Loop Forge — Productivity skill for Claude Code
Turn a one-line repetitive task into a reusable, self-guarding slash command (loop-forge).
How to install Loop Forge
Installs to ~/.claude/skills/cavaleiro-ai-claude-forge-loop-forge/SKILL.md
mkdir -p ~/.claude/skills/cavaleiro-ai-claude-forge-loop-forge && curl -fsSL https://raw.githubusercontent.com/cavaleiro-ai/claude-forge/HEAD/commands/loop-forge.md -o ~/.claude/skills/cavaleiro-ai-claude-forge-loop-forge/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Loop Forge does
description: Turn a one-line repetitive task into a reusable, self-guarding slash command (loop-forge) argument-hint: "[one-line description of the task you keep doing by hand]"
/loop-forge
Hand the one-line situation in `$ARGUMENTS` to the **loop-forge** skill and run its 6-stage flow exactly as written in `skills/loop-forge/SKILL.md`:
- Entry — read the situation from
$ARGUMENTS. If empty, ask (in the user's language): "What task do you keep doing by hand? Describe it in
Alternatives in Productivity
- Grow A Product — Workflow recipe — turn a growth goal into a funnel diagnosis, experiment backlog, retention loop, and lifecycl 1.3k ★
- Browser Harness JS — Self-healing browser harness that enables LLMs to complete any task 480 ★
- Chief — CLI that wraps Claude Code in a loop 396 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Autoconst Claude 2D PDF To Priced Boq
Turn a flat 2D construction PDF into a priced Bill of Quantities in Excel. Two-witness cross-check between sch
Verify Loop Skill
A Claude skill that runs a supervised, self-verifying loop on a coding task. The loop is the easy part — verif
Ulw Loop
Self-referential loop that runs a task until Oracle-verified completion (cap 100 iterations).
Gaia Forensics
Turn a GAIA workflow misfire into a redacted, classified, filing-ready bug report in one read-only pass. Self-
Skills Learn From Task
Extract reusable, de-identified lessons from a completed authorized task — what worked, what failed, false pos
Detect Patterns
Analyze tool call history to detect repetitive workflow patterns and propose automations
Related Agents
Bead Polisher
Polishes .beads/beads.jsonl in isolated context. Runs the full polish loop (self-containment, dependencies, te
Slash Command Architect
Use proactively for designing, creating, reviewing, and improving Claude Code slash commands. Specialist for d
Plugin Refactorer
Refactor an existing shotcowboystyle Claude Code workspace repo into a shareable Claude Code plugin. Fetches t