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

75%

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.

A well-structured, actionable workflow with clear phases and confirmation checkpoints. The main weakness is redundancy: the when-to-use versus skip guidance is repeated across three sections, which hurts conciseness and organization.

Suggestions

Collapse 'Activation Contract', 'When to use this skill', and 'Decision rule' into a single when-to-use / when-to-skip section to remove the repeated guidance and tighten the body.

Add a brief worked example of a complete EARS acceptance criterion set or a filled tasks.md to lift actionability from schematic templates to copy-paste-ready guidance.

Add an explicit feedback loop for when a phase's artifacts are rejected at a confirmation checkpoint (revise -> re-confirm) to push workflow_clarity to the top anchor.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but the when-to-use guidance is restated across three overlapping sections ('Activation Contract', 'When to use this skill', and 'Decision rule'), which is more than minor padding. It is not a 4 because the redundancy is noticeable rather than trivial, and not a 2 because the content is not heavily padded with concepts Claude already knows.	3 / 5
Actionability	Provides concrete guidance — file paths (specs/<spec_name>/requirements.md), an EARS pattern template with an example, and a markdown task format — giving mostly executable direction. It is not a 5 because the templates are schematic rather than fully worked example artifacts, and not a 3 because the guidance is concrete and specific rather than pseudocode-level.	4 / 5
Workflow Clarity	The four phases are clearly sequenced with explicit confirmation checkpoints ('Only start implementation after the user confirms the task plan', 'Get confirmation before moving to the next phase'). It is not a 5 because there are no explicit error-recovery feedback loops, and not a 3 because the checkpoints are present and explicit rather than implicit.	4 / 5
Progressive Disclosure	Structure is clean with well-organized sections and one-level-deep, clearly signaled references to sibling skills (../ui-design/SKILL.md, ../data-model-creation/SKILL.md); no nested references and no bundle files to misorganize. It is not a 5 because the overlapping when-to-use sections slightly muddy the overview, and not a 3 because references are clearly signaled and content is appropriately placed.	4 / 5
	Total	15 / 20 Passed

Description

83%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.

A strong description that clearly states both what the skill does and when to use it, with concrete trigger phrases and good keyword coverage. Minor gaps in action comprehensiveness and synonym coverage keep specificity and trigger_term_quality just below the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain (medium-to-large changes) and lists several concrete deliverables — 'explicit requirements, technical design, and task planning' — with only minor gaps (no mention of execution/validation artifacts). It is not a 3 because it goes beyond 1-2 actions, and not a 5 because coverage is not fully comprehensive.	4 / 5
Completeness	Explicitly answers both what ('explicit requirements, technical design, and task planning before implementation') and when via a 'Use when...' clause with concrete trigger phrases, matching the anchor for clearly answering both. It is not a 4 because the when-clause is specific with multiple concrete triggers rather than weakly implied.	5 / 5
Trigger Term Quality	Includes natural trigger phrases a user would say — 'multi-module work, unclear acceptance criteria, or architecture-heavy requests' — with good keyword coverage. It is not a 5 because common synonyms like 'spec', 'feature', or 'plan the work' are absent, and not a 3 because the terms present are natural rather than jargon-only.	4 / 5
Distinctiveness Conflict Risk	The spec-workflow niche (requirements/design/task planning for medium-to-large changes) is mostly distinct with clear triggers and only minor overlap with general planning skills. It is not a 5 because the framing could still overlap with broad 'help me plan this change' requests, and not a 3 because the triggers are specific rather than generic.	4 / 5
	Total	17 / 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: f07c33c

Reviewed: 4 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.