Channel Debug Core
vercel-labs/vercel-openclaw-archived
Channel webhook triage for vercel-openclaw Slack/Telegram/Discord/WhatsApp issues: prove deployment state, collect admin readiness endpoints, build evidence-first handoff before fixes.
HITL Protocol — the open standard for human decisions in autonomous agent workflows.
$ npx skills add LeoYeAI/openclaw-master-skills --skill hitl-protocol -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills hitl-protocol --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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-srcUse ~/.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/
Install the "hitl-protocol" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/hitl-protocol into .claude/skills/hitl-protocol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hitl-protocol", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/hitl-protocolType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill hitl-protocol -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills hitl-protocol --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/hitl-protocol .agents/skills/hitl-protocol && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "hitl-protocol" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/hitl-protocol into .agents/skills/hitl-protocol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hitl-protocol", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill hitl-protocol -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills hitl-protocol --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/hitl-protocol .cursor/skills/hitl-protocol && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "hitl-protocol" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/hitl-protocol into .cursor/skills/hitl-protocol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hitl-protocol", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/hitl-protocol--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill hitl-protocol -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills hitl-protocol --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/hitl-protocol .gemini/skills/hitl-protocol && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "hitl-protocol" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/hitl-protocol into .gemini/skills/hitl-protocol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hitl-protocol", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills hitl-protocolInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill hitl-protocol -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/hitl-protocol .github/skills/hitl-protocol && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "hitl-protocol" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/hitl-protocol into .github/skills/hitl-protocol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hitl-protocol", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill hitl-protocol -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills hitl-protocol --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/hitl-protocol .opencode/skills/hitl-protocol && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "hitl-protocol" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/hitl-protocol into .opencode/skills/hitl-protocol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "hitl-protocol", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
hitl-protocolHITL 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 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.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
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.
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.
Hosts in commands or code, which the agent is likely to contact:
api.jobboard.comAlso links to:
rfc-editor.orgrotorstar.github.ioFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
["claude","codex","gemini","openclaw","goose","copilot"]
From compatibility in the SKILL.md frontmatter.
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.
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.
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.
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.
.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.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.
| Your role | You want to... | Read |
|---|---|---|
| Service/website builder | Add HITL endpoints to your API so agents can request human input | Service Integration Guide |
| Agent developer | Handle HTTP 202 + HITL responses from services | Agent Integration Guide |
| Both / Learning | Understand the full protocol | Continue reading below |
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 | Details |
|---|---|
| Review types | approval, selection, input, confirmation, escalation |
| Form field types | text, textarea, number, date, email, url, boolean, select, multiselect, range, custom x-* |
| Transport | Polling (required), SSE (optional), Callback/Webhook (optional) |
| Inline submit | submit_url + native messaging buttons (Telegram, Slack, Discord, WhatsApp, Teams) — service opt-in |
| States | pending → opened → in_progress → completed / expired / cancelled |
| Security | Opaque tokens (43 chars, base64url, 256-bit entropy), SHA-256 hash storage, timing-safe comparison, HTTPS only |
| Multi-round | previous_case_id / next_case_id for iterative edit cycles (Approval type) |
| Forms | Single-step fields, multi-step wizard, conditional visibility, validation rules, progress tracking |
| Timeouts | ISO 8601 duration, default_action: skip / approve / reject / abort |
| Discovery | .well-known/hitl.json, SKILL.md metadata.hitl extension |
| Reminders | reminder_at timestamps, review.reminder SSE event |
| Rate limiting | 60 requests/min per case on poll endpoint, Retry-After header |
| Type | Actions | Multi-round | Form fields | Use case |
|---|---|---|---|---|
| Approval | approve, edit, reject | Yes | No | Artifact review (CV, email, deployment plan) |
| Selection | select | No | No | Choose from options (job listings, targets) |
| Input | submit | No | Yes | Structured data entry (salary, dates, preferences) |
| Confirmation | confirm, cancel | No | No | Irreversible action gate (send emails, deploy) |
| Escalation | retry, skip, abort | No | No | Error recovery (deployment failed, API error) |
When a service needs human input, it returns HTTP 202 with this structure:
{
"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"
}
}
}| Field | Type | Description |
|---|---|---|
spec_version | "0.7" | Protocol version |
case_id | string | Unique, URL-safe identifier (pattern: review_{random}) |
review_url | URL | HTTPS URL to review page with opaque bearer token |
poll_url | URL | Status polling endpoint |
type | enum | approval / selection / input / confirmation / escalation / x-* |
prompt | string | What the human needs to decide (max 500 chars) |
created_at | datetime | ISO 8601 creation timestamp |
expires_at | datetime | ISO 8601 expiration timestamp |
| Field | Type | Description |
|---|---|---|
timeout | duration | How long the review stays open (24h, PT24H, P7D) |
default_action | enum | skip / approve / reject / abort — action on expiry |
callback_url | URL / null | Echoed callback URL if agent provided one |
events_url | URL | SSE endpoint for real-time status events |
context | object | Arbitrary data for the review page (not processed by agent) |
reminder_at | datetime / datetime[] | When to re-send the review URL |
previous_case_id | string | Links to prior case in multi-round chain |
surface | object | UI format declaration (format, version) |
submit_url | URL | Agent-submit endpoint for channel-native inline buttons (v0.7) |
submit_token | string | Bearer token for submit_url authentication (required if submit_url set) |
inline_actions | string[] | Actions permitted via submit_url (e.g. ["confirm", "cancel"]). If absent, all actions for the type are allowed. |
{
"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).
