2114 个 · 按相关度排序
Iteratively improve research by having Claude Code review code, results, and drafts while Codex implements fixes. Repeat until the assessment meets the stopping criteria or the round limit is reached, preserving feedback and unresolved issues.
中文简介正在准备中。当前显示英语简介。
Improve research through repeated Gemini reviews, code changes, experiments, and analysis. The workflow records full feedback and actions, then stops when both the score and readiness criteria are met or the round limit is reached.
中文简介正在准备中。当前显示英语简介。
Improve research code, results, and paper drafts through repeated review by a second Codex agent. The workflow implements fixes, checks them again, and records assessments and unresolved issues across up to four rounds.
中文简介正在准备中。当前显示英语简介。
Use MiniMax to review research, address weaknesses through code changes, experiments, or analysis, and request another assessment. The workflow runs up to four rounds and preserves reviewer responses, actions, results, and unresolved blockers.
中文简介正在准备中。当前显示英语简介。
Explore hardware and electronic design configurations by repeatedly running programs, measuring results, and adjusting parameters. Track constraints and every trial, then report the best configuration found within the time and iteration limits.
中文简介正在准备中。当前显示英语简介。
Review recent changes, automated test failures, issues, and conversations to prioritize engineering work. Produce a concise report separating urgent actions, watch items, noise, and state updates, with suggested next steps and rough effort estimates.
中文简介正在准备中。当前显示英语简介。
Independently checks code changes against the original issue, runs tests, and verifies that edits stay within scope. Produces an approval, rejection, or request for human judgment, supported by test results and specific findings.
中文简介正在准备中。当前显示英语简介。
Reviews recent changes, CI failures, open issues, pull requests, and conversations to produce a prioritized findings report. It separates urgent work from monitoring and noise, suggests next actions, and records facts for the next automated review cycle.
中文简介正在准备中。当前显示英语简介。
Build a looping animated hero, the large visual at the top of a page, or a video opening. Combine rotating text, a globe or abstract geometry, a timer, and floating labels with cinematic colors and one neon accent.
中文简介正在准备中。当前显示英语简介。
Turn site requirements or existing content into a SITE.md project guide for the Stitch Build Loop. It records the site's purpose, visual direction, navigation, file structure, and prioritized tasks to guide successive development rounds.
中文简介正在准备中。当前显示英语简介。
Runs repeated reviews and fixes on a Claude Code skill until no critical or major findings remain. Tracks findings across rounds, checks change boundaries, and stops for a design decision when fixes stop making progress.
中文简介正在准备中。当前显示英语简介。
Build continuous scrolling rows for logos, testimonials, screenshots, or short tags. The skill explains how to duplicate content, stabilize item widths, soften edges, and accommodate people who prefer reduced motion.
中文简介正在准备中。当前显示英语简介。
Create SVG illustrations of active figures using one continuous black line and offset color patches that resemble misaligned printing. The skill guides poses, colors, composition, rendering, and visual checks for product pages and announcement cards.
中文简介正在准备中。当前显示英语简介。
Build or extend an isometric action RPG, viewed from an angled overhead perspective, using web technology. Develop a playable loop covering movement, combat, rewards, progression, and saves, with staged implementation and release checks.
中文简介正在准备中。当前显示英语简介。
Run repeated Ouroboros execution and improvement cycles as a background job, starting from a Seed specification or continuing an existing lineage. The loop stops on a quality check pass, convergence, cancellation, or the generation limit, and reports the outcome.
中文简介正在准备中。当前显示英语简介。
Start and monitor an Ouroboros development loop that revises project concepts and acceptance criteria, the conditions for judging completion. Run and evaluate successive generations, focus revisions on failed criteria, inspect progress, or rewind to an earlier generation.
中文简介正在准备中。当前显示英语简介。
Plan work across several AI agents by defining task owners, deliverables, dependencies, and acceptance criteria. Choose a finite workflow or repeated improvement cycles, then review results before allowing dependent tasks to proceed.
中文简介正在准备中。当前显示英语简介。
Manage a project’s execution plan and lifecycle across multiple agents. Track task dependencies or repeated work cycles, identify tasks ready to start, handle pauses and completion, and prepare project status reports and final results.
中文简介正在准备中。当前显示英语简介。
Optimize .NET loops with SIMD, which processes multiple values in one operation, or review existing SIMD code. Check behavioral equivalence, memory safety, platform fallbacks, and benchmarks to establish whether the optimization is correct and worthwhile.
中文简介正在准备中。当前显示英语简介。
Update existing Lark/Feishu documents while preserving comments, highlights, citations, and newer remote edits. Maintain a private local copy, apply targeted changes, and verify the updated document for ongoing project use; LoopX integration is optional.
中文简介正在准备中。当前显示英语简介。
Manage a project's stored materials through inventory, migration, archiving, and ranking based on verified source reads. Changes follow owner approval, preserve material references, and include validation records and rollback procedures.
中文简介正在准备中。当前显示英语简介。
Investigate fast-agent session files and logs to diagnose unexpected endings, tool loops, and mismatched tool responses. Inspect conversation history, summarize model and tool execution times, and connect sub-agent traces with the corresponding main-session activity.
中文简介正在准备中。当前显示英语简介。
Breaks a long-running goal into small, tracked actions and records observable evidence for each success criterion. Checkpoints preserve progress so the agent can resume after interruptions and verify completion against the current work.
中文简介正在准备中。当前显示英语简介。
[omh] Ambitious project goal needing many build cycles: agentic interviewer -> planner -> researcher -> builder -> reviewer cycles until a real gate. Use when the user says: loop, goal loop, long horizon goal, never stop, research plan goal feedback, token exhaustion resume, permission profile, star 10k.
中文简介正在准备中。当前显示原文说明。