repo
01Skill Claude Code
General repository hygiene and environment tools — audits, cleanup, branch/worktree pruning, link checking, and cloud dev sessions.
not rated 73
changed 2d ago F ✓ AI review 25 tokens
original MIT
73Stars on the repository
172Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
squad
02Skill Claude CodeCodex
Collaborate in a local Squad room with Claude, Codex, and human teammates. Use to join live collaboration, manage shared goals or research nodes (Science Cards), coordinate distinct workers, run steward checks, or reset the room.
not rated 73
changed 5d ago A 49 tokens
original MIT
Skill Claude Code needs its repo
Identifies improvement opportunities and creates proposals.
not rated 73
changed 26d ago A 11 tokens
original MIT
loom-auditor
04Skill Claude CodeCodex needs its repo
Verifies claims made by other agents against runtime reality by building and testing software.
not rated 73
changed 26d ago A 20 tokens
original MIT
Skill Claude CodeCodex needs its repo
This document covers complexity assessment, issue decomposition, and scope management for the Builder role. For the core builder workflow, see builder.md.
not rated 73
changed 25d ago A 34 tokens
original MIT
Skill Claude CodeCodex needs its repo
This document covers PR creation, test output handling, and quality requirements for the Builder role. For the core builder workflow, see builder.md.
not rated 73
changed 13d ago A 33 tokens
original MIT
Skill Claude Code
Human avatar for final decisions - promotes quality issues to approved status AND auto-merges Judge-approved PRs that meet safety criteria.
not rated 73
changed 8d ago A 28 tokens
original MIT
Skill Claude CodeCodex
Single canonical copy; role prompts' short pointers refer here.
not rated 73
changed 1mo ago A 19 tokens
original MIT
loom-curator
09Skill Claude Code needs its repo
Enhances approved issues and prepares them for implementation.
not rated 73
changed 2d ago A 13 tokens
original MIT
loom-doctor
10Skill Claude Code needs its repo
Addresses review feedback on PRs labeled loom:changes-requested.
not rated 73
changed 6d ago A 16 tokens
original MIT
loom-driver
11Skill Claude CodeCodex
Standard shell environment with no specialized role.
not rated 73
changed 26d ago A 10 tokens
original MIT
loom-guide
12Skill Claude CodeCodex needs its repo
Keeps the backlog healthy: tier labels, orphan verification, unblocking, epic tracking, living docs.
not rated 73
changed 2d ago A 23 tokens
original MIT
Skill Claude CodeCodex needs its repo
This file contains detailed patterns, examples, and reference scripts for the Hermit role. It is meant to be consulted when needed, not loaded as primary instructions.
not rated 73
changed 26d ago A 38 tokens
original MIT
loom-hermit
14Skill Claude CodeCodex needs its repo
Identifies and proposes removal of unnecessary complexity, bloat, and over-engineering.
not rated 73
changed 2d ago A 20 tokens
original MIT
Skill Claude CodeCodex needs its repo
Detailed reference material for the Judge role, split out of judge.md (the largest prompt in the repo) to keep the main workflow scannable — mirroring how champion.md references champion-reference.md / champion-common.md.
not rated 73
changed 22d ago C 59 tokens
original MIT
loom-judge
16Skill Claude Code needs its repo
Reviews PRs labeled loom:review-requested.
not rated 73
changed 3d ago B 13 tokens
original MIT
loom-loom
17Skill Claude CodeCodex needs its repo
Tier 2 daemon-mode operator surface: observes the running Rust loom-daemon via MCP tools and dispatches sweeps for multi-account autonomous batches.
not rated 73
changed 23d ago B 32 tokens
original MIT
Skill Claude CodeCodex
Loom uses an intelligent probe system to detect what's running in each terminal. When you receive a probe command, respond according to this protocol.
not rated 73 yesterday A 34 tokens
original MIT
Skill Claude CodeCodex
Load when: you are about to run (or just ran) a local cargo build/cargo test/cargo run whose result will inform a verdict — a Judge approval or rejection, a Doctor "the fix works", or a Builder "tests pass" before opening a PR.
not rated 73
changed 27d ago C 70 tokens
original MIT
Skill Claude CodeCodex
Why curator.md's per-issue recipes are REST, and what is still unmeasured.
not rated 73 yesterday A 29 tokens
original MIT
Skill Claude CodeCodex
Load when: loom-daemon forge wait-checks printed LOOM-CHECKS-ERROR naming an HTTP 401/403/429, it left a stderr note about legacy commit statuses, or a job needs a re-run (cancelled by a runner shutdown, or flaky).
not rated 73 yesterday A 73 tokens
original MIT
Skill Claude CodeCodex
For every issue you actually curate or re-curate, write exactly one concrete, standalone comment in the current issue body (replace its previous estimate).
not rated 73
changed 24d ago A 35 tokens
original MIT
Skill Claude CodeCodex needs its repo
Load when: loom-daemon forge wait-checks printed LOOM-CHECKS-RED, or post-verdict.sh … approved exited 6, and a CI-failing verdict is next.
not rated 73
changed 8d ago A 52 tokens
original MIT
Skill Claude CodeCodex
Load when: you are working a PR that carries loom:merge-conflict and a trusted head= --> comment, in a repository where loom-daemon branch-update strategy answers merge.
not rated 73 yesterday A 65 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: