Menu

#382 by GitHub stars

Forward-Future/loopy

A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

CodexEngineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/loop-library/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

75966cbd572a → 75966cbd572a

Compare on GitHub

skills/loopy/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

75966cbd572a → 75966cbd572a

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 75966cbd572a4185064971c9fe5e9c52e8f8456d

git clone --filter=blob:none --no-checkout https://github.com/Forward-Future/loopy.git .hotskills/forward-future-loopy && git -C .hotskills/forward-future-loopy checkout --detach 75966cbd572a4185064971c9fe5e9c52e8f8456d # Copy each selected skill directory from .hotskills/forward-future-loopy into .agents/skills/<skill-name>/
3.2kGitHub stars
11stars in 7 days
2skills in this repository
0commits in 30 days

Heat

4.5
  • Star growth, last 7 daysAhead of 66% of tracked repositories
  • Star growth, last 24 hoursAhead of 69% of tracked repositories
  • Rank movement, last 7 daysAhead of 38% of tracked repositories
  • Commits, last 30 daysAhead of 0% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 2, 2026Nov 6, 20263,227

Individual skills in this repository

How it works

loop-library

When your agent uses it

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.

What it loads into context

Frontmatter

69 tokens

Always available to the agent

SKILL.md

3,285 tokens

When the skill is activated

Reference documents

3,078 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Route the request
  2. Discover loops from existing work
  3. Find a published loop
  4. Audit and repair a loop
  5. Run a loop
  6. Debrief completed runs
  7. Prepare or publish a loop
  8. Save and reuse project loops
  9. Keep every workflow grounded
  10. Craft a loop through an interview
  11. Design the feedback cycle
  12. Validate every crafted loop
  13. Deliver the loop

Files

  • SKILL.mdcore15,609 bytes
  • SKILL.mdcore15,609 bytes
  • SKILL.mdcore15,609 bytes
  • SKILL.mdcore15,609 bytes
  • SKILL.mdcore15,609 bytes
  • SKILL.mdcore15,609 bytes
  • SKILL.mdcore15,609 bytes
  • agents/openai.yamlasset240 bytes
  • references/audit.mddoc2,742 bytes
  • references/debrief.mddoc1,792 bytes
  • references/discover.mddoc3,872 bytes
  • references/publish.mddoc3,249 bytes
  • references/run.mddoc3,422 bytes
Read SKILL.md

# Loop Library (legacy alias)

`loop-library` is the compatibility name for Loopy. Complete the user's request
with this workflow. Use `loopy`, `$loopy`, or `/loopy` for new installations
and explicit invocations.

Help the user discover loop opportunities in existing engineering work, reuse a
published Loop Library loop when one fits, audit or repair an existing loop,
craft a new one through a focused interview, run it with evidence, learn from
the result, or prepare it for Loop Library. Treat a loop as a feedback system
with terminal states, not as permission for endless autonomy.

## Route the request
View the complete source on GitHub

Skills included

  • loop-library
  • loopy

Repository facts

License
MIT
Created
Jun 12, 2026
Last pushed
Sep 11, 2026
Forks
286
Open issues
2
Project activity
Active

