loop-engineering skills

b3rys/b3rys-team-os

Skill Claude CodeCodex

Use when adding, testing, disabling, offboarding, or archiving a b3rys team member across Claude Code channel, OpenClaw, Hermes Agent, or future runtimes.

muzafferkadir/nextjs-loop-engineering-starter

Skill Claude CodeCodex

(loop-engineering) Implements exactly one feature from the BACKLOG.md Backlog — syncs main, acquires the loop lock, creates a feature branch, implements all acceptance criteria with tests, visually inspects UI changes, passes the independent verifier, and opens a PR. Use for Build-mode loop runs, or when asked to…

muzafferkadir/nextjs-loop-engineering-starter

Skill Claude CodeCodex

(loop-engineering) Runs the daily Report-mode triage — checks open PRs, CI status and the BACKLOG.md backlog, then updates STATE.md and appends to the run log without writing any code. Use for scheduled daily loop runs, project health checks, or when asked to "triage", "run report mode", or "update the loop state".

muzafferkadir/nextjs-loop-engineering-starter

Skill Claude CodeCodex

(loop-engineering) Visually inspects UI changes by screenshotting routes with pnpm snap and reading the images against a design checklist (layout, spacing, hierarchy, semantic tokens, empty/loading/error states). Use after implementing any UI change, before opening a PR that touches src/app or src/components, or when…

Ruisi-Lu/github-loop-engineering-skill

Skill Claude CodeCodex

Run an evidence-gated Loop Engineering control loop for GitHub Issues and GitHub Projects through the official GitHub MCP Server. Use when an agent needs to discover work state; create, triage, prioritize, assign, split, block, start, finish, close, or verify work items; update project fields; maintain acceptance…

yohey-w/kagemusha

Skill Claude CodeCodex

A procedure for consulting a frontier-class external reasoning model (extended-thinking tier) on a decision that matters — and for accepting its answer afterwards. Generates the consultation prompt, then audits the reply. Vendor-neutral: any top-tier model will do. Not for routine work sent to a cheap model — that is…

yohey-w/kagemusha

Skill Claude CodeCodex

A two-machine live meeting copilot. A Windows laptop streams two audio channels (your mic, and a loopback of the other side's voice) to a parent machine, which transcribes them, drives a teleprompter you read from, watches every incoming utterance against a ledger of pre-agreed facts, and answers off-script questions.…

lunkerchen/loop-engineering-skill

Skill Claude CodeCodex

Loop Engineering framework: design autonomous agent feedback cycles instead of hand-prompting each step.

yangchao228/loop-builder

Skill Claude CodeCodex

A design workbench for turning a vague task into a controlled, repeatable Agent Loop. An Agent Loop is a task process with defined steps, checks, stopping points, and recovery actions.

yangchao228/loop-builder

Skill Claude CodeCodex

A screenshot-driven workflow for rebuilding a webpage or frontend so its rendered appearance matches a supplied visual. It compares screenshots, identifies the largest differences, and repeats the implementation and correction cycle.

tinhtran24/maestro

Skill Claude CodeCodex

Full-cycle delivery method for Maestro sessions — Analysis and Plan when a task is created, then Development and Testing, then a conventionally-named branch and Conventional Commit. Use when planning a task draft or driving a worker task from start to pull request.

tinhtran24/maestro

Skill Claude CodeCodex

Catalog of the Maestro maestro CLI: spawning workers, managing sessions and projects, sending messages, previewing pages, and daemon control. Use when using the to CLI, spawning workers, or managing Maestro sessions in an Maestro workspace.

tinhtran24/maestro

Skill Claude CodeCodex

Triage bugs reported in chat/issues, search for duplicates, file or update GitHub issues with full context, and push fix PRs.

hiphapis/loopcraft

Skill Claude CodeCodex

Onboards loopcraft into a project — scans the repo to detect gate commands, confirms the backlog and rubrics through an interview, then scaffolds the .loop/ structure. Run once per project, or when refreshing the config.

hiphapis/loopcraft

Skill Claude CodeCodex

Traverses the backlog unattended, applying the loop-task cycle (rubric · verifier · gate · Loop-Verified commit) to each item. Invoke only when the user explicitly starts an autonomous batch run — for individual work, use loop-task directly.

hiphapis/loopcraft

Skill Claude CodeCodex

Runs non-trivial implementation/fix work that needs a verifiable output through a rubric + independent verifier grading cycle. Invoke before starting code/docs work. Not for simple questions, exploration, or one-line fixes.

VibeCodingNights/loop-engineering

Skill Claude CodeCodex

Crystallize a one-line objective into a sub-4k GOAL, scaffold a resumable task-hypergraph workspace on disk, and drive it to completion via PARALLEL map->do->review cycles run as Workflow fan-outs, with adversarial review gates, worktree isolation, and honest pass/fail gates. Use when decomposing a repo / refactor /…

MuhammadMustafa18/proteus

Skill Claude CodeCodex

Navigate the Odyseus reference project (parent directory) to study a specific feature, compare it with Proteus, and adapt the implementation. Use when the user asks to check/learn/compare/reference Odyseus for any feature.

encircleacity2/loopath

Skill Claude CodeCodex

Interactive bilingual course skill for learning loop engineering through Loopath. Use when a user wants to start, continue, install, teach, study, verify, or be quizzed on the Loopath course; when they ask for an agent-guided course on coding-agent loops, harness design, AGENTS.md, action schemas, tool use, policy…

DennisWei9898/loop-engineering-reviewer

Skill Claude CodeCodex

A reviewer for automated agent or workflow projects, based on the Loop Engineering rules by Addy Osmani. It checks whether creation and review are separated, whether pass conditions are objective, and whether the loop has limits and human approval points.

alanvaa06/forge-master

Skill Claude CodeCodex

Execute an approved forge-master plan as an autonomous loop. Disk-backed state machine — reads docs/forge/plans/plan-NNN.md, runs phases in dependency order, verifies with the test runner (never opinion), escalates tier/process by deterministic rules, flushes state after every phase so it survives compaction, and ends…

alanvaa06/forge-master

Skill Claude CodeCodex

Decompose an approved PRD into docs/forge/plans/plan-NNN.md — phases tagged tier (junior/senior) and process (light/heavy), each mapped to the ACs it covers, with a proven total-coverage table and an acyclic dependson graph. Reads docs/context/lessons.md so past escalations improve triage. Stops at human approval…

alanvaa06/forge-master

Skill Claude CodeCodex

Interview a user from a raw idea into a testable PRD at docs/forge/prd/NNN-name.md. Every user story gets at least one Given/When/Then acceptance criterion verifiable by test or command. Mandatory Non-Goals. Stable IDs (US-n, AC-n.m). Stops at human approval gate. Use when starting a forge-master run, or when the user…

auron-lmh/data-quality-loop

Skill Claude CodeCodex

A data-quality repair process in which one role proposes database fixes and another independently checks them on a copy before changes are saved.