kiro-discovery

Entry point for new work. Determines the best action path or work decomposition (update existing spec, create new spec, mixed decomposition, or no spec needed) and refines ideas through structured dialogue.

Quality

61%

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 ./tools/cc-sdd/templates/agents/antigravity-skills/skills/kiro-discovery/SKILL.md

Quality

Content

63%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 well-sequenced, actionable discovery workflow with concrete templates, file paths, and verification steps, but it is longer than necessary due to repeated disk-persistence imperatives and inlines template content that could be externalized. Progressive disclosure is limited by the absence of any reference files.

Suggestions

De-duplicate the 'write files to disk before suggesting the next command' rule — state it once (e.g., in Critical Constraints) and reference it from Step 7 and Safety & Fallback.

Move the brief.md and roadmap.md templates into reference files (e.g., references/brief-template.md) and link to them from Step 7 to improve progressive disclosure and shorten the body.

Add an explicit validation checkpoint in Step 2 (e.g., 'confirm the chosen path against the Step 1 metadata before skipping later steps') so every decision branch has a stated verification step.

Dimension	Reasoning	Score
Conciseness	The body is instruction-dense and avoids explaining concepts Claude already knows, but repeats the 'write files to disk before next command' imperative across Step 7's CRITICAL note, Critical Constraints, and Safety & Fallback, and re-states Path rules in Step 8.	3 / 5
Actionability	Provides concrete file paths ({{KIRO_DIR}}/specs/<feature>/brief.md), copy-paste-ready brief.md and roadmap.md templates, and specific next commands (/kiro-spec-init, /kiro-spec-batch); minor gaps remain in dialogue-style steps that are guidance rather than exact scripts.	4 / 5
Workflow Clarity	Eight steps are clearly sequenced with checkpoints — Step 5 viability sub-agent with revisit loop, user confirmation before proceeding, and Step 7 'verify the files exist by reading them back' — though validation is implicit in a few decision-path steps.	4 / 5
Progressive Disclosure	No bundle files exist and all content (including the full brief.md and roadmap.md templates) is inlined in a single ~250-line SKILL.md; the file is well-sectioned but content that could live in separate template references is not split out.	3 / 5
	Total	14 / 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 third-person with concrete enumerated actions, but lacks an explicit 'Use when...' trigger clause and leans on technical jargon over natural user phrasings. Distinctiveness is reasonably strong within its spec-discovery niche.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g., 'Use when starting new feature work, decomposing a large request, or deciding whether a spec is needed').

Include user-natural synonyms like 'new feature', 'break down this work', or 'do I need a spec?' alongside the technical 'action path'/'decomposition' terms.

Tighten the four-path enumeration into the trigger clause so the 'when' is as concrete as the 'what'.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Determines the best action path or work decomposition', 'refines ideas through structured dialogue') and enumerates four specific path types, giving specific capability coverage with minor gaps.	4 / 5
Completeness	It clearly states what the skill does, but provides no explicit 'when to use it' / 'Use when...' clause; per the rubric a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant domain keywords ('action path', 'work decomposition', 'spec', 'structured dialogue') but these lean technical; common natural user phrasings ('new feature', 'break this down') and an explicit 'Use when...' trigger are missing.	3 / 5
Distinctiveness Conflict Risk	'Entry point for new work' with spec/decomposition framing carves a mostly distinct niche, though it could overlap with sibling kiro spec-creation skills, giving minor conflict risk.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gotalab/cc-sdd
Path: tools/cc-sdd/templates/agents/antigravity-skills/skills/kiro-discovery/SKILL.md
Commit: e2a0c67

Reviewed: 5 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.