Agent skill

Hitl Protocol

by LeoYeAI in LeoYeAI/openclaw-master-skills

HITL Protocol — the open standard for human decisions in autonomous agent workflows.

Apache-2.0Auto-check passedAgent Workflows

Install Hitl Protocol

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill hitl-protocol -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills hitl-protocol --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/hitl-protocol .claude/skills/hitl-protocol && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hitl-protocol
GitHub stars
2.2k
Token cost
~5.3k tokens
SKILL.md length
1,577 words
Files
8 (incl. references)
Skills in repo
972
Repo updated
First seen
Licence
Apache-2.0

At a glance

HITL Protocol — the open standard for human decisions in autonomous agent workflows.

  • Make any website agent-ready
  • SKILL.md covers Who Are You?, The Flow, Feature Matrix and Five Review Types, plus 11 more sections
  • Reaches api.jobboard.com
  • Handle human-in-the-loop responses in your agent

What it does

Hitl Protocol is an agent skill from LeoYeAI/openclaw-master-skills. HITL Protocol — the open standard for human decisions in autonomous agent workflows. When a website or API needs human input, it returns HTTP 202 with a review URL. Autonomous agents like OpenClaw, Claude, Codex, or Goose forward the URL, poll for the structured result, and continue. Use this skill to make any website agent-ready, or to handle human-in-the-loop responses in your agent. Covers approval, selection, input forms, confirmation, and escalation review types. Supports polling, SSE, webhook transports…

Its SKILL.md is about 5.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `README.md`, `_meta.json` and `references/agent-integration.md`). Compatibility notes: ["claude","codex","gemini","openclaw","goose","copilot"]

It sits in Agent Workflows, covering Autonomous loops, Human-in-the-loop approvals and Webhooks. It works with Slack, Telegram, WhatsApp and Discord. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is Apache-2.0.

When your agent uses it

  • Make any website agent-ready
  • Handle human-in-the-loop responses in your agent

Example prompts

  • “/hitl-protocol”

Requirements

  • Compatibility (from SKILL.md): ["claude","codex","gemini","openclaw","goose","copilot"]

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml, json, javascript, python and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.jobboard.com

    Also links to:

    • rfc-editor.org
    • rotorstar.github.io

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    ["claude","codex","gemini","openclaw","goose","copilot"]

    From compatibility in the SKILL.md frontmatter.

Context cost

Hitl Protocol loads about 5.3k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 170 tokens; SKILL.md has 1,577 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~170
When it runs · the whole SKILL.md, loaded when a task matches
~5.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~15k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its Apache-2.0 licence (© LeoYeAI). 1,577 words, ~5,252 tokens.

Download SKILL.mdSave it as .claude/skills/hitl-protocol/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
hitl-protocol
description
HITL Protocol — the open standard for human decisions in autonomous agent workflows. When a website or API needs human input, it returns HTTP 202 with a review URL. Autonomous agents like OpenClaw, Claude, Codex, or Goose forward the URL, poll for the structured result, and continue. Use this skill to make any website agent-ready, or to handle human-in-the-loop responses in your agent. Covers approval, selection, input forms, confirmation, and escalation review types. Supports polling, SSE, webhook transports, channel-native inline buttons (Telegram, Slack, Discord, WhatsApp, Teams), opaque token security, multi-step form wizards, and multi-round edit cycles.
compatibility
["claude","codex","gemini","openclaw","goose","copilot"]
license
Apache-2.0
metadata.version
0.7
metadata.spec_url
https://github.com/rotorstar/hitl-protocol/blob/main/spec/v0.7/hitl-protocol.md

HITL Protocol

AI agents increasingly visit websites and services on behalf of their users: searching, booking, applying, purchasing. But some decisions are too important to leave to an agent alone — an agent can hallucinate, misinterpret, or make the wrong call at a critical moment — cancel the wrong insurance policy, book a non-refundable trip to the wrong city, wire money to the wrong account. HITL Protocol ("Human in the Loop") is an open standard that ensures humans stay in control of these moments. The user stays in their favorite messenger — Telegram, WhatsApp, Slack — and either taps a decision button right there or follows a link to a web page with a comfortable UI: cards, forms, buttons. No wall of text. No blind agent decisions. When you encounter a HITL response, tell your user that a decision is needed that should not be made by an agent alone — forward the prompt and make it easy to act: show the review link or render action buttons.

