicit validate/retry loop beyond 'if unclear, ask again', which keeps it just below 5.

4 / 5

Progressive Disclosure

Well-organized into clear single-level sections (Contract, When/Not, Examples, Anti-Patterns, Output Format) with no bundle files present; the content is appropriately self-contained though the body is somewhat long for a single-file skill.

4 / 5

Total

15

/

20

Passed

Description

58%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 specific and distinct, naming concrete actions and platform coverage, with good trigger-term keywords. Its main weakness is the missing explicit 'Use when...' guidance, leaving the 'when' only weakly implied and capping completeness at 3.

Suggestions

Add an explicit 'Use when...' clause with concrete user-facing trigger phrases (e.g. 'Use when the user presents an ambiguous request, a destructive operation needs confirmation, or a routing decision must be made').

Surface the 2-4 option / escape-hatch contract more directly so the description previews the core rule, not just the high-level pattern.

Include a couple of natural synonyms users would say (confirm, yes/no, pick one) to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names several concrete actions ('presenting the user with explicit choices', 'gating execution until they respond', 'platform-agnostic — works on Telegram, Discord, CLI') with minor gaps in coverage; lacks the full enumerated contract from the body.

4 / 5

Completeness

Clearly states 'what' it does but the 'when' is only weakly implied via 'Used by other skills when a decision point requires human input' — no explicit 'Use when...' clause with concrete user-facing trigger phrases, capping completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Good coverage of natural terms (choice gate, ask before proceeding, user decision, inline buttons); a few common phrasings users might say (confirm, yes/no prompt) are missing.

4 / 5

Distinctiveness Conflict Risk

Carves a distinct niche (choice-gate pattern, used by other skills) with only minor overlap risk against general clarification skills.

4 / 5

Total

15

/

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.

Validation15 / 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
garrytan/gbrain
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.