kiro-spec-batch

Create complete specs (requirements, design, tasks) for all features in roadmap.md using parallel subagent dispatch by dependency wave.

Quality

73%

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-batch/SKILL.md

Quality

Content

88%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 tightly written, highly actionable orchestration procedure with strong sequencing and validation for a batch operation. Its main gap is structural: the long verbatim subagent prompts are inlined rather than split into reference files.

Suggestions

Move the spec-generation and cross-spec-review subagent prompt templates into reference files (e.g. references/spec-dispatch-prompt.md and references/cross-spec-review-prompt.md), signaling them clearly from the steps.

Trim redundancy between 'Critical Constraints' and the step text by stating each rule once (e.g., wave strictness and parallel dispatch appear in both Step 3 and the constraints).

Dimension	Reasoning	Score
Conciseness	The body is lean and operative — exact paths, prompts, and templates with no explanation of concepts Claude already knows. Minor trimming is possible: 'Critical Constraints' partially restates rules already stated in the execution steps (e.g., wave ordering, parallel dispatch).	4 / 5
Actionability	Fully executable guidance: verbatim subagent prompts with bound arguments and fast-track flags, exact file paths, literal error messages, and copy-ready output templates for the plan and final summary.	5 / 5
Workflow Clarity	A clearly sequenced multi-step process with explicit validation checkpoints: brief.md existence checks up front, per-wave file verification, cross-spec review with a bounded fix loop (max 3 remediation rounds), and explicit failure, circular-dependency, and missing-roadmap fallbacks — strong feedback loops for a batch operation.	5 / 5
Progressive Disclosure	Well-organized sections delegate phase detail to other skills' SKILL.md files one level deep, keeping the controller lightweight. However, the two long inline subagent prompts (spec generation and cross-spec review) are sizable inlined content that could live in reference files for a cleaner overview.	4 / 5
	Total	18 / 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 distinct, clearly stating what the skill does and how, but it lacks any 'when to use' trigger guidance and misses natural keyword variations. Adding a 'Use when...' clause would resolve its main weakness.

Suggestions

Add a 'Use when...' clause, e.g. "Use when the user wants to spec out all features in a roadmap at once, batch-generate specs, or create specifications for multiple features in dependency order."

Include natural synonyms and trigger variations such as "specifications", "generate specs", or "spec out the roadmap" so the description matches how users actually phrase the request.

Mention the downstream artifacts (spec.json, requirements.md, design.md, tasks.md) or the cross-spec consistency check to sharpen what 'complete specs' means.

Dimension	Reasoning	Score
Specificity	The description names concrete deliverables ("specs (requirements, design, tasks)"), the input artifact ("roadmap.md"), and a concrete method ("parallel subagent dispatch by dependency wave") — several specific actions with only minor gaps (e.g., cross-spec consistency review and output file types are not mentioned).	4 / 5
Completeness	The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Relevant keywords like "specs", "requirements, design, tasks", and "roadmap.md" are present, but common natural variations users would say ("specifications", "spec out", "generate specs for", "batch") are missing, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The batch framing ("all features", "parallel subagent dispatch by dependency wave") carves out a mostly distinct niche from single-feature spec skills, though "create specs" overlaps in vocabulary with the kiro-spec-* family.	4 / 5
	Total	14 / 20 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: gotalab/cc-sdd
Path: tools/cc-sdd/templates/agents/claude-code-skills/skills/kiro-spec-batch/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.