Results for “loop”

やりたいことを1行で言うと、B 型 loop engineering の 7 要素 (context / feedback / verification gate / termination / error handling / state / cost guard) を埋めた loop spec をコピペ可能な形で生成する。生成した spec は現行 Claude Code の実行プリミティブ (Workflow ツール / /loop skill / ralph-loop plugin / claude -p) に落とせる骨格になる (旧 `claude --goal` は廃止)。10 件 failure mode (F1-F10) の対策フックも自動挿入。Hybrid モード: 1 行入力 → デフォルト埋めで一発出力 → 「ここを調整したい」場所だけ短く聞き直す。Use when ユーザーが「loop を作りたい / loop-design / 自走ループ書いて / Workflow 用の spec 作って / 7 要素埋めて / verification gate ありで」と言ったとき、または `/loop-design` を実行したとき。Loop engineering の理論背景は Cards/loop-engineering-autonomous-agents、失敗モード対策は Cards/loop-failure-modes-mechanism-2026 を参照。

The English summary is being prepared. Showing the original description.

Set up Loop Engineering through a single command-line tool, choosing a workflow pattern and agent tool. Start in report-only mode, check setup health and readiness, and provide next actions and first-run instructions.

• Introducing a daily issue and priority review workflow
• Setting up workflows for stalled pull requests or failing CI
• Checking the health of an existing Loop Engineering setup

Run a prompt immediately, then repeat it on a fixed schedule or when another check is useful. Use it to follow builds and pull requests, work through a task file, and list or cancel scheduled jobs.

• Check build status at regular intervals
• Follow up on a pull request
• Work through tasks stored in loop.md

Design or review repeating agent workflows with machine-checkable goals, protected boundaries, independent verification, and retry limits. It helps identify endless retries, manipulated checks, and incorrect completion while keeping final judgment with a human.

• Define completion criteria for repeating agent tasks
• Review loops for endless retries and manipulated checks
• Separate planning, building, and independent verification

Guides LoopX project setup and repair, including goal configuration, shared registry synchronization, stale dashboard status, and command-line routing issues. It distinguishes project lifecycle maintenance from ordinary task execution and directs each operation to its relevant procedure.

• Connecting a project and configuring its goal
• Repairing stale dashboard status
• Diagnosing registry and history routing mismatches

Expert in designing and optimizing growth loops - self-reinforcing systems where the output of one cycle becomes the input for the next. Covers viral loops, content loops, paid loops, sales loops, and product loops. Knows how to identify, measure, and accelerate the specific loop mechanics that drive sustainable growth. Use when "growth loop, viral loop, content loop, flywheel, compounding growth, acquisition loop, referral loop, " mentioned.

The English summary is being prepared. Showing the original description.

Register lasting project documents in a connected LoopX project's document registry, using metadata that conceals private details. This helps future agents locate relevant designs, research notes, procedures, and other project materials.

• Registering design documents and wiki references
• Keeping research notes and papers discoverable
• Recording procedures and migration reports

Investigate unexpected LoopX behavior, such as stalled progress or conflicting next steps. Identify whether agent decisions, state reporting, or workflow rules caused the problem, then repair, validate, and record the correction.

• Investigating tasks that make unexpectedly little progress
• Resolving stale or contradictory next-step recommendations
• Correcting task priorities and missing follow-up work

Decide whether a LoopX pull request is ready for approval or merge by checking review evidence for the current commit, required validation, and owner authorization. Record the decision and its supporting checks on the pull request.

• Check whether a pull request is ready to merge
• Verify authority for merging your own pull request
• Record validation results and reasons for holding a merge

Use only after explicit Codex `$superloopy:superloopy-research` or Claude Code `/superloopy:superloopy-research` invocation, a research task started with a leading `loopy` or `루피` (such as `loopy research`), or an active Superloopy loop explicitly routing a research deliverable here. Evidence-backed Superloopy research orchestration with automatic advisory usage targets, parallel read-only lanes, per-retrieval verdicts, graded and dated sources, empirical verification, a priced claim ledger, cited synthesis, and optional reports. Do not activate from research, investigate, look-up, summarize, deep-dive, report, or similar vocabulary alone, in any language; ordinary questions, debugging, and implementation context-gathering stay with their primary workflows.

The English summary is being prepared. Showing the original description.

Cancel an active PUA loop from Codex CLI using an alias for the corresponding Claude Code command. The workflow cleans loop state and worktree references, records the cancellation, and requires execution evidence before claiming completion.

• Stopping an active PUA loop
• Cleaning loop state and worktree references during cancellation
• Recording cancellation and checking execution evidence

Guide role-specific work in LoopX auto-research, from defining research conditions and proposing hypotheses to experiments, evaluation, and adoption or retirement decisions. Keep evidence, failed attempts, task handoffs, and stopping conditions tied to each worker’s assigned role.

• Define research objectives, metrics, and editable scope
• Record hypotheses and unsuccessful research directions
• Run a selected experiment and capture evidence

Discover, find, compare, audit, repair, adapt, craft, run, debrief, save, and prepare repeatable AI-agent loops for publication. Use when a user asks to analyze code or coding threads for recurring work, find a published loop, interview them to turn a goal into a bounded loop, review a loop for weak checks or unsafe authority, execute a loop with an evidence receipt, learn from completed runs, save or reuse a project loop, or validate and submit a loop to Loop Library.

