kiro-spec-init

Initialize a new specification with detailed project description

Quality

67%

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/claude-code-skills/skills/kiro-spec-init/SKILL.md

Quality

Content

85%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 a well-structured, self-contained instruction skill: a numbered execution sequence with validation checkpoints, explicit placeholder mappings, a clear output contract, and error-recovery fallbacks. Its only weaknesses are minor — a slightly over-specified fallback section and a missing example/format rule for the feature-name generation that sits at the heart of the task.

Dimension	Reasoning	Score
Conciseness	The body is efficient with tight numbered steps and no explanations of concepts Claude already knows; only minor trimmable padding exists in the Safety & Fallback section (e.g., "suggest checking permissions or disk space"), fitting the 'efficient; minor instances of over-explanation' anchor rather than the every-token-earns-its-place level.	4 / 5
Actionability	Guidance is mostly executable: exact template paths, an explicit placeholder-replacement mapping ({{FEATURE_NAME}}, {{TIMESTAMP}}, {{PROJECT_DESCRIPTION}}, {{LANG_CODE}}), and concrete fallback behaviors. It stops short of a 5 because the core step 'Generate a unique feature name from the project description' lacks a format rule or example (kebab-case is only implied by the output section).	4 / 5
Workflow Clarity	A clear 5-step sequence with explicit checkpoints (check for brief, verify naming conflicts, skip-if-exists) plus a Safety & Fallback section giving error-recovery loops for missing templates, name conflicts, and write failures — matching the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.	5 / 5
Progressive Disclosure	The skill is under 50 lines, single-purpose, with no bundle files (no references/, scripts/, or assets/ exist) and no need for external references; sections are well-organized and clearly labeled, which per the rubric's simple-skill guideline earns a 5.	5 / 5
	Total	18 / 20 Passed

Description

50%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 delivers a clear, concise 'what' in third person, but is a single bare action statement: no trigger guidance, no enumeration of the concrete artifacts created, and no synonyms beyond "specification". It reads like a command summary rather than a description designed to help Claude decide when to invoke the skill.

Suggestions

Add an explicit trigger clause, e.g. "Use when starting a new feature spec or when the user asks to initialize/scaffold a specification."

Enumerate the concrete actions so the 'what' is comprehensive: creating the spec directory, generating spec.json and requirements.md from templates, and pre-filling from a discovery brief.

Include natural trigger variations users would say — "spec", "new spec", "feature specification", "requirements" — to improve trigger term quality and distinctiveness from sibling kiro-spec-* skills.

Dimension	Reasoning	Score
Specificity	"Initialize a new specification with detailed project description" names the domain and one concrete action but lists no further specific actions (no mention of the spec directory, spec.json, or requirements.md it creates), matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor.	3 / 5
Completeness	The description has a clear 'what' (initialize a new specification with a detailed project description) but contains no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords exist ("specification", "initialize", "project description") but common natural variations users would say — "spec", "new spec", "feature spec", "requirements" — are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"Specification" is a moderately specific domain, but the generic phrasing "Initialize a new specification" could overlap with other spec-scaffolding or init skills in the same suite (e.g., /kiro-spec-requirements), fitting the 'somewhat specific but could still overlap with similar skills' anchor.	3 / 5
	Total	12 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: tools/cc-sdd/templates/agents/claude-code-skills/skills/kiro-spec-init/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.