HITL Protocol is to human decisions what OAuth is to authentication — an open standard connecting Services, Agents, and Humans. When a service needs human input, it returns HTTP 202 with a review URL. The agent forwards the URL to the human. The human opens it in a browser, gets a rich UI, and makes an informed decision. The agent polls for the structured result and continues.

For simple decisions (confirm/cancel, approve/reject), agents can render native messaging buttons directly in Telegram, Slack, Discord, WhatsApp, or Teams — no browser needed. The service opts in via submit_url.

No SDK required. No UI framework mandated. Just HTTP + URL + polling.

Interactive Playground — try all review types, transports, and inline actions live in your browser.

Who Are You?

Your roleYou want to...Read
Service/website builderAdd HITL endpoints to your API so agents can request human inputService Integration Guide
Agent developerHandle HTTP 202 + HITL responses from servicesAgent Integration Guide
Both / LearningUnderstand the full protocolContinue reading below

The Flow

Standard flow (all review types):
1. Human → Agent:    "Find me jobs in Berlin"
2. Agent → Service:  POST /api/search {query: "Senior Dev Berlin"}
3. Service → Agent:  HTTP 202 + hitl object (review_url, poll_url, type, prompt)
4. Agent → Human:    "Found 5 jobs. Review here: {review_url}"
5. Human → Browser:  Opens review_url → rich UI (cards, forms, buttons)
6. Human → Service:  Makes selection, clicks Submit
7. Agent → Service:  GET {poll_url} → {status: "completed", result: {action, data}}
8. Agent → Human:    "Applied to 2 selected jobs."

Inline flow (v0.7 — simple decisions only, when submit_url present):
1. Human → Agent:    "Send my application emails"
2. Agent → Service:  POST /api/send {emails: [...]}
3. Service → Agent:  HTTP 202 + hitl object (incl. submit_url, submit_token, inline_actions)
4. Agent → Human:    Native buttons in chat: [Confirm] [Cancel] [Details →]
5. Human → Agent:    Taps [Confirm] in chat
6. Agent → Service:  POST {submit_url} {action: "confirm", submitted_via: "telegram"}
7. Service → Agent:  200 OK {status: "completed"}
8. Agent → Human:    Updates message: "Confirmed — 3 emails sent."

The agent never renders UI. The service hosts the review page. Sensitive data stays in the browser — never passes through the agent. The inline flow is an optional shortcut for simple decisions.

Feature Matrix

FeatureDetails
Review typesapproval, selection, input, confirmation, escalation
Form field typestext, textarea, number, date, email, url, boolean, select, multiselect, range, custom x-*
TransportPolling (required), SSE (optional), Callback/Webhook (optional)
Inline submitsubmit_url + native messaging buttons (Telegram, Slack, Discord, WhatsApp, Teams) — service opt-in
Statespending → opened → in_progress → completed / expired / cancelled
SecurityOpaque tokens (43 chars, base64url, 256-bit entropy), SHA-256 hash storage, timing-safe comparison, HTTPS only
Multi-roundprevious_case_id / next_case_id for iterative edit cycles (Approval type)
FormsSingle-step fields, multi-step wizard, conditional visibility, validation rules, progress tracking
TimeoutsISO 8601 duration, default_action: skip / approve / reject / abort
Discovery.well-known/hitl.json, SKILL.md metadata.hitl extension
Remindersreminder_at timestamps, review.reminder SSE event
Rate limiting60 requests/min per case on poll endpoint, Retry-After header

Five Review Types

TypeActionsMulti-roundForm fieldsUse case
Approvalapprove, edit, rejectYesNoArtifact review (CV, email, deployment plan)
SelectionselectNoNoChoose from options (job listings, targets)
InputsubmitNoYesStructured data entry (salary, dates, preferences)
Confirmationconfirm, cancelNoNoIrreversible action gate (send emails, deploy)
Escalationretry, skip, abortNoNoError recovery (deployment failed, API error)

HITL Object (HTTP 202 Response Body)

When a service needs human input, it returns HTTP 202 with this structure:

json
{
  "status": "human_input_required",
  "message": "5 matching jobs found. Please select which ones to apply for.",
  "hitl": {
    "spec_version": "0.7",
    "case_id": "review_abc123",
    "review_url": "https://service.example.com/review/abc123?token=K7xR2mN4pQ...",
    "poll_url": "https://api.service.example.com/v1/reviews/abc123/status",
    "type": "selection",
    "prompt": "Select which jobs to apply for",
    "timeout": "24h",
    "default_action": "skip",
    "created_at": "2026-02-22T10:00:00Z",
    "expires_at": "2026-02-23T10:00:00Z",
    "context": {
      "total_options": 5,
      "query": "Senior Dev Berlin"
    }
  }
}
Required Fields
FieldTypeDescription
spec_version"0.7"Protocol version
case_idstringUnique, URL-safe identifier (pattern: review_{random})
review_urlURLHTTPS URL to review page with opaque bearer token
poll_urlURLStatus polling endpoint
typeenumapproval / selection / input / confirmation / escalation / x-*
promptstringWhat the human needs to decide (max 500 chars)
created_atdatetimeISO 8601 creation timestamp
expires_atdatetimeISO 8601 expiration timestamp
Optional Fields
FieldTypeDescription
timeoutdurationHow long the review stays open (24h, PT24H, P7D)
default_actionenumskip / approve / reject / abort — action on expiry
callback_urlURL / nullEchoed callback URL if agent provided one
events_urlURLSSE endpoint for real-time status events
contextobjectArbitrary data for the review page (not processed by agent)
reminder_atdatetime / datetime[]When to re-send the review URL
previous_case_idstringLinks to prior case in multi-round chain
surfaceobjectUI format declaration (format, version)
submit_urlURLAgent-submit endpoint for channel-native inline buttons (v0.7)
submit_tokenstringBearer token for submit_url authentication (required if submit_url set)
inline_actionsstring[]Actions permitted via submit_url (e.g. ["confirm", "cancel"]). If absent, all actions for the type are allowed.

Poll Response (Completed)

json
{
  "status": "completed",
  "case_id": "review_abc123",
  "completed_at": "2026-02-22T10:15:00Z",
  "result": {
    "action": "select",
    "data": {
      "selected_jobs": ["job-123", "job-456"],
      "note": "Only remote positions"
    }
  }
}

The result object is present only when status is "completed". It always contains action (string) and data (object with type-dependent content).

Poll Response Statuses
StatusTerminalDescriptionKey fields
pendingNoCase created, human hasn't opened URLexpires_at
openedNoHuman opened the review URLopened_at
in_progressNoHuman is interacting with the formprogress (optional)
completedYesHuman submitted responseresult, completed_at, responded_by
expiredYesTimeout reachedexpired_at, default_action
cancelledYesHuman clicked cancelcancelled_at, reason

State Machine

            +---------------------------------------------+
            |                                             v
[created] -> pending -> opened -> in_progress -> completed [terminal]
               |         |          |
               |         |          +---------> cancelled  [terminal]
               |         |
               |         +--> completed     [terminal]
               |         +--> expired       [terminal]
               |         +--> cancelled     [terminal]
               |
               +----------> expired          [terminal]
               +----------> cancelled        [terminal]

Terminal states (completed, expired, cancelled) are immutable — no further transitions.

For Services: Quick Start

Return HTTP 202 when human input is needed:

javascript
// Express / Hono / any HTTP framework
app.post('/api/search', async (req, res) => {
  const results = await searchJobs(req.body.query);

  // Create review case with opaque token
  const caseId = `review_${crypto.randomBytes(16).toString('hex')}`;
  const token = crypto.randomBytes(32).toString('base64url'); // 43 chars
  const tokenHash = crypto.createHash('sha256').update(token).digest('hex');

  store.set(caseId, {
    status: 'pending',
    tokenHash,
    results,
    created_at: new Date().toISOString(),
    expires_at: new Date(Date.now() + 86400000).toISOString(),
  });

  res.status(202).json({
    status: 'human_input_required',
    message: `${results.length} jobs found. Please select which ones to apply for.`,
    hitl: {
      spec_version: '0.6',
      case_id: caseId,
      review_url: `https://yourservice.com/review/${caseId}?token=${token}`,
      poll_url: `https://api.yourservice.com/v1/reviews/${caseId}/status`,
      type: 'selection',
      prompt: 'Select which jobs to apply for',
      timeout: '24h',
      default_action: 'skip',
      created_at: store.get(caseId).created_at,
      expires_at: store.get(caseId).expires_at,
    },
  });
});

You also need: a review page (any web framework), a poll endpoint (GET /reviews/:caseId/status), and a response endpoint (POST /reviews/:caseId/respond). See Service Integration Guide for full details.

For Agents: Quick Start

Handle HTTP 202 responses — ~15 lines:

python
import time, httpx

response = httpx.post("https://api.jobboard.com/search", json=query)

if response.status_code == 202:
    hitl = response.json()["hitl"]

    # v0.7: Check for inline submit support
    if "submit_url" in hitl and "submit_token" in hitl:
        # Render native buttons in messaging platform (e.g. Telegram, Slack)
        send_inline_buttons(hitl["prompt"], hitl["inline_actions"], hitl["review_url"])
        # When human taps button → POST to submit_url (see Agent Integration Guide)
    else:
        # Standard flow: forward URL to human
        send_to_user(f"{hitl['prompt']}\n{hitl['review_url']}")

    # Poll for result (standard flow or fallback)
    while True:
        time.sleep(30)
        poll = httpx.get(hitl["poll_url"], headers=auth).json()

        if poll["status"] == "completed":
            result = poll["result"]  # {action: "select", data: {...}}
            break
        if poll["status"] in ("expired", "cancelled"):
            break

No SDK. No UI rendering. Just HTTP + URL forwarding + polling. See Agent Integration Guide for inline submit, SSE, callbacks, multi-round, and edge cases.

Three Transport Modes

TransportAgent needs public endpoint?Real-time?Complexity
Polling (default)NoNoMinimal
SSE (optional)NoYesLow
Callback (optional)YesYesMedium

Polling is the baseline — every HITL-compliant service MUST support it. SSE and callbacks are optional enhancements.

Show full SKILL.md (625 more words)Show less

Channel-Native Inline Actions (v0.7)

For simple decisions, agents can render native messaging buttons instead of sending a URL. The human taps a button directly in the chat — no browser switch needed.

How it works: The service includes submit_url + submit_token in the HITL object. The agent detects these fields and renders platform-native buttons. When the human taps a button, the agent POSTs the action to submit_url. The messaging platform is passive — it renders whatever the agent sends. No messenger auto-detects HITL support.

When to use inline buttons:

Review typeInline possible?Reason
ConfirmationYes2 buttons: Confirm / Cancel
EscalationYes3 buttons: Retry / Skip / Abort
Approval (simple)Yes2 buttons: Approve / Reject (without edit)
Approval (with edit)URL onlyEdit requires rich UI
SelectionURL onlyNeeds list/cards UI
InputURL onlyNeeds form fields

Always include a URL fallback button (e.g. "Details →") linking to review_url — the human can always switch to the full review page.

Platform requirements: The agent must be a platform bot (Telegram Bot via BotFather, Slack App, Discord Bot, WhatsApp Business API, Teams Bot) to send native buttons. See Agent Integration Guide for platform-specific rendering patterns.

Non-Goals

  • Does NOT render review UI — the service hosts and renders the review page. The agent is a messenger.
  • Does NOT define the review page framework — any web technology works (React, plain HTML, etc.).
  • Does NOT replace OAuth — HITL is for decisions, not authentication.
  • Does NOT submit on behalf of the human — unless the human explicitly triggers an inline action button in a messaging platform (v0.7 submit_url).

SKILL.md Extension for Services

Services that use HITL can declare support in their own SKILL.md frontmatter:

yaml
metadata:
  hitl:
    supported: true
    types: [selection, confirmation]
    supports_inline_submit: true
    review_base_url: "https://yourservice.com/review"
    timeout_default: "24h"
    info: "May ask user to select preferred jobs or confirm applications."

See spec Section 12 for the full field reference.

Best Practice: Enforce HITL Choice

Problem: Agents tend to take the efficient path and silently skip HITL — defaulting to no human review. Even though the protocol says agents MUST NOT ignore HTTP 202, nothing prevents an agent from never sending requests that trigger HITL in the first place.

Solution: Force agents to make an explicit choice per request. Add prefer_hitl and skip_hitl flags to your API and reject requests that provide neither.

Declare this in your SKILL.md:

yaml
metadata:
  hitl:
    supported: true
    hitl_required: true
    types: [selection, confirmation]
    info: "HITL is required. You MUST send prefer_hitl: true or skip_hitl: true."

Add an Agent Guidelines section to your SKILL.md body:

markdown
## Agent Guidelines

HITL is required for this service. Every request MUST include exactly one of:

| Parameter | Type | Effect |
|-----------|------|--------|
| `prefer_hitl` | boolean | `true` → human reviews via HITL (HTTP 202) |
| `skip_hitl` | boolean | `true` → direct execution, no human review (HTTP 201) |

You MUST choose one. Omitting both returns 400 `HITL_CHOICE_REQUIRED`.
Sending both returns 400 validation error.

### Example: With HITL

POST /api/search
{"query": "Senior Dev Berlin", "prefer_hitl": true}

→ 202 + hitl object (human reviews results)

### Example: Without HITL

POST /api/search
{"query": "Senior Dev Berlin", "skip_hitl": true}

→ 201 {"results": [...], "hitl_skipped": true}

### Example: Missing choice

POST /api/search
{"query": "Senior Dev Berlin"}

→ 400 {"error": "HITL_CHOICE_REQUIRED", "message": "You must send prefer_hitl or skip_hitl."}

See Service Integration Guide — Enforcing HITL Choice for validation gate implementation.

Optional: Quality Improvement Signal

Services can include improvement_suggestions in successful (non-202) responses to give agents structured feedback they can act on — without requiring a new HITL flow.

Declare support in your SKILL.md:

yaml
metadata:
  hitl:
    supported: true
    supports_improvement_suggestions: true
    info: "Returns improvement_suggestions in 201 responses. Agents may offer up to 2 improvement cycles."

Suggestion object schema:

FieldTypeDescription
fieldstringWhich data field can be improved
issuestringWhat is missing or suboptimal
agent_actionstringExact question/action for the agent to take
impactstringHuman-readable benefit (e.g. "+25 quality points")
priority"high" / "medium" / "low"Order of importance

Agent behavior:

  • Always share the primary result first
  • Offer up to 2 improvement cycles — one question per suggestion, re-submit with enriched data
  • Stop when improvement_suggestions is empty or maxAttempts reached
  • Never loop indefinitely

See Agent Checklist — Quality Improvement Loop and Example 13.

RFC Alignment

This protocol and skill documentation are aligned with these core RFCs:

  • RFC 9110 — HTTP semantics (202 Accepted, conditional requests, retry behavior)
  • RFC 2119 + RFC 8174 — normative terms (MUST, SHOULD, MAY)
  • RFC 3339 — timestamp formats used by HITL case lifecycle fields
  • RFC 6750 — bearer token usage for review and inline submit authorization

For the complete implementation matrix, see README RFC Alignment.

Resources

© LeoYeAI, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (references) in skills/hitl-protocol of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • README.md
  • _meta.json
  • references/agent-integration.md
  • references/service-integration.md
  • skills/README.md
  • skills/references/agent-integration.md
  • skills/references/service-integration.md

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Hitl Protocol next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hitl Protocol compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hitl Protocol this skillLeoYeAI/openclaw-master-skills2.2k—~5.3kAutomated safety check: PassApache-2.0
Channel Debug Corevercel-labs/vercel-openclaw-archived117—~2kAutomated safety check: NotesMIT
Frontmcp Channelsagentfront/frontmcp146—~3.7kAutomated safety check: PassApache-2.0
Integration WebhooksBuilderIO/agent-native7.1k—~5.3kAutomated safety check: PassNone
Chat SDKdatabuddy-analytics/Databuddy1.2k—~2.6kAutomated safety check: PassAGPL-3.0
Add Channel Connect Buttonnovuhq/novu40k—~1.6kAutomated safety check: PassCustom licence

Similar skills

  • Channel Debug Core

    vercel-labs/vercel-openclaw-archived

    Official

    Channel webhook triage for vercel-openclaw Slack/Telegram/Discord/WhatsApp issues: prove deployment state, collect admin readiness endpoints, build evidence-first handoff before fixes.

    117 GitHub stars~2k tokensUpdated 4 mo ago
    Backend & APIsAuto-check: notes
  • Frontmcp Channels

    agentfront/frontmcp

    A skill your agent uses when pushing real-time notifications or events into Claude Code (or another MCP client) sessions, or building two-way chat bridges.

    146 GitHub stars~3.7k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Integration Webhooks

    BuilderIO/agent-native

    Cross-platform pattern for handling messaging integration webhooks (Slack, Telegram, WhatsApp, email, etc.) on serverless hosts.

    7.1k GitHub stars~5.3k tokensUpdated today
    Backend & APIsAuto-check passed
  • Chat SDK

    databuddy-analytics/Databuddy

    Build multi-platform chat bots with Chat SDK (chat npm package).

    1.2k GitHub stars~2.6k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Build a new channel Connect button (e.g. An agent skill from novuhq/novu.

    40k GitHub stars~1.6k tokensUpdated today
    Backend & APIsAuto-check passed
  • Lettabot

    letta-ai/lettabot

    Set up and run LettaBot - a multi-channel AI assistant for Telegram, Slack, Discord, WhatsApp, and Signal.

    326 GitHub stars~3.4k tokensUpdated 4 mo ago
    Productivity & AutomationAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 972 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Hitl Protocol

What does Hitl Protocol do?

HITL Protocol — the open standard for human decisions in autonomous agent workflows. Hitl Protocol is an agent skill from LeoYeAI/openclaw-master-skills. HITL Protocol — the open standard for human decisions in autonomous agent workflows.

When should I use Hitl Protocol?

Hitl Protocol fits situations like: make any website agent-ready; handle human-in-the-loop responses in your agent.

How do I install Hitl Protocol in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill hitl-protocol -a claude-code`. Or copy the skill folder (skills/hitl-protocol in LeoYeAI/openclaw-master-skills) into .claude/skills/hitl-protocol in your project. Claude Code loads it when a task matches its description.

How do I install Hitl Protocol in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill hitl-protocol -a codex`. Or copy the skill folder (skills/hitl-protocol in LeoYeAI/openclaw-master-skills) into .agents/skills/hitl-protocol in your project. Codex loads it when a task matches its description.

Can I use Hitl Protocol in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill hitl-protocol -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hitl-protocol, .gemini/skills/hitl-protocol, .github/skills/hitl-protocol and .opencode/skills/hitl-protocol in your project.

What does Hitl Protocol need to run?

SKILL.md names no scripts, command-line tools or credentials: Hitl Protocol is instructions for the agent only. Compatibility (from SKILL.md): ["claude","codex","gemini","openclaw","goose","copilot"].

Does Hitl Protocol access the network?

SKILL.md names 3 domains. In commands or code: api.jobboard.com; the agent is likely to contact it when it follows the instructions. As links in the text: rfc-editor.org and rotorstar.github.io. This is read from the text; nothing was executed.

Is Hitl Protocol safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hitl Protocol use?

Hitl Protocol is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hitl Protocol use?

About 5.3k tokens (SKILL.md is roughly 21k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.9k tokens, read only when the agent opens those files.

What are the alternatives to Hitl Protocol?

Skills that share tags, products or a category with Hitl Protocol: Channel Debug Core (vercel-labs/vercel-openclaw-archived, 117 stars), Frontmcp Channels (agentfront/frontmcp, 146 stars), Integration Webhooks (BuilderIO/agent-native, 7.1k stars) and Chat SDK (databuddy-analytics/Databuddy, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hitl Protocol?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,159 GitHub stars. The repository holds 972 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.