Human-in-the-loop approvals

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

The opencode binding of the AutoMCM-Pro math modeling pipeline for CUMCM and MCM/ICM contests, with tool mappings, install prompts and checkpointed runs.

RealSeaberry/AutoMCM-Pro

Author a pull request in the Guild's standard shape — a fixed Summary / Changes / Verification / Notes skeleton that mirrors the review-gate, plus the hard anti-leak rule that no agent @mention or…

inkline/inkline

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

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

nightly-labs/openbot

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

Reference for picking the right Plannotator tool or command for plan review, code review, annotating files and URLs, archived plan decisions and Guided Reviews.

backnotprop/plannotator

Check whether Claude Code CLI is ready in this environment and optionally toggle the turn-end review gate.

sendbird/cc-plugin-codex

Find, download, resize, and embed images for the three Highlight links in draft.md.

rweekly/rweekly.org

Acts as a proxy for the Cline CLI, dispatching coding tasks one at a time, monitoring runs by hard evidence, relaying decisions to you and learning per-project preferences.

sickn33/agentic-awesome-skills

Troubleshoots Kode permission prompts and denials, including allowlists, command-level tool limits, dontAsk mode and subagent inheritance, without loosening permissions.

shareAI-lab/Kode-CLI

Creates AI2Human tasks for steps that need a real person, such as manual QA or local checks, and returns a task URL the agent can track.

BankrBot/skills

A skill your agent uses when preparing a fix or feature PR for review and adding before/after plot evidence to the PR body.

RussellSB/pytrendy

Guides changes to the Smithers agent loop's host wiring: credentialed model seats, budget accounting, sandbox limits and flow-call authorization.

smithersai/smithers

Watches a pull request's CI checks after creation, separates required from auxiliary failures, applies limited safe fixes and escalates anything semantic to you.

modu-ai/moai-adk

Opens Plannotator's browser annotation view for a markdown, config, HTML, URL or folder target and acts on the feedback you leave, with an optional approval gate.

backnotprop/plannotator

Runs a project on one Kanban board shared by people and AI agents, where a dispatcher splits goals into tasks and any task can go to either a human or an agent.

Hermes-brasil/hermes-brasil

Switches on full safety by combining warnings before destructive commands with a block on edits outside one directory you choose, for work on production or live systems.

garrytan/gstack

Help a clinic supervisor author a practice-area guide that configures how student-facing skills behave — intake questions, pedagogy posture (assist / guide / teach), review gates, cross-plugin…

anthropics/claude-for-legal

Deletes Mem0 memories found by search query or memory ID, listing the matches and requiring explicit confirmation before anything is removed.

mem0ai/mem0

PAO workflow for scanning, drafting, and presenting community responses with human review gate

FritzAndFriends/SharpSite

Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows.

seb1n/awesome-ai-agent-skills

Explains how to build agents with the Deep Agents framework: create_deep_agent, the built-in middleware, the harness, SKILL.md format and configuration options.

langchain-ai/langchain-skills

Runs a manual QA session for a PR, issue, or branch — publishes an interactive runbook the tester works through in parallel from the moment a plan exists, updated with AI verdicts and bugs at the end.

open-mercato/skills

Implement LangGraph error handling with current v1 patterns.

soba-labs/langchain-agent-skills

Runs Gemini CLI once in headless JSON mode for repository analysis or coding work, keeping its approvals read-only unless you ask for changes.

CherryHQ/cherry-studio

Runs GitHub Copilot CLI non-interactively on a repository task and reads its JSONL output, denying tools by default so nothing changes unless you ask.

CherryHQ/cherry-studio

Runs Hermes Agent once for a bounded local task, with warnings about its automatic tool approval and advice to use a disposable copy for read-only work.

CherryHQ/cherry-studio

Sends a bounded task to MiniMax Code with mcode exec, passing the smart permission mode for analysis and never the full one.

CherryHQ/cherry-studio

Runs OpenCode once with opencode run and reads its JSON event stream, leaving its default denial of permission prompts in place for analysis.

CherryHQ/cherry-studio

Runs the Qoder CN CLI statelessly with JSON output and accepts the result only when the is_error field says the task succeeded.

CherryHQ/cherry-studio

Guide to designing n8n AI agents: choosing between Agent, chain, classifier and extractor nodes, wiring model, memory, tools and parser, plus RAG and human review.

czlonkowski/n8n-skills

A skill your agent uses when the user is done editing and wants to ship the current branch via a pull request — phrases like "open a PR", "ship it", "ship this", "submit the PR", "let's send it"…

openbootdotdev/openboot

Runs the gstack CEO, design, engineering and DX review skills on a plan file in sequence and makes borderline taste decisions automatically using six stated decision principles.

garrytan/gstack

Shows which questions gstack skills ask you, lets you set per-question preferences and compares your declared style with what your behavior suggests.

garrytan/gstack

Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them.

fabricioctelles/skills

Opens Plannotator on the agent's latest rendered reply so you can annotate it, then folds the returned feedback into a revision or the next step.

backnotprop/plannotator

Manages Alibaba Cloud Bailian managed agents as infrastructure as code with the bl managed-agent command, previewing every change before apply or destroy.

modelstudioai/cli

Adds one optional external Codex critique that tries to break a council's decision draft, sent to OpenAI only after you consent.

affaan-m/ECC

Review completed implementation batches for spec compliance and code quality.

MageByte-Zero/spec-superflow

Builds human-in-the-loop (HITL) Airflow workflows - approval gates, form input, and human-driven branching.

astronomer/agents

Runs new features, scripts and structural changes through explore, design, approval, implementation and verification phases, with a tool search and an explicit plan sign-off.

mp-web3/claude-starter-kit

A decision tree for an agent changing its own setup: edit memory directly, request approval for packages and MCP servers, and delegate code edits to a builder agent.

nanocoai/nanoclaw

Design patterns for building autonomous coding agents. An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

Fetches harness learning proposals from the moai CLI, hands them to the orchestrator for approval and applies, rejects or rolls back the resulting changes.

modu-ai/moai-adk

Supplies the mechanics for sending a message to a registered human, discovering who to contact, checking the channel is ready, and drafting a short, phone-readable brief.

mvschwarz/openrig

Review IEEE conference, journal, Transactions, Letters, or magazine manuscripts from a technical reviewer perspective using routed IEEE review gates.

CloudWave818/ieee-skills

Reads orchestration and judgment logs without writing to them, finds failures that keep recurring, and proposes rule candidates with confidence scores for human review.

Chachamaru127/claude-code-harness