The English summary is being prepared. Showing the original description.

Use only after explicit Codex `$superloopy:superloopy-research` or Claude Code `/superloopy:superloopy-research` invocation, a research task started with a leading `loopy` or `루피` (such as `loopy research`), or an active Superloopy loop explicitly routing a research deliverable here. Evidence-backed Superloopy research orchestration with automatic advisory usage targets, parallel read-only lanes, per-retrieval verdicts, graded and dated sources, empirical verification, a priced claim ledger, cited synthesis, and optional reports. Do not activate from research, investigate, look-up, summarize, deep-dive, report, or similar vocabulary alone, in any language; ordinary questions, debugging, and implementation context-gathering stay with their primary workflows.

The English summary is being prepared. Showing the original description.

Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them. Use when the user wants to design, build, or set up an agent loop, iterative agent workflow, self-review loop, LLM-as-judge loop, multi-model council, reviewer/judge gate, or goal-driven looping process. Guides goal refinement, typed verification criteria, reviewer/judge selection, privacy boundaries, termination guards, and observability, then emits a RUN_IN_SESSION.md handoff prompt plus portable loop.yaml, loop.resolved.json, LOOP.md, and run-loop.py.

The English summary is being prepared. Showing the original description.

Set up or run repeated verification in Codex with explicit checking commands and stopping conditions. This alias corresponds to Claude Code’s `/pua:loop` command and requires command output as evidence before reporting completion.

• Setting up repeated verification
• Defining verification commands
• Specifying when verification should stop

Reviews authorized LoopX goals, tasks, and deliveries to explain project progress and identify decisions the owner needs to make. It also guides handoffs to suitable agents while preserving the original objective, constraints, and evidence.

• Summarizing progress across active projects
• Identifying decisions that need the owner's input
• Handing work to a suitable agent

Review pull requests at a specific commit using existing discussions, review plans, and executed checks. Produce a detailed Chinese review and a concise English verdict, then publish and read back the result to confirm its contents.

• Review a named pull request at a specific commit
• Review a queue filtered by state or time period
• Audit changes against maintainer guidance

Guides LoopX benchmark experiments through benchmark-toolkit, covering run management, comparisons under matched conditions, and analysis of agent action histories. It helps explain outcomes and efficiency while tracking source versions, score validity, and evidence boundaries.

• Planning and managing benchmark runs
• Comparing baselines and treatments under matched conditions
• Diagnosing outcomes and efficiency from agent action histories

Review the exact final set of changes for a LoopX goal, checking reuse, simplification, concrete risks, and project validations. Record and verify a quality receipt, a review record tied to those specific changes.

• Reviewing final changes before delivery or merge
• Checking reuse and opportunities to simplify code
• Recording validation results and concrete quality risks

Track multiple pull requests or merge requests across repositories with LoopX. Reconcile meaningful status changes, preserve requirement priorities and dependencies, and maintain a roadmap with one shared monitor for the whole delivery program.

• Inventory PRs and MRs across repositories
• Order pending work by requirements and dependencies
• Update completed and pending work in a roadmap

When you want to set up an agent loop, cron-scheduled task, or recurring workflow that runs autonomously. Judgment layer on top of Claude Code's ScheduleWakeup, CronCreate, and /loop — or, on other hosts, cron/GitHub Actions plus a headless agent CLI. Picks dynamic pacing, fixed cron, or a one-shot loop; designs idempotent loop bodies; sets bail-out conditions so loops don't run forever. Examples — weekly review pulse, daily brief, hourly metric monitor, periodic vault compile, upstream-check for an adapted skill. Triggers on "/loopify," "set up a loop," "schedule this task," "run this daily," "run this weekly," "cron this," "make this recurring," "automate this on a schedule," "keep this running until X." Part of the -ify trifecta (skillify / toolify / loopify). NOT for authoring a new skill — that's skillify. NOT for adding a tool/integration — that's toolify.

The English summary is being prepared. Showing the original description.

Use when installing, bootstrapping, configuring, starting, verifying, operating, or troubleshooting Looper, looperd, the looper CLI, ~/.looper config, or runtime paths; when setting up Looper with opencode, claude-code, codex, cursor-cli, Grok Build, Pi, or Oh My Pi (omp); when registering repos or configuring planner/reviewer/fixer/worker loops; or when diagnosing status, logs, osascript, git, gh, LOOPER_TOKEN, writable path, or daemon startup issues.

The English summary is being prepared. Showing the original description.

Use only after explicit Codex `$superloopy:superloopy-frontend` or Claude Code `/superloopy:superloopy-frontend` invocation for supported screen-based application UI across browser-hosted Web, interactive deployed content-led Web, desktop, mobile/tablet, embedded/hybrid, Qt, custom-rendered, or mixed targets, such a task started with a leading `loopy` or `루피`, or an active Superloopy loop explicitly routing it here. Do not activate from UI, frontend, desktop, mobile, or framework vocabulary alone, or for TV, wearable, XR, automotive, game UI, TUI, static media/document artifacts, or non-UI work.

The English summary is being prepared. Showing the original description.