Tooluck logoTooluck
SKILL.md

loop-library

Agent skill fromForward-Future/loopy

Compatibility alias for Loopy. Use only when an existing installation or older instruction explicitly invokes loop-library; use Loopy for new installations and requests. Provides the same discovery, recommendation, audit, repair, adaptation, guided crafting, bounded execution, run debrief, project loop saving, and publication-preparation workflows.

How to install loop-library

install loop-library
# install the loopy pack with the skills CLI
npx skills add Forward-Future/loopy

# or add only this skill to Claude Code: copy the folder

skills/loop-library/

# into

~/.claude/skills/loop-library/ (all projects)

.claude/skills/loop-library/ (one project)

skills/loop-library/SKILL.md

MITFull file
1# Loop Library (legacy alias)
2
3`loop-library` is the compatibility name for Loopy. Complete the user's request
4with this workflow. Use `loopy`, `$loopy`, or `/loopy` for new installations
5and explicit invocations.
6
7Help the user discover loop opportunities in existing engineering work, reuse a
8published Loop Library loop when one fits, audit or repair an existing loop,
9craft a new one through a focused interview, run it with evidence, learn from
10the result, or prepare it for Loop Library. Treat a loop as a feedback system
11with terminal states, not as permission for endless autonomy.
12
13## Route the request
14
15Choose the smallest useful path:
16
17- **Discover:** Analyze a codebase, coding-thread history, or both for repeated
18 work that can become a bounded loop.
19- **Find:** Recommend one to three published loops for a stated problem.
20- **Audit / Loop Doctor:** Diagnose an existing loop and repair only material
21 weaknesses without changing its intended outcome.
22- **Adapt:** Start from a published loop and replace its thresholds, tools,
23 cadence, owners, or checks without weakening its feedback cycle.
24- **Craft / Guided Design:** Interview the user about the outcome and what
25 success means, then produce a new bounded loop.
26- **Run:** Execute an identified loop within the user's authorized scope and
27 return an evidence-backed run receipt.
28- **Debrief:** Analyze one or more completed run receipts, diagnose what helped
29…

Excerpt shown under the repository's MIT license.

More skills in loopy

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates