Human-in-the-loop approvals

Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.

cursor/plugins

Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.

alchaincyf/darwin-skill

Installs or refreshes Iron Proxy and its Iron Control web console for NanoClaw, with a local Docker setup, database, credentials and a human approval bridge.

nanocoai/nanoclaw

Patterns for building LLM agents on Trigger.dev tasks: prompt chaining, routing, parallel workers, orchestrator-workers, evaluator loops and human approval gates.

papermark/papermark

Implement, fix, refactor, or remove repository code under required scope, non-regression, verification, and review gates.

apache/shardingsphere

Loads a project's loop-constraints.md before any other action and blocks pushes, edits or merges that violate the rules it defines.

cobusgreyling/loop-engineering

Shows a question as a modal in the interface to clarify a task, collect a preference or get approval, since the user cannot see terminal output.

MemTensor/MemOS

Appends two or three targeted follow-up questions after a substantive answer, pointing at facts to verify, reasoning to probe, or context that was assumed.

anthropics/skills

Pushes an agent to keep verifying and changing approach after repeated failures, using a diagnosis line, evidence-based completion and confirmation before risky edits.

tanweai/pua

Merge a reviewed pull request the way the Symfony core team does: one --no-ff merge commit per PR, whose message archives the whole discussion, with the review gates checked first.

symfony/symfony

Teaches an agent to drive the Mole (mo) Mac cleaning CLI safely: preview first, use JSON output, and leave destructive runs to the user.

tw93/Mole

Deletes chosen memories from agentmemory only after showing the matches and getting an explicit yes, for privacy requests and cleanup of outdated notes.

rohitg00/agentmemory

Mines a Plannotator archive of denied plans for feedback patterns and prompt improvements, then writes an HTML dashboard report, with a Claude Code fallback.

backnotprop/plannotator

Turns an underspecified do-something request into a typed IntentSpec by looking things up, asking only necessary questions or halting, before any planning or coding.

angel291592/Intent-Router

A skill your agent uses when helping someone install, configure, or debug a fresh clone of JARVIS (this repo) — especially "the mic doesn't work", "JARVIS says his language systems are down", any…

ethanplusai/jarvis

A skill your agent uses when designing, reviewing, or implementing single-cell RNA-seq QC in Python or R with a human-in-the-loop, data-driven approach.

xuzhougeng/wisp-science

Holds student work in a queue for a legal clinic professor to approve, edit-then-approve or return before anything reaches clients or courts.

anthropics/claude-for-legal

A Chinese-language guide and reference for building agents with LangGraph 1.0, from a first ReAct agent through middleware, memory, MCP, RAG and web search.

luochang212/dive-into-langgraph

Shows a categorized, interactive menu of common Squad operations, such as install, upgrade and team management, and collects arguments before running anything.

microsoft/waza

Shows one digest of coding-agent sessions across your connected machines and lets you open, read, steer, approve, stop and close them, over Herdr, tmux or MSP.

asgeirtj/system_prompts_leaks

Triages and manages Codewhale fleet runs and workers with typed commands, classifying failures and choosing a safe restart, resume or escalation.

codewhale-hq/Codewhale

Drives desktop GUI apps and OS dialogs by letting Jev pick the next action from a menu of safe actions the agent built, with a Mac Co-Agent shortcut.

kerpopule/hermes-jev-skills

Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between…

google/adk-python

Coordinates and recovers multi-stage Light research projects from a single passport file, with checkpoints, stale-work tracking and rerouting only when you approve.

Light0305/Light-skills

Guidelines and step-by-step workflow for debugging DevTools extensions locally, including stub mode, fixed-port launching, browser auto-opening, URL query parameters, target app connection, and…

flutter/devtools

Moves a design-grilling interview from the terminal to a local web page, where each question, recommendation and discussion thread can be handled in any order.

jasonku09/grill-with-ui

End-to-end GitHub repository maintenance for open-source projects.

numman-ali/n-skills

Linggen — durable cross-host memory plus browser control, over two local MCP servers: ling-mem for memory, the Linggen engine for browser, X and agents.

linggen/linggen-memory

A skill your agent uses when running claudikins-kernel:outline, brainstorming implementation approaches, gathering requirements iteratively, structuring complex technical plans, or facing analysis…

povvo/claudikins-kernel

INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph.

langchain-ai/langchain-skills

Operates cmux Cloud machines from the cmux CLI, running durable remote commands or detached agents and presenting their workspaces, with authorization limits on destructive steps.

manaflow-ai/cmux

Generates UiPath Tasks workflows for form tasks, external tasks and task management, with form.io schemas, lint rules and scaffold hooks loaded through uipath-core.

marcelocruzrpa/uipath-ai-skills

Integrate SimplePDF into a web application for PDF viewing, editing, filling, signing, programmatic control, AI-agent interaction, human-in-the-loop form prefilling, submissions, webhooks, or…

SimplePDF/simplepdf-embed

Lets a plotting agent query a gallery of scientific figure references, show candidates for you to pick from, and export the chosen ones before it writes plot code.

Dsadd4/AgentFigureGallery

Runs or authors Smithers TypeScript flows for ordered agent stages with retries, approvals, bounded loops and crash-safe recovery, built from Flow.make, Action.make and Effect.

smithersai/smithers

Human-in-the-loop theoretical economics research pipeline: from economic intuition to manuscript skeleton in 10 structured stages with quality gates.

maxwell2732/pAI-Econ-claude

Interactive debugging mode that generates hypotheses, instruments code with runtime logs, and iteratively fixes bugs with human-in-the-loop verification.

doraemonkeys/claude-code-debug-mode

An instruction-only discipline for Trae that forces evidence-based work when an agent keeps failing, gives up or declares a task finished without proof.

tanweai/pua

Browses open tasks on the TaskMarket agent-worker market and, with explicit operator approval, creates tasks, tracks submissions and submits finished work.

aeonfun/aeon

Enforces explicit user permission before any file deletion. Activates when you're about to use rm, unlink, fs.rm, or any operation that removes…

MemTensor/MemOS

审查当前 git 变更、PR、提交范围、技能定义文件、架构调整或安全敏感代码时使用。输出结构化 Review Gate 结论（Pass/Reject）、问题分级（blocker/warning/suggest）、最低验证矩阵、证据链与复查基线。覆盖正确性、安全、架构、SOLID、可删除代码、性能、异常处理与测试风险；默认只输出 review，不直接修改代码。用户提到 review、code…

CaoMeiYouRen/caomei-auth

Designs, evaluates and improves the harness around an AI agent: tool permissions, approval gates, state, memory, evals and observability, with phased plans.

NateBJones-Projects/OB1

Lets Claude keep working while you are away, after a pre-flight that surfaces blockers, risky operations and open decisions, with a stop hook scoped to the session.

andylizf/nonstop

Generate a Phase-2 Walkthrough artifact (walkthrough.md) once implementation and verification are complete.

smallnest/goal-workflow

Inspects, plans, changes and rolls back macOS default app handlers for file types, MIME types and URL schemes through Dutis, with approval before any write.

tsonglew/dutis

A workflow for Google Cloud changes: pick gcloud, bq or gsutil, check the command against official docs, preview with a dry run and ask for approval before executing.

rominirani/antigravity-skills

End-to-end 10x Visium spatial transcriptomics analysis workflow with staged execution and human review gates.

QING1105/ezST

Run a spec-driven agent loop where coding tasks live as markdown specs that move through inbox → active → archive, get implemented by Claude Code or Codex, and pass a review gate before they count…

JuliusBrussee/skills