spec-loop-clarify-task

Engage the User to resolve important open decisions in Spec Loop work, including tasks, plans, design updates, work breakdowns, implementation checkpoints, and ADR drafting. Use when the user asks to clarify, compare options, discuss criteria, or stress-test, or when different answers could materially change scope, behavior, policy, constraints, route, Design, Test specification, or ADR content. Provides mandatory decision screening for workflows that require it before dependent Spec Loop content is written or revised. Also use for general grilling when explicitly selected.

Quality

92%

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

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with exact templates, a well-sequenced decision tree, validation steps, and a clear exit checklist. Its main weakness is verbosity and repetition, plus all content is inline with no progressive split, leaving conciseness and progressive disclosure short of the top anchor.

Suggestions

Consolidate the repeated 'important open decision' definition and the alternatives-format rules into one section to reduce redundancy and trim length.

Move the detailed per-section ADR/task storage rules and the fixed clarification-effort template into a referenced file (e.g., references/clarification-templates.md) so SKILL.md stays a lean overview.

The 'Decision screening outcomes' list restates conditions already covered by the decision tree; summarize and cross-reference instead of repeating.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes competence (no explaining of basic concepts), but at ~400 lines it repeats and elaborates several rules (e.g., the important-open-decision definition appears in both intro and 'Mandatory decision screening', and the alternatives format is restated with validation), so it could be tightened.	2 / 3
Actionability	Gives concrete, copy-paste-ready templates with exact shapes: 'Decision: <brief answer> (<N>%)', 'Recorded: <choice>', and a fixed clarification-effort question template, plus precise per-section storage rules — fully executable instruction-only guidance.	3 / 3
Workflow Clarity	The decision tree is a clearly numbered, sequenced process with an explicit validation checkpoint ('Before sending any response containing Options:, validate that ...') and a four-condition Exit checklist, matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	There are no bundle directories and references are only sibling-skill links one level deep (well-signaled), which is fine; however all substantive content is inline in one large SKILL.md rather than split, so it is not maximally structured for navigation.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 strong: it states concrete capabilities, gives explicit 'Use when' triggers with natural user phrasing, answers both what and when, and carves a distinct Spec Loop niche. It is detailed but not padded.

Dimension	Reasoning	Score
Specificity	Names many concrete actions across the Spec Loop domain — 'resolve important open decisions', 'compare options, discuss criteria, or stress-test', 'decision screening ... before dependent Spec Loop content is written or revised', 'ADR drafting' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (resolve open decisions, decision screening) and when via a clear 'Use when the user asks to clarify, compare options, discuss criteria, or stress-test, or when different answers could materially change ...' trigger clause, satisfying the 'clearly answers both what AND when' anchor.	3 / 3
Trigger Term Quality	Covers natural user phrasing the skill itself enumerates ('clarify, compare options, discuss criteria, or stress-test', 'general grilling'), giving good coverage of terms a user would actually say; not jargon-only.	3 / 3
Distinctiveness Conflict Risk	Scoped to 'Spec Loop work' with niche-specific triggers (ADR content, work breakdowns, decision screening) and an explicit 'Prefer this skill over a generic grill-me variant' framing, making it unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 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
relative_links	Relative link issues: 8 suspicious	Warning

	Total	15 / 16 Passed

Repository: dpolivaev/spec-loop
Path: skills/spec-loop-clarify-task/SKILL.md
Commit: 741f932

Reviewed: 4 days ago

Table of Contents

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.