CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

63

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./config/.claude/skills/spec-workflow/SKILL.md

The canonical home for this skill is spec-workflow in TencentCloudBase/CloudBase-AI-Toolkit

SKILL.md
Quality
Evals
Security

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 process skill with clear phased sequencing, confirmation gates, and concrete templates. Its main weakness is redundant decision guidance repeated across three sections, which hurts conciseness and organization.

Suggestions

Consolidate the repeated use/skip criteria: the 'Do NOT use for'/'Minimal checklist', 'When to use this skill', and 'Decision rule' sections overlap heavily — merge them into one decision section to remove redundancy.

Add a brief full example of a requirements.md or design.md artifact so the templates have a concrete end-to-end reference, closing the minor actionability gap.

Add an explicit feedback loop for underspecified or failed phases (e.g., 'If acceptance criteria cannot be made explicit, ask clarifying questions and re-draft before proceeding') to push workflow clarity toward 5.

DimensionReasoningScore

Conciseness

The body is mostly efficient and free of beginner-concept padding, but the use/skip criteria are stated three times — 'Do NOT use for'/'Minimal checklist', 'When to use this skill', and 'Decision rule' — creating noticeable redundancy that could be tightened, fitting the 3 anchor rather than the leaner 4.

3 / 5

Actionability

Provides concrete, copy-paste-ready templates (the EARS pattern, an EARS example, and the markdown task format) plus explicit output file paths, giving mostly executable guidance with only minor gaps (no full example requirements.md or design.md).

4 / 5

Workflow Clarity

The four phases are clearly sequenced with explicit confirmation checkpoints ('Get confirmation before moving to the next phase', 'Only start implementation after the user confirms the task plan'), but explicit validate-fix-retry feedback loops are only implicit, capping it at 4 rather than 5.

4 / 5

Progressive Disclosure

Content is well-organized into clear headed sections with one-level-deep, clearly signaled sibling references under 'Then also read'; the duplicated decision guidance is a minor organization gap that keeps it just below the clean-navigation 5.

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, third-person description that explicitly couples concrete 'what' actions with specific 'when' trigger conditions. It is distinctive and well-targeted, with only minor gaps in action coverage and keyword synonyms.

DimensionReasoningScore

Specificity

Names several concrete actions — 'explicit requirements, technical design, and task planning before implementation' — but stops short of comprehensive coverage of the produced artifacts (e.g., user stories, EARS criteria), fitting the 'lists several specific actions; minor gaps' anchor rather than the 5.

4 / 5

Completeness

It opens with an explicit 'Use when...' clause giving concrete triggers (the 'when') and states the 'what' — producing requirements, design, and task planning — clearly answering both questions with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'medium-to-large changes', 'multi-module work', 'unclear acceptance criteria', and 'architecture-heavy requests' give good keyword coverage, but synonyms/common variations are limited, so it does not reach comprehensive 5-level coverage.

4 / 5

Distinctiveness Conflict Risk

The spec-workflow niche (requirements/design/task planning before implementation) is mostly distinct with clear triggers, but the sibling references to ui-design and data-model skills indicate minor overlap risk with closely related skills, matching the 4 anchor rather than a clean 5.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
TencentCloudBase/CloudBase-AI-Toolkit
Reviewed

Table of Contents

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.