Name: spec-to-repo
Rating: 69.6 (1 reviews)
Author: alirezarezvani

spec-to-repo

Use when the user says 'build me an app', 'create a project from this spec', 'scaffold a new repo', 'generate a starter', 'turn this idea into code', 'bootstrap a project', 'I have requirements and need a codebase', or provides a natural-language project specification and expects a complete, runnable repository. Stack-agnostic: Next.js, FastAPI, Rails, Go, Rust, Flutter, and more.

Quality

85%

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

The canonical home for this skill is spec-to-repo in alirezarezvani/claude-skills

Quality

Content

85%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 highly actionable with a clear, well-validated workflow and mostly efficient prose. The main weakness is progressive disclosure: it points to references and scripts that are not present in the bundle, breaking the navigation it signals.

Suggestions

Ship the referenced bundle files (references/stack-templates.md and scripts/validate_project.py) so the signaled one-level-deep navigation resolves, or remove the references if they are not part of the bundle.

Tighten the Validation Script section to avoid restating the Phase 4 checklist, pointing to the script instead of duplicating its checks.

Consider condensing the three full example file trees into one detailed example plus briefer ones to reduce token weight in the Examples section.

Dimension	Reasoning	Score
Conciseness	Mostly lean with terse tables, explicit rules, and no padding of concepts Claude already knows, though the validation-script section reiterates the Phase 4 checklist and the Examples section is lengthy, leaving minor instances that could be trimmed rather than a fully lean anchor-5.	4 / 5
Actionability	Fully executable guidance — concrete file trees, explicit rules ('No // TODO: implement or pass'), an ordered file-generation sequence, a validation checklist, and real CLI commands for validate_project.py — covering common cases copy-paste ready.	5 / 5
Workflow Clarity	Clear four-phase sequence with explicit validation checkpoints: an interpretation confirmation in Phase 1, a full validation checklist and script run in Phase 4, and a user feedback loop after MVP in Progressive Enhancement, matching the anchor-5 example.	5 / 5
Progressive Disclosure	The body is well-organized with one-level-deep references (references/stack-templates.md, scripts/validate_project.py, cross-referenced skills), but those bundle files do not actually exist, so the signaled navigation leads to missing targets rather than a clean split, fitting anchor 3.	3 / 5
	Total	17 / 20 Passed

Description

86%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 strong on triggers and completeness, with a comprehensive set of natural user phrases and an explicit Use-when clause. It is somewhat thinner on enumerated concrete capabilities, which keeps specificity at the midpoint-anchor level.

Suggestions

Add one or two more concrete capability actions (e.g., 'designs the file tree, generates real working code, configures CI and env files') to lift specificity from anchor 3 toward 4-5.

Consider trimming the long quoted trigger list slightly and folding a couple of phrases into a tighter sentence to reduce length without losing coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and the core concrete action ('expects a complete, runnable repository') plus a stack list, but the capability surface is essentially a single action rather than multiple distinct actions, fitting anchor 3 better than 4.	3 / 5
Completeness	Explicitly answers both 'what' (turns a natural-language spec into a complete, runnable repository) and 'when' ('Use when the user says...') with concrete trigger phrases, matching the anchor-5 example.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases — 'build me an app', 'create a project from this spec', 'scaffold a new repo', 'bootstrap a project', 'turn this idea into code' — are exactly what users say, matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	A clear niche (spec-to-repo generation) with distinct, specific triggers and minimal conflict risk, though there is minor overlap risk with general scaffolding skills, placing it just below the minimal-conflict anchor.	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
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	15 / 16 Passed

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

Reviewed: ~4 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.