CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

kiro-spec-design

Create comprehensive technical design for a specification

Quality

69%

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/codex-skills/skills/kiro-spec-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A well-structured orchestration skill: the 6-step workflow is clearly sequenced with explicit approval and review gates, bounded repair loops, and stop conditions, and the guidance is largely concrete (paths, flags, metadata fields). Its weaknesses are minor — some duplicated load instructions and a couple of abstract spots in the research-dispatch section.

DimensionReasoningScore

Conciseness

The body is dense, imperative instruction with no tutorial padding about concepts Claude already knows; template and rule-file paths are repeated between Steps 1 and 4 and occasional meta-commentary ("Critical: This phase ensures design is based on complete, accurate information.") could be trimmed. Fits anchor 4 ("Efficient; minor instances of over-explanation that could be trimmed"); not 5 due to the duplication and not 3 because the padding is minor.

4 / 5

Actionability

Concrete file paths, flags ($1, $2, -y), JSON metadata fields to set (phase, approvals.design.generated, updated_at), and a feature-type decision table make the guidance mostly executable. Minor gaps keep it from 5: sub-agent decomposition is left abstract ("the agent should decide the optimal decomposition") and "quick pattern check" is vague.

4 / 5

Workflow Clarity

A clear 6-step sequence with explicit validation checkpoints (requirements approval gate in Step 1, design review gate in Step 5) and explicit feedback loops: repair-and-re-review bounded to at most 2 passes, and a stop-and-return-to-requirements path when a real spec gap is found. This matches anchor 5 (clear sequence, explicit validation, feedback loops for error recovery).

5 / 5

Progressive Disclosure

Five rule files (design-principles.md, design-discovery-full.md, design-discovery-light.md, design-synthesis.md, design-review-gate.md) are each clearly signaled with when to read them, one level deep; no bundle files exist to verify beyond these references. The inlined 200-line workflow is the appropriate core content, with minor organization gaps (repeated load instructions, Safety & Fallback detail that could be tightened) keeping it at anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

45%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 names a clear domain and artifact type but stops there: one generic action verb, no "Use when" trigger guidance, and no natural keyword variations. It is serviceable but well below the quality of the reference good examples, which pair concrete action lists with explicit trigger phrases.

Suggestions

Add an explicit trigger clause, e.g. "Use when generating or updating the design.md for an approved Kiro spec, or when the user asks for a technical design or architecture for a specification."

Replace the buzzword "comprehensive" with 2-3 concrete actions, e.g. "Creates the technical design for a specification: runs architecture discovery and research, synthesizes findings, and generates design.md with boundary definitions, file structure plan, and testing strategy."

Include natural keyword variations users would actually say ("design doc", "architecture", "spec design") to improve trigger matching and distinctiveness.

DimensionReasoningScore

Specificity

"Create comprehensive technical design for a specification" names the domain but offers a single generic action — "create" — padded by the buzzword "comprehensive". This matches anchor 2 ("Names the domain but actions are minimal or generic", e.g. "Processes PDF files"); it is not 3 because no second concrete action is listed.

2 / 5

Completeness

It answers "what" (create a technical design) but has no "when" clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines. Not 4 because the "when" is entirely absent rather than merely implicit.

3 / 5

Trigger Term Quality

"technical design" and "specification" are relevant domain keywords, but common natural variations a user would say ("design doc", "architecture", "design spec", "spec") are missing. Fits anchor 3 ("Some relevant keywords but missing common variations"); not 4 since natural phrasing coverage is thin, not 2 since the terms are domain-specific rather than generic.

3 / 5

Distinctiveness Conflict Risk

"for a specification" anchors it to a spec-workflow niche, but it could overlap with other design, architecture, or spec-writing skills. Matches anchor 3 ("Somewhat specific but could still overlap with similar skills"); not 4 because no distinctive trigger terms set it apart from those neighbors.

3 / 5

Total

11

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

gotalab/cc-sdd

Path

tools/cc-sdd/templates/agents/codex-skills/skills/kiro-spec-design/SKILL.md

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.