Rank over the last 12 weeks

Now #382 · best #278 · down 59 in 30 days

  1. #372 on Nov 1
  2. #377 on Nov 2
  3. #378 on Nov 3
  4. #377 on Nov 4
  5. #379 on Nov 5
  6. #382 since Nov 6
73 earlier periods
  1. #270 on Aug 2
  2. #274 on Aug 7
  3. #277 on Aug 8
  4. #271 on Aug 9
  5. #281 on Aug 10
  6. #278 from Aug 11 to Aug 12
  7. #282 on Aug 13
  8. #280 on Aug 14
  9. #278 on Aug 15
  10. #284 on Aug 16
  11. #282 on Aug 17
  12. #289 on Aug 18
  13. #287 on Aug 20
  14. #291 on Aug 21
  15. #285 on Aug 22
  16. #291 on Aug 23
  17. #294 on Aug 24
  18. #295 from Aug 25 to Aug 26
  19. #292 on Aug 27
  20. #294 on Aug 28
  21. #293 on Aug 29
  22. #287 on Aug 30
  23. #300 on Sep 1
  24. #297 on Sep 2
  25. #304 on Sep 3
  26. #296 on Sep 4
  27. #294 on Sep 6
  28. #303 on Sep 7
  29. #302 on Sep 8
  30. #303 on Sep 9
  31. #304 on Sep 10
  32. #300 on Sep 11
  33. #304 on Sep 12
  34. #303 on Sep 13
  35. #305 on Sep 14
  36. #307 on Sep 15
  37. #304 on Sep 16
  38. #303 on Sep 17
  39. #304 on Sep 18
  40. #301 on Sep 19
  41. #311 on Sep 20
  42. #309 on Sep 21
  43. #313 on Sep 22
  44. #312 from Sep 24 to Sep 25
  45. #308 on Sep 26
  46. #313 on Sep 27
  47. #320 on Sep 29
  48. #317 on Sep 30
  49. #315 on Oct 1
  50. #318 on Oct 2
  51. #315 on Oct 3
  52. #320 from Oct 5 to Oct 6
  53. #323 on Oct 7
  54. #328 on Oct 8
  55. #333 on Oct 9
  56. #327 on Oct 10
  57. #331 on Oct 11
  58. #340 on Oct 12
  59. #337 on Oct 13
  60. #338 on Oct 14
  61. #337 on Oct 15
  62. #342 on Oct 16
  63. #339 on Oct 17
  64. #344 on Oct 18
  65. #345 on Oct 19
  66. #347 on Oct 20
  67. #349 on Oct 21
  68. #349 on Oct 23
  69. #345 on Oct 24
  70. #358 on Oct 25
  71. #367 on Oct 28
  72. #370 on Oct 29
  73. #373 from Oct 30 to Oct 31

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 2, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 12 notes
  • skills/loop-library/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/loop-library/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/loop-library/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/loop-library/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/loop-library/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/loop-library/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/loopy/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/loopy/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/loopy/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/loopy/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/loopy/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/loopy/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • No broad tool permissions
  • No dangerous shell commands
  • 6 network referencesin 2 files: loop-library/SKILL.md:70 loopy/SKILL.md:66
  • No hidden or obfuscated text
  • No instruction overrides
  • No executable scripts
  • No access to secrets
  • No requests to vote in Hot
Show all 6 signals by file

skills/loop-library/SKILL.md

  • Network accessline 70
    1. When web access is available, read the live    [catalog.md](https://signals.forwardfuture.com/loop-library/catalog.md).
  • Network accessline 71
    [catalog.md](https://signals.forwardfuture.com/loop-library/catalog.md).
  • Network accessline 72
    Use [catalog.json](https://signals.forwardfuture.com/loop-library/catalog.json)

skills/loopy/SKILL.md

  • Network accessline 66
    1. When web access is available, read the live    [catalog.md](https://signals.forwardfuture.com/loop-library/catalog.md).
  • Network accessline 67
    [catalog.md](https://signals.forwardfuture.com/loop-library/catalog.md).
  • Network accessline 68
    Use [catalog.json](https://signals.forwardfuture.com/loop-library/catalog.json)

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Signal confidence: 6 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md skills/loop-library/SKILL.md.claude/skills/<skill-name>/
CodexNativeManifest AGENTS.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/loop-library/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/loop-library/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/loop-library/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/loop-library/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

DenisSergeevitch/agents-best-practices

Use this skill when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral ag…

2.4kGitHub stars

MattMagg/ralph-wiggum-codex

Installable Codex skill for long-running autonomous coding refinement loops with validation and resumable state

12GitHub stars

ComposioHQ/awesome-claude-skills

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

78.9kGitHub stars

majiayu000/spellbook

Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.

290GitHub stars

serejaris/personal-corp-os

Personal Corp OS — управление личной компанией через AI-агентов: задачи вне головы, отделы вместо памяти, недельное ретро. Открытые скиллы для Claude Code и Codex

241GitHub stars

jdrhyne/agent-skills

A collection of AI agent skills for Clawdbot, Claude Code, Codex

240GitHub stars

Add this badge to your README

It updates every night and links to this page.

Forward-Future/loopy: #382 on hotskills, 3.2k stars

[![Forward-Future/loopy on hotskills](https://hotskills.dev/badge/forward-future-loopy.svg)](https://hotskills.dev/skill/forward-future-loopy/)