3412 个 · 按相关度排序
Configure and debug MCP servers for Claude Code, OpenCode, and Codex CLI, including auth headers, scope, and validation checks. Use when MCP tools fail to connect, when an MCP server returns 401/404/HTML, or when adding a new MCP server to this repo.
中文简介正在准备中。当前显示原文说明。
Use to process automated PR review feedback (Copilot, Greptile, Codex) and iterate until all AI threads are addressed, checks are green, and the PR is merge-ready. Trigger when the user says "address review feedback", "recycle reviews", or references an automated reviewer.
中文简介正在准备中。当前显示原文说明。
Autonomous bug-hunt workflow for the Humans repository. Use when the user wants Codex to scan for real bugs, work in a dedicated git worktree branched from origin/main, commit each fix separately, push progress, and continue until diminishing returns.
中文简介正在准备中。当前显示原文说明。
Adversarial triage of open review findings on a PR. Every finding (Codex, Claude bot, Gemini) is a hostile hypothesis to REFUTE — fix only what is proven real, reachable, in the PR's scope, and above the round's severity bar. The bar rises every review round. Everything else is declined or filed as an issue. Use for 'fix the PR findings', '/fix', '/fix 123', or before any fix commit in a review loop.
中文简介正在准备中。当前显示原文说明。
Run multiple Reforge-guided section-refactor lanes in parallel, each in its own worktree/branch off origin/main, with a score-blind adversarial review panel gating every commit, one draft PR per section. Use when the user wants to reduce Reforge surface/internal score across several sections at once via architecturally-correct deletions (dead surface, entity-leak removal, cross-section consumers moved onto the public contract) — not by relocation, parameter bags, or accessibility-dodging. Wraps the per-lane process in .codex/skills/humans-refactor. Triggers: 'refactor swarm', 'parallel section refactors', 'run reforge refactor on Users/Tickets/...', 'burn down surface score across sections'. Has an intensity dial (light|standard|deep) and a workflow|solo execution mode to trade token burn against autonomy per unit of output.
中文简介正在准备中。当前显示原文说明。
Autonomous tech-debt reduction workflow for the Humans repository. Use when the user wants Codex to improve high-value code quality issues in a dedicated git worktree branched from origin/main, commit each improvement separately, push progress, and continue until diminishing returns.
中文简介正在准备中。当前显示原文说明。
Autonomous Reforge-guided refactor workflow for the Humans repository. Use when the user wants Codex to target a section such as Shifts, Users, Teams, Tickets, Camps, or Store, create a dedicated worktree/branch from origin/main, run iterative architecture-focused improvements, score each stage with Reforge, gate commits through a score-blind read-only architecture review, append score and verdict details to commit messages after review acceptance, push progress, and open a PR when the loop reaches stasis.
中文简介正在准备中。当前显示原文说明。
Turn character reference images into reusable, rigged voxel 3D assets for Blender and Three.js through an imagegen turnaround and user-approval workflow. Use when Codex needs to preserve a character's likeness across front, side, and back views; create or revise Minecraft-like cube-headed models; prevent missing rear hair or clothing; split features between block geometry and face/clothing textures; generate GLB and editable .blend files; add walk/smash-compatible rigid-part pivots; or diagnose why a voxel conversion is not recognizable.
中文简介正在准备中。当前显示原文说明。
Audit required bioinformatics command-line tools against Lmod or Environment Modules on Linux HPC clusters, resolve executable and version requirements, and reproducibly deploy missing software through a site-approved EasyBuild, Spack, Bioconda/micromamba, Apptainer, binary, or source-build workflow. Use when Codex must inspect module availability, diagnose a missing or wrong-version bioinformatics tool, install scientific software on Slurm/PBS clusters, publish or validate modulefiles, or produce an auditable and rollback-ready cluster software deployment.
中文简介正在准备中。当前显示原文说明。
Build natural-language crypto/DeFi agents and EVM MCP plugins (Claude Code, Cursor, Codex, Gemini). Aomi turns prompts into wallet-signed txs on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated. 40+ apps: Uniswap, Aave, Lido, Morpho, GMX, Hyperliquid, Polymarket.
中文简介正在准备中。当前显示原文说明。
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches. AI agents running in CI/CD pipelines.
中文简介正在准备中。当前显示原文说明。
Download NASA GES DISC NLDAS_FORA0125_H version 2.0 primary hourly forcing data for a point location. Use when Codex needs to retrieve NLDAS File A meteorological forcing from the GES DISC API or HTTPS archive for a longitude/latitude pair, including Earthdata username/password authentication, hourly URL generation, nearest-grid-point extraction, CSV output, or EcoSIM climate-forcing preprocessing.
中文简介正在准备中。当前显示原文说明。
Extract one EcoSIM PFT parameter record from a PFT-parameter NetCDF file into a standalone NetCDF. Use when Codex needs to isolate all parameters for a given EcoSIM six-character PFT code such as ndlf34, or a four-character pfts_short value plus Koppen climate code, while preserving all non-PFT-specific variables such as pfts_short, pfts_long, and Koppen metadata.
中文简介正在准备中。当前显示原文说明。
Extract study sites, observational variables, coordinates, climate-forcing sources, and cited data sources from ecosystem-modeling papers, PDFs, supplements, or article text, then plan or create EcoSIM simulation workflows and run folders for those sites. Use when Codex is asked to read a paper for EcoSIM feasibility, including requests phrased as "read paper for ecosim feasibility"; read a paper for sites/data availability; reproduce a published site simulation in EcoSIM; compare EcoSIM outputs to paper observations; or convert paper-derived AmeriFlux, FLUXNET, US NLDAS-domain, non-US ERA5, crop, peatland, forest, grassland, wetland, or unmanaged field-site information into EcoSIM inputs and runnable cases.
中文简介正在准备中。当前显示原文说明。
Sort AmeriFlux BASE-BADM BIF variables from Excel or CSV files into observation, management-event, static metadata, and plotting-ready target time-series tables. Use when Codex is asked to sort AmeriFlux BIF variables into time series; organize BADM/BIF variables by date; pivot AMF *_BIF_*.xlsx files by GROUP_ID; output total LAI, leaf mass per area, above-ground biomass, canopy height, fruit yield, or total yield time series; write MATLAB readers for BIF time-series plotting; or prepare dated AmeriFlux site observations and management records for EcoSIM workflows.
中文简介正在准备中。当前显示原文说明。
Build EcoSIM atmospheric greenhouse-gas forcing files by combining a historical monthly atmgas NetCDF with RCMIP/CMIP6 SSP concentration pathways. Use when Codex needs SSP245/SSP585 or other SSP atmospheric CO2, CH4, and N2O concentrations, key-year tables, or scenario NetCDF files spanning historical years through 2100 for EcoSIM or related biogeochemical forcing workflows.
中文简介正在准备中。当前显示原文说明。
A radically minimal, blank-canvas interface built as a pure edge-to-edge surface, with almost no color and typography carrying the visual weight. Black serves as the only filled color, the only divider, and the sole surface tone cards.
中文简介正在准备中。当前显示原文说明。
Create new OpenCode agents with a gpt-5.2-codex default.
中文简介正在准备中。当前显示原文说明。
Use when the user wants the project instructions file generated or updated from the detected stack and conventions — 'gerar o arquivo de instruções do projeto', 'criar convenções do projeto', 'setup governance', 'gerar AGENTS'. Writes the shared instructions file read by Claude Code, Codex, Hermes and OpenCode. Do NOT use to analyze the codebase in depth (feat-map) or to initialize the workspace (feat-init).
中文简介正在准备中。当前显示原文说明。
Delegate a bounded repository task to an allowlisted external coding CLI through the guarded Flow runner. Use for automatic provider selection or explicit Codex, OpenCode, Kimi, Gemini, or Kiro delegation that requires timeout handling and independent local review.
中文简介正在准备中。当前显示原文说明。
Launch, inspect, and tear down autonomous phase fleets in isolated Git worktrees, on the Codex or the Claude runtime. Use when approved Flow phase slugs should run in parallel, when fleet status is requested, or when a fleet member must be stopped or explicitly merged.
中文简介正在准备中。当前显示原文说明。
Pair a remote AI agent with your browser. One command generates a setup key and prints instructions the other agent can follow to connect. Works with OpenClaw, Hermes, Codex, Cursor, or any agent that can make HTTP requests. The remote agent gets its own tab with scoped access (read+write by default, admin on request). Use when asked to "pair agent", "connect agent", "share browser", "remote browser", "let another agent use my browser", or "give browser access". (gstack) Voice triggers (speech-to-text aliases): "pair agent", "connect agent", "share my browser", "remote browser access".
中文简介正在准备中。当前显示原文说明。
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when asked to "auto review", "autoplan", "run all reviews", "review this plan automatically", or "make the decisions for me". Proactively suggest when the user has a plan file and wants to run the full review gauntlet without answering 15-30 intermediate questions. (gstack) Voice triggers (speech-to-text aliases): "auto plan", "automatic review".
中文简介正在准备中。当前显示原文说明。
Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".
中文简介正在准备中。当前显示原文说明。