CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

55

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./tools/cc-sdd/templates/agents/claude-code-skills/skills/kiro-discovery/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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, example prompts, and validation checkpoints. Its main weakness is redundancy around the file-persistence theme and an opportunity to externalize the large templates for better progressive disclosure.

Suggestions

Consolidate the repeated file-persistence and re-entry guidance into a single canonical section to remove duplication across Step 7, Critical Constraints, and Safety & Fallback.

Move the full brief.md and roadmap.md templates into reference files (e.g., references/brief-template.md) and link to them, reducing inline bulk.

Add a brief 'When to skip this skill' callout so Path A/B quick exits are visible before the reader dives into the deep context loading.

DimensionReasoningScore

Conciseness

The body is mostly efficient process guidance, but the 'files on disk are the source of continuity' theme and re-entry handling recur across Step 7, Critical Constraints, and Safety & Fallback, adding avoidable repetition.

3 / 5

Actionability

Provides concrete Glob patterns, copy-pasteable brief.md and roadmap.md templates, an explicit clarifying-question list, and example subagent prompts, with only minor templated-path gaps.

4 / 5

Workflow Clarity

An explicit 8-step sequence with decision paths A-E includes a viability-check feedback loop (Step 5) and a 'verify the files exist by reading them back' checkpoint (Step 7), with only minor validation gaps elsewhere.

4 / 5

Progressive Disclosure

Well-organized into clearly headed steps, but ~250 lines are entirely inline with no external references and the large brief.md/roadmap.md templates could plausibly be split into reference files.

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 clearly conveys what the skill does and enumerates concrete action paths, giving it solid specificity and distinctiveness. It is held back by an absent explicit 'Use when...' trigger clause and jargon-heavy language that weakens natural trigger-term coverage.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrases (e.g., 'Use when starting new feature work, planning a new spec, or decomposing a large request').

Soften jargon by adding user-facing synonyms alongside 'spec' and 'decomposition' (e.g., 'feature', 'work breakdown', 'planning').

Tighten the generic closer 'refines ideas through structured dialogue' into a more concrete capability statement.

DimensionReasoningScore

Specificity

Names the discovery/spec domain and several concrete actions including the four enumerated action paths (update existing spec, create new spec, mixed decomposition, no spec needed), with only minor gaps such as the generic 'refines ideas through structured dialogue'.

4 / 5

Completeness

Has a clear 'what' (determines action path/work decomposition, refines ideas) but the 'when' is only weakly implied via 'Entry point for new work' with no explicit trigger clause, which caps completeness at 3.

3 / 5

Trigger Term Quality

Contains 'new work', 'idea', 'spec', and 'decomposition' but is jargon-heavy and lacks the natural trigger phrasing ('Use when...') a user would say, missing common variations.

3 / 5

Distinctiveness Conflict Risk

The spec/decomposition workflow niche is mostly distinct with minimal conflict risk, though the broad 'Entry point for new work' opener could overlap with other planning skills.

4 / 5

Total

14

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
gotalab/cc-sdd
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.