Agent Workflows

A skill your agent uses when the user asks to architect, run or continue the autonomous software factory, turn a goal into a hardened tracker issue plan, dispatch builder jobs, grade finished work…

DanMcInerney/architect-loop

Commit facts to the MemForks memory DAG using memfork commit --facts.

Ghost-xDD/memforks

Author, package, validate, or run mathematical evaluations as Jacobian Harbor datasets.

morluto/jacobian

Knowledge base for the Kingdee MCP Dev Squad. An agent skill from WaHaiLong/KingdeeMCP.

WaHaiLong/KingdeeMCP

Write or correct this repo's agent documentation — a workspace AGENTS.md (or its CLAUDE.md symlink), a playbook under .agents/docs/playbooks, an architecture doc, or the workspace map.

DouglasNeuroInformatics/OpenDataCapture

Run the nohuman review gate (fresh-session adversarial reviewer + tamper guard) over the current branch or a GitHub pull request, with no server, no database, and no onboarding, and relay the…

no-human-ai/no_human

When the user invokes this skill, the agent reflects on the most important lessons learned recently and suggests adding a new rule to AGENTS.md to prevent the same issue from recurring.

kovrichard/catalyst

Bootstraps a new multi-agent repository from the RepoBrain template via initagentrepo.

study8677/repobrain

Guides creating, updating and reviewing built-in MoviePilot agent skills: file layout, frontmatter, allowed tools and the version bump that syncs changes to users.

jxxghp/MoviePilot

Drafts and iterates on local-development bug reports in the role of a staff-level Tech Lead.

FHIR/fhir-codegen

Kernel-version skew check (ADR-027). An agent skill from ruvnet/metaharness.

ruvnet/metaharness

把 v9.5.5 项目的 .aistate/ 升级到 v9.6 schema (INDEX + details/ 重构)。

m-xlsea/ruoyi-plus-soybean

Babysit a pull request through the NorbiAI review loop until no valid issue remains.

nightly-labs/openbot

Reports which OMG modes are active, such as autopilot, ralph, team, ultraqa and self-improve, with phase, story or cycle progress read from their state files.

zereight/gitlab-mcp

A skill your agent uses when creating or updating Doc View repository documentation, AGENTS.md, AI workflow guidance, OpenSpec configuration, or repo-local Codex skills.

liuzhihang/doc-view

Guide to designing and building MCP servers: tool, resource and prompt design for agent usability, with TypeScript or Python implementation workflows.

shareAI-lab/Kode-CLI

A skill your agent uses when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.

AVIDS2/memorix

Save durable project knowledge to Mission Control's Recall (project memory) so future sessions start already knowing it, AND navigate this project's indexed code graph.

AgentSystemLabs/mission-control

Ревью изменений в текущей ветке относительно main. An agent skill from justxor/claude-code-pro-course.

justxor/claude-code-pro-course

Extracts durable insights from temp/ files to SoT during EPIC Phase E.

mattgierhart/PRD-driven-context-engineering

Operational notes for generating, evaluating and debugging strategies in the autocontext grid_ctf scenario, with tier rules and parameter ranges that worked or failed.

greyhaven-ai/autocontext

Run or inspect declared iOS and Android native app tests through Horizon devicetestrun and app MCP tools.

peters/horizon

A skill your agent uses when writing or auditing content that has to be easy to follow — explainer reels, teaching carousels, how-to scripts, any piece that teaches or explains something — or when a…

artemnovitckii/content-skills

Audit your OpenClaw setup for token waste, context bloat, and cost optimization opportunities

alexgreensh/token-optimizer

A skill your agent uses when rules or instructions mention "adversarial-authoring", "adversarial authoring", "must use adversarial-authoring skill", "model council", "cross-model review", or…

intent-driven-dev/intent-driven-template

Multi-bot Telegram bridge — routes messages between Telegram and Claude tmux sessions

AIOSAI/AIPass

Human-In-The-Loop gate that presents the action plan with full context, collects an informed approval/modification/rejection decision, and records the outcome.

kayba-ai/agentic-context-engine

When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.

antonbabenko/deliberation

A skill your agent uses when applying oh-my-claude workflow guidance, ultrawork modes, agent orchestration, plan execution, or plugin configuration.

TechDufus/oh-my-claude

Creates and validates a new native Muse plugin package in the current workspace, limited to five capability families, and leaves installation to you.

asgeirtj/system_prompts_leaks

Runs deterministic DAG pipelines from a JSON descriptor with journal-based crash recovery, so an interrupted run resumes without repeating finished nodes.

Yeachan-Heo/oh-my-claudecode

Scan the codebase for deepening opportunities, prioritize them, then turn as many as the user wants into ordered plan tasks.

ordewell/ordewell

Manage Nix package, profile, flake, and diagnostic work in this dotfiles repository.

wcygan/dotfiles

Manage Haft's typed specification lifecycle and source-currentness repair: inspect current SpecSections, draft or clarify carriers, classify FPF semantic fanout, record operator-requested spec…

m0n0x41d/haft

Show detailed cost breakdown and budget status for the Bernstein orchestrator.

sipyourdrink-ltd/bernstein

Summarize AI coding sessions into concise, privacy-safe markdown focused on implementation-relevant context.

mandel-macaque/memento

Operates or analyzes a LoopX-managed benchmark experiment: launching runs, maintaining the experiment board, qualifying integrity, and writing case insights.

loopx-project/loopx

Verify claims in pitch decks and founder statements using multiple independent sources.

Abilityai/trinity

Scaffold an MCP App tool + UI resource pair. An agent skill from cyanheads/pubmed-mcp-server.

cyanheads/pubmed-mcp-server

Create or edit native Siemens NX parts through the existing NXMCP tools, including sketch/extrude workflows, result checks, and recovery from stale references or uncertain execution.

DreamEnding/NX_MCP

Loads Prism session memory on the first user turn, greets the developer by their configured name and shows recent-session context at the configured depth.

dcostenco/prism-coder

Walks you through creating, running and reading waza evals for an agent skill, then proposes concrete fixes when tasks fail or the score is low.

microsoft/waza

Rules for several agents sharing one repository: an orchestrator tracks work in two tiers, workers write to scratch files, and every handoff leaves a pointer to an artifact.

dralgorhythm/claude-agentic-framework

Guides creating or improving codewhale skills: file layout, discovery paths, writing rules and whether a need fits a skill, an MCP server, hooks or a plugin.

codewhale-hq/Codewhale

Creates or updates Dynamo Enhancement Proposals as GitHub issues, including lightweight DEPs, implementation plans, and retroactive DEPs for ai-dynamo/dynamo.

ai-dynamo/dynamo

Guide for creating persistent Near desktop digital avatars (数字分身) via natural-language interview and the createavatar tool.

DemonDamon/AgenticX

Have an interactive discussion about a topic, approach, feature, or bug without making code changes.

greenfield-inc/Pane

Add a new tool to the MoneyMatter MCP server. An agent skill from letehaha/moneymatter.

letehaha/moneymatter