Official agent skill

Channel Debug Core

by vercel-labs in 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.

OfficialMITAuto-check: notesBackend & APIs

Install Channel Debug Core

skills CLI

$ npx skills add vercel-labs/vercel-openclaw-archived --skill channel-debug-core -a claude-code

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

GitHub CLI

$ gh skill install vercel-labs/vercel-openclaw-archived channel-debug-core --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/vercel-labs/vercel-openclaw-archived.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/channel-debug-core .claude/skills/channel-debug-core && 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/

Paste into Claude Code

Install the "channel-debug-core" agent skill from https://github.com/vercel-labs/vercel-openclaw-archived/tree/main/.agents/skills/channel-debug-core into .claude/skills/channel-debug-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "channel-debug-core", 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

$skill-installer install https://github.com/vercel-labs/vercel-openclaw-archived/tree/main/.agents/skills/channel-debug-core

Type 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.

skills CLI

$ npx skills add vercel-labs/vercel-openclaw-archived --skill channel-debug-core -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install vercel-labs/vercel-openclaw-archived channel-debug-core --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/vercel-labs/vercel-openclaw-archived.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/channel-debug-core .agents/skills/channel-debug-core && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "channel-debug-core" agent skill from https://github.com/vercel-labs/vercel-openclaw-archived/tree/main/.agents/skills/channel-debug-core into .agents/skills/channel-debug-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "channel-debug-core", 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.

skills CLI

$ npx skills add vercel-labs/vercel-openclaw-archived --skill channel-debug-core -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install vercel-labs/vercel-openclaw-archived channel-debug-core --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/vercel-labs/vercel-openclaw-archived.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/channel-debug-core .cursor/skills/channel-debug-core && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "channel-debug-core" agent skill from https://github.com/vercel-labs/vercel-openclaw-archived/tree/main/.agents/skills/channel-debug-core into .cursor/skills/channel-debug-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "channel-debug-core", 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

$ gemini skills install https://github.com/vercel-labs/vercel-openclaw-archived.git --path .agents/skills/channel-debug-core

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add vercel-labs/vercel-openclaw-archived --skill channel-debug-core -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install vercel-labs/vercel-openclaw-archived channel-debug-core --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/vercel-labs/vercel-openclaw-archived.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/channel-debug-core .gemini/skills/channel-debug-core && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "channel-debug-core" agent skill from https://github.com/vercel-labs/vercel-openclaw-archived/tree/main/.agents/skills/channel-debug-core into .gemini/skills/channel-debug-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "channel-debug-core", 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.

GitHub CLI

$ gh skill install vercel-labs/vercel-openclaw-archived channel-debug-core

Installs 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).

skills CLI

$ npx skills add vercel-labs/vercel-openclaw-archived --skill channel-debug-core -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/vercel-labs/vercel-openclaw-archived.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/channel-debug-core .github/skills/channel-debug-core && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "channel-debug-core" agent skill from https://github.com/vercel-labs/vercel-openclaw-archived/tree/main/.agents/skills/channel-debug-core into .github/skills/channel-debug-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "channel-debug-core", 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.

skills CLI

$ npx skills add vercel-labs/vercel-openclaw-archived --skill channel-debug-core -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install vercel-labs/vercel-openclaw-archived channel-debug-core --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/vercel-labs/vercel-openclaw-archived.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/channel-debug-core .opencode/skills/channel-debug-core && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "channel-debug-core" agent skill from https://github.com/vercel-labs/vercel-openclaw-archived/tree/main/.agents/skills/channel-debug-core into .opencode/skills/channel-debug-core/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "channel-debug-core", 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.

Facts

Skill name: channel-debug-core
GitHub stars: 117
Token cost: ~2k tokens
SKILL.md length: 849 words
Files: 5 (incl. scripts, references)
Skills in repo: 16
Repo updated: May 15, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

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

Works in 4 steps: Deployment-state proof. → Runtime path diagram with each edge… → Hypothesis table with fastest falsifier… → …
Tasks that involve Deployment
SKILL.md covers Non-Negotiables, Parallel First Rule, Project Targeting Preflight and Required Admin Surfaces, plus 8 more sections
Runs Shell scripts from its folder; calls npx, git and curl; needs ADMIN_SECRET

What it does

Channel Debug Core is an agent skill from vercel-labs/vercel-openclaw-archived, published by the product's own GitHub organization. Channel webhook triage for vercel-openclaw Slack/Telegram/Discord/WhatsApp issues: prove deployment state, collect admin readiness endpoints, build evidence-first handoff before fixes.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/handoff-template.md`, `references/readiness-glossary.md` and `references/terminal-path-checklist.md`).

It sits in Backend & APIs, covering Deployment and Webhooks. It works with Vercel, Discord, Slack and Telegram. The repository describes itself as: Deploy OpenClaw on Vercel. The licence is MIT.

When your agent uses it

Tasks that involve Deployment
Tasks that involve Webhooks

Example prompts

“/channel-debug-core”

Requirements

Node.js
A Bash shell
A credential in ADMIN_SECRET

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

Deployment-state proof.
Runtime path diagram with each edge marked unknown, verified-good, or verified-bad.
Hypothesis table with fastest falsifier and status.
Channel Specialist Handoff.

What it can do on your machine

Read from SKILL.md and the folder at commit d592f7b. 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
Ships 1 file in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
- npx
- git
- curl
- node
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npx, git and curl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- ADMIN_SECRET
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Channel Debug Core loads about 2k tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 51 tokens; SKILL.md has 849 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~51
When it runs · the whole SKILL.md, loaded when a task matches: ~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~3.7k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NoteMentions a .env fileSKILL.md:96

es a release-specific env file, such as `.env.45`, use it only to investigate that release's live run.

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); the scripts in this folder are not scanned.

SKILL.md

The full file from vercel-labs/vercel-openclaw-archived at commit d592f7b, republished under its MIT licence (© vercel-labs). 849 words, ~2,001 tokens.

Download SKILL.mdSave it as .claude/skills/channel-debug-core/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.

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

Channel Debug Core

Use this skill for any Slack, Telegram, Discord, or WhatsApp delivery issue.

Non-Negotiables

Before proposing a fix, produce:

Deployment-state proof.
Runtime path diagram with each edge marked unknown, verified-good, or verified-bad.
Hypothesis table with fastest falsifier and status.
Channel Specialist Handoff.

Do not write "most likely" twice. Gather direct evidence.

Parallel First Rule

For live deployments, channel debugging starts with parallel lanes. The parent agent creates one artifact root and launches these lanes before any patch proposal:

Lane	Agent role	Evidence focus
Vercel/app logs	`channel_vercel_logs`	Project targeting proof, deployment proof, admin readiness JