Contribute To — Testing skill for Claude Code
Join an EXISTING, in-progress work item (issue or PR) as a contributor — walk the contribution loop toward a human-stated goal and success criteria, without the full spec chain.
How to install Contribute To
Installs to ~/.claude/skills/madarauchiha-314-the-loop-contribute-to/SKILL.md
mkdir -p ~/.claude/skills/madarauchiha-314-the-loop-contribute-to && curl -fsSL https://raw.githubusercontent.com/MadaraUchiha-314/the-loop/HEAD/commands/contribute-to.md -o ~/.claude/skills/madarauchiha-314-the-loop-contribute-to/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Contribute To does
description: Join an EXISTING, in-progress work item (issue or PR) as a contributor — walk the contribution loop toward a human-stated goal and success criteria, without the full spec chain. argument-hint: " (e.g. 12 | issue-12 — an item that already has work in progress)" allowed-tools: Read, Write, Edit, Bash, Glob, Grep, Task
the-loop: contribute-to `$ARGUMENTS`
Make a **scoped intervention** in a work item the-loop does not own: an issue or pull request that already ex
Alternatives in Testing
- Debug — You are tasked with helping debug issues during manual testing or implementation 10k ★
- AI Contribution Skills (Engram) — branch-pr: clean branch and PR workflow 2.5k ★
- Add Plugin — Integrate a spec-driven/skill framework as a bundled agtx plugin 1.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Review Queue
Triage pending human-review items — resolve cruft, walk Decisions/Actions/Testing/Deferred Visual buckets, ref
Create Design
Create design.md for a work item from its approved requirements.md (Phase 2 of the spec chain).
Create E2e
Create a Playwright E2E test with explicit success criteria
Define Problem
Define the problem statement, success criteria, and testing strategy through a structured dialogue. Produces .
Spectastic.Spec
Write a feature specification — what to build, for whom, and how success is measured. Use when starting a new
Pharn Loop
Run the PRODUCT pipeline as a BOUNDED, FLOOR-GATED auto-iteration: the same gated chain as /pharn-ship (/pharn
Related Agents
Redteam Commander
Red team engagement lead. Owns research, planning, multi-domain grow-agent dispatch, cross-target synthesis, a
Preflight Runner
Runs design-founder's pre-flight on one backlog item against the project brain (success criteria, principles,
Kimi Pursue
Use this agent ONLY when the user has explicitly asked Kimi to pursue a stated objective AUTONOMOUSLY across m