spec-loop
Turns a raw user story into shipped, reviewed code through a bounded loop — grill it for gaps, write a spec, plan it, split it into small PR-sized tasks…
Going through the checklist
What it does
A user story is not a spec, and a spec is not a plan. This skill is the loop that turns one into the other, then keeps a human at exactly two checkpoints — spec approval and PR review — while everything in between runs as a bounded, observable, adversarially-checked loop instead of turn-by-turn prompting.
Use when a user hands you a feature request, ticket, or user story and no spec/plan exists yet, or when they ask to "plan this properly,"…
You don’t need to name it. Ask for the job in your own words — your AI loads the skill when the request matches.
What it can touch
Includes 1 script
Your AI can run these when the skill is used — on your computer in a coding tool (which asks first unless you have told it not to), or in the AI’s own sandbox in Claude and ChatGPT.
How we know
Found in the skill’s folder: scripts/scaffold.sh.
Lets your AI run any terminal command without asking, while the skill is in use
While the skill is working, Claude Code will not stop to ask before each terminal command. The permission ends when you send your next message.
How we know
SKILL.md line 1: “allowed-tools: Read, Write, Edit, Bash, Grep, Glob, AskUserQuestion, Agent, Workflow”. Read 2026-10-04, commit 1f06b4b.
SKILL.md, line 1 ↗1 smaller thing worth knowing
Adds to your AI's standing instructions file. Usually legitimate — listed so nothing is hidden.
How we know
Adds to your AI's standing instructions file — scripts/scaffold.sh line 39. Read 2026-10-04, commit 1f06b4b.
scripts/scaffold.sh, line 39 ↗No serious risk pattern found
Launch7’s automated check read all 22 text files in this skill and matched none of its serious risk patterns. This is not a guarantee: a check like this can miss new or disguised tricks, and the author can change the files after the check.
How we know
Read 2026-10-04, commit 1f06b4b by pipeline/trust/analyze.py — 40+ patterns for hidden text, prompt injection, downloads that run, credential access and more. It reads; it never runs the skill.
Updated this year
Its repository has had changes recently.
How we know
Last push to aelhady03/spec-loop: 2026-07-04 (92 days before the scan).
Read automatically from the skill’s own files on GitHub on 4 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Partly. Upload it in Claude’s settings — the instructions work; the scripts need the full folder.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
This skill ships 1 script beside its instructions. The download here is the SKILL.md alone — enough for the instructions, not for the parts that run code. Use the command route, or take the full folder from the repository.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end