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

76%

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

77%

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 clear, actionable, well-sequenced planning workflow with strong templates and explicit confirmation checkpoints. Its main weakness is redundancy across the usage/decision sections and the absence of bundled progressive-disclosure reference files.

Suggestions

Collapse the overlapping 'Activation Contract', 'When to use this skill', and 'Decision rule' sections into a single decision/usage block to remove triplicated criteria.

Move the 'Standalone Install Note' and detailed sibling-skill fallback URLs into a separate references file to keep SKILL.md a lean overview.

Consider extracting the per-phase templates (EARS pattern, task format) into a bundled reference document linked from a concise overview.

DimensionReasoningScore

Conciseness

Individual sections are lean and assume Claude's competence, but the decision/usage criteria are restated three times (Activation Contract, 'When to use this skill', and 'Decision rule') and the Standalone Install Note is operational boilerplate.

2 / 3

Actionability

Provides concrete artifact paths, a usable EARS pattern with a worked example, a copy-ready task markdown template, and an explicit output-expectations mapping — actionable for a process skill.

3 / 3

Workflow Clarity

Four phases are explicitly sequenced with confirmation checkpoints ('Only start implementation after the user confirms the task plan') and a feedback loop requiring confirmation between phases.

3 / 3

Progressive Disclosure

No bundle reference files exist and there is no nested reference chain, but inline duplicated usage/decision content should be split out and sibling-skill references are external pointers rather than cleanly bundled one-level-deep material.

2 / 3

Total

10

/

12

Passed

Description

75%

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 well-structured with an explicit 'Use when' trigger covering both what and when, and occupies a distinct niche. It is slightly held back by planning-jargon triggers and abstract rather than concrete enumerated actions.

Suggestions

Add concrete user-facing trigger phrasings such as 'new feature', 'redesign', or 'cross-module refactor' alongside the planning terminology.

Enumerate specific deliverables the skill produces (e.g., 'produce requirements.md, design.md, and tasks.md') to make the actions more concrete.

DimensionReasoningScore

Specificity

Names the planning domain and concrete activities ('explicit requirements, technical design, and task planning'), but these are abstract planning verbs rather than a list of multiple specific concrete deliverable actions.

2 / 3

Completeness

Explicitly answers both what (requirements, technical design, task planning) and when via a clear 'Use when...' clause with concrete triggering conditions.

3 / 3

Trigger Term Quality

Includes relevant triggers ('multi-module work', 'architecture-heavy requests', 'unclear acceptance criteria') but leans technical/planning jargon and misses common user phrasings like 'new feature', 'redesign', or 'refactor'.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (spec/planning-before-code) with distinct triggers tied to change size and architecture, making it unlikely to fire for the wrong skill.

3 / 3

Total

10

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

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.