Name: spec-driven-workflow
Rating: 60.8 (1 reviews)
Author: alirezarezvani

spec-driven-workflow

Use when the user asks to write specs before code, define acceptance criteria, plan features before implementation, generate tests from specifications, or follow spec-first development practices.

Quality

72%

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 ./.gemini/skills/spec-driven-workflow/SKILL.md

The canonical home for this skill is spec-driven-workflow in alirezarezvani/claude-skills

Quality

Content

70%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 delivers a well-sequenced, validation-rich workflow with concrete commands and formats. Its weaknesses are motivational padding that inflates length and a progressive-disclosure structure that points to bundle files which are not actually present.

Suggestions

Add the missing referenced files under references/ (spec_format_guide.md, acceptance_criteria_patterns.md, bounded_autonomy_rules.md) and the scripts under scripts/ (spec_generator.py, spec_validator.py, test_extractor.py), or remove the dangling references.

Trim the "Why Spec-First Matters" and "Iron Law" advocacy sections to a one-line rationale so the skill stays focused on execution guidance.

Move the large Tools table and command examples into a single condensed section to reduce duplicate mentions of the validator/extractor commands.

Dimension	Reasoning	Score
Conciseness	The core phases and tables are efficient, but advocacy sections like "Why Spec-First Matters" and the dramatic "Iron Law" block are motivational padding that does not help Claude execute and could be trimmed.	3 / 5
Actionability	Concrete, copy-paste-ready commands (e.g., `python spec_validator.py --file spec.md --strict`) and specific formats (RFC 2119, Given/When/Then) dominate, with only the minor gap that the referenced scripts are not bundled.	4 / 5
Workflow Clarity	Six numbered phases each with a Goal, steps, and Exit criteria, plus explicit validation in Phase 3, a Self-Review Checklist, and feedback loops ("If you discover a missing requirement, STOP and update the spec first").	5 / 5
Progressive Disclosure	References are clearly signaled as one-level-deep links, but the referenced files (references/spec_format_guide.md, acceptance_criteria_patterns.md, bounded_autonomy_rules.md) and scripts (spec_validator.py, test_extractor.py, spec_generator.py) do not exist in the bundle, so navigation is broken.	3 / 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 leads with explicit, natural trigger phrases and names several concrete actions, giving it strong completeness and specificity. Its main weakness is the absence of a clean declarative "what this skill does" sentence before the triggers.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("write specs before code, define acceptance criteria, plan features before implementation, generate tests from specifications") rather than vague language, though they are framed as triggers rather than declared capabilities.	4 / 5
Completeness	Explicit "Use when..." trigger guidance is present and the "what" is conveyed through the listed actions, but there is no standalone declarative capability statement preceding the triggers.	4 / 5
Trigger Term Quality	Good coverage of natural phrases users would say ("write specs before code", "plan features before implementation", "spec-first development practices"), though a few common synonyms (e.g., "requirements", "acceptance testing") are absent.	4 / 5
Distinctiveness Conflict Risk	Spec-first triggers are mostly distinct with only minor overlap risk against closely related skills (TDD guide, requirements gathering), which the body itself cross-references.	4 / 5
	Total	16 / 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
relative_links	Relative link issues: 3 missing	Warning
referenced_paths_exist	Referenced path issues: 7 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/spec-driven-workflow/SKILL.md
Commit: 19392f7

Reviewed: ~6 hours 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.