kiro-spec-quick

Quick spec generation with interactive or automatic mode

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

Quality

Content

73%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 strong orchestration skill: concrete commands, exact paths, explicit mode handling, a real validation gate with a feedback loop, and thorough failure recovery. Its main weaknesses are redundancy (repeated per-phase mode blocks, duplicated error handling) and a description that does not match the body's quality.

Suggestions

Factor the per-phase 'Automatic Mode / Interactive Mode' blocks into a single stated rule once, instead of repeating it after every phase.

Merge the 'Important Constraints > Error Handling' block with the 'Safety & Fallback' section to remove the duplicated error guidance.

Specify the sanity-review subagent prompt shape and the exact repair criteria (what counts as a task-plan-local issue) so Phase 4's review loop is fully copy-ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly procedural and lean, but mode handling is restated at every phase ("Automatic Mode: IMMEDIATELY continue... / Interactive Mode: Prompt...") and error handling is duplicated between the 'Important Constraints' section inside <instructions> and the 'Safety & Fallback' section. Fits anchor 3 (mostly efficient but could be tightened); not 4 due to the repeated and duplicated blocks.	3 / 5
Actionability	Gives concrete commands (mkdir -p, date -u ISO timestamp), exact template and output paths, explicit placeholder substitutions, and Skill invocations with flags. Minor gaps: the sanity-review subagent gets an objective but no concrete prompt shape, and the repair step is underspecified. Anchor 4; not 5 because a few steps remain hints rather than copy-ready instructions.	4 / 5
Workflow Clarity	A clearly sequenced 4-phase loop with per-phase progress output, an explicit final sanity-review gate, a repair-once-then-rerun feedback loop, and per-failure recovery suggestions with concrete next commands. Matches anchor 5 (clear sequence, explicit validation, feedback loops for error recovery).	5 / 5
Progressive Disclosure	No bundle files exist; all content lives inline in a ~250-line SKILL.md with well-organized sections, and detail is appropriately externalized to on-disk templates and sibling skills. Minor gaps: the output banners and error-scenario catalog are fully inline and somewhat long. Anchor 4; not 5 because a couple of sections (mode banner text, error catalog) could be split out or trimmed.	4 / 5
	Total	16 / 20 Passed

Description

48%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 concise and names a specific domain, but it is terse to a fault: no concrete actions, no trigger context, and no 'when to use' guidance. It reads as a label rather than a triggerable capability description.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to quickly generate a spec (requirements, design, tasks) from a feature description, or asks to spec out a feature.'

List the concrete outputs and actions, e.g. 'Generates requirements.md, design.md, and tasks.md from a feature description in 4 phases, with a final sanity review.'

Include natural trigger variations such as 'spec', 'requirements', 'design doc', and 'task breakdown' to improve retrieval.

Dimension	Reasoning	Score
Specificity	"Quick spec generation" names the domain and the modes are distinguished, but no concrete actions are listed (no mention of generating requirements, design, or tasks files). Matches anchor 2 (names domain, actions minimal/generic); below 3 because no concrete output actions appear.	2 / 5
Completeness	The 'what' is stated ("Quick spec generation with interactive or automatic mode") but there is no 'when' clause at all — per judging guidelines a missing 'Use when...' caps this at 3. Not 4 because 'when' is not even weakly implied.	3 / 5
Trigger Term Quality	"spec generation", "interactive", "automatic" are natural trigger words in this domain, but common variations users would say ("requirements", "design", "tasks", "spec out a feature") are missing. Fits anchor 3; not 4 because keyword coverage is thin for a multi-artifact skill.	3 / 5
Distinctiveness Conflict Risk	"Spec generation" is a clear niche with distinct triggers; minor overlap risk only with the closely related kiro-spec-* skills it orchestrates. Fits anchor 4; not 5 because the bare phrase 'spec generation' could collide with general spec-writing skills.	4 / 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-quick/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.