| Status | Terminal | Description | Key fields |
|---|---|---|---|
pending | No | Case created, human hasn't opened URL | expires_at |
opened | No | Human opened the review URL | opened_at |
in_progress | No | Human is interacting with the form | progress (optional) |
completed | Yes | Human submitted response | result, completed_at, responded_by |
expired | Yes | Timeout reached | expired_at, default_action |
cancelled | Yes | Human clicked cancel | cancelled_at, reason |
+---------------------------------------------+
| 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.
Return HTTP 202 when human input is needed:
// 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.
Handle HTTP 202 responses — ~15 lines:
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"):
breakNo SDK. No UI rendering. Just HTTP + URL forwarding + polling. See Agent Integration Guide for inline submit, SSE, callbacks, multi-round, and edge cases.
| Transport | Agent needs public endpoint? | Real-time? | Complexity |
|---|---|---|---|
| Polling (default) | No | No | Minimal |
| SSE (optional) | No | Yes | Low |
| Callback (optional) | Yes | Yes | Medium |
Polling is the baseline — every HITL-compliant service MUST support it. SSE and callbacks are optional enhancements.
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 type | Inline possible? | Reason |
|---|---|---|
| Confirmation | Yes | 2 buttons: Confirm / Cancel |
| Escalation | Yes | 3 buttons: Retry / Skip / Abort |
| Approval (simple) | Yes | 2 buttons: Approve / Reject (without edit) |
| Approval (with edit) | URL only | Edit requires rich UI |
| Selection | URL only | Needs list/cards UI |
| Input | URL only | Needs 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.
submit_url).Services that use HITL can declare support in their own SKILL.md frontmatter:
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.
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:
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:
## 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.
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:
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:
| Field | Type | Description |
|---|---|---|
field | string | Which data field can be improved |
issue | string | What is missing or suboptimal |
agent_action | string | Exact question/action for the agent to take |
impact | string | Human-readable benefit (e.g. "+25 quality points") |
priority | "high" / "medium" / "low" | Order of importance |
Agent behavior:
improvement_suggestions is empty or maxAttempts reachedSee Agent Checklist — Quality Improvement Loop and Example 13.
This protocol and skill documentation are aligned with these core RFCs:
202 Accepted, conditional requests, retry behavior)MUST, SHOULD, MAY)For the complete implementation matrix, see README RFC Alignment.
© 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
SKILL.md and 7 other files (references) in skills/hitl-protocol of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Hitl Protocol this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~5.3k | Automated safety check: Pass | Apache-2.0 | |
| Channel Debug Corevercel-labs/vercel-openclaw-archived | 117 | — | ~2k | Automated safety check: Notes | MIT | |
| Frontmcp Channelsagentfront/frontmcp | 146 | — | ~3.7k | Automated safety check: Pass | Apache-2.0 | |
| Integration WebhooksBuilderIO/agent-native | 7.1k | — | ~5.3k | Automated safety check: Pass | None | |
| Chat SDKdatabuddy-analytics/Databuddy | 1.2k | — | ~2.6k | Automated safety check: Pass | AGPL-3.0 | |
| Add Channel Connect Buttonnovuhq/novu | 40k | — | ~1.6k | Automated safety check: Pass | Custom licence |
vercel-labs/vercel-openclaw-archived
Channel webhook triage for vercel-openclaw Slack/Telegram/Discord/WhatsApp issues: prove deployment state, collect admin readiness endpoints, build evidence-first handoff before fixes.
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.
BuilderIO/agent-native
Cross-platform pattern for handling messaging integration webhooks (Slack, Telegram, WhatsApp, email, etc.) on serverless hosts.
databuddy-analytics/Databuddy
Build multi-platform chat bots with Chat SDK (chat npm package).
novuhq/novu
Build a new channel Connect button (e.g. An agent skill from novuhq/novu.
letta-ai/lettabot
Set up and run LettaBot - a multi-channel AI assistant for Telegram, Slack, Discord, WhatsApp, and Signal.
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.
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.
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.
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.
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.
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.
Categories
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.
Hitl Protocol fits situations like: make any website agent-ready; handle human-in-the-loop responses in your agent.
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.
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.
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.
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"].
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.
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.
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.
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.
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.
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.