spec-workflow

Use when medium-to-large changes need explicit requirements, technical design, and task planning before implementation, especially for multi-module work, unclear acceptance criteria, or architecture-heavy requests.

Quality

71%

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 ./plugin/cloudbase/skills/spec-workflow/SKILL.md

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 body is a well-structured, actionable spec workflow with clear phases and confirmation gates. Its main weakness is redundancy across three overlapping trigger/decision sections, and it lacks error-recovery feedback loops.

Suggestions

Consolidate the 'Activation Contract', 'When to use this skill', and 'Decision rule' sections into one trigger/decision block to remove redundancy and recover token budget.

Add an explicit error-recovery feedback loop (e.g., what to do when a phase review fails or acceptance criteria are found to be inconsistent) to strengthen workflow_clarity.

Tighten the per-phase 'What to do' bullet lists into more concrete, prescriptive steps so each phase is copy-paste actionable rather than descriptive.

Dimension	Reasoning	Score
Conciseness	Avoids explaining concepts Claude already knows, but the 'Activation Contract', 'When to use this skill', and 'Decision rule' sections substantially overlap on triggers and decisions, adding redundancy that could be tightened. Not a 4 because the overlap is more than minor.	3 / 5
Actionability	Provides concrete file targets (specs/<spec_name>/requirements.md), an EARS pattern with a worked example, and a copy-pasteable task markdown template; the 'What to do' bullets remain higher-level, a minor gap. Not a 5 because some guidance is still abstract.	4 / 5
Workflow Clarity	Clear four-phase sequence (Requirements, Design, Tasks, Execution) with explicit confirmation checkpoints ('Require confirmation between requirements, design, and task breakdown'). Not a 5 because there are no error-recovery feedback loops.	4 / 5
Progressive Disclosure	Single self-contained file with well-organized headers and clearly signaled sibling-skill references in 'Then also read'; no bundle files exist so no splitting is required. Minor organizational redundancy keeps it just below 5.	4 / 5
	Total	15 / 20 Passed

Description

75%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, trigger-rich, and clearly scoped to spec-driven development for medium-to-large changes. It answers both 'what' and 'when' well, though the 'what' is somewhat implicit and a few natural synonyms are missing.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('explicit requirements, technical design, and task planning') matching the anchor for several specific actions with minor gaps; not a 5 because it omits execution/validation coverage.	4 / 5
Completeness	Explicit 'Use when...' clause with multiple concrete triggers answers 'when' clearly; the 'what' is implied (changes need requirements/design/planning) rather than stated as a direct skill action, so it is not a 5.	4 / 5
Trigger Term Quality	Includes natural trigger phrases ('multi-module work', 'unclear acceptance criteria', 'architecture-heavy requests') but misses common synonyms like 'refactor', 'new feature', or 'design doc'.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (spec-driven planning for medium-to-large changes) with distinct triggers; minor overlap risk with general planning/design skills keeps it just below 5.	4 / 5
	Total	16 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: TencentCloudBase/CloudBase-AI-Toolkit
Path: plugin/cloudbase/skills/spec-workflow/SKILL.md
Commit: ef9f182

Reviewed: 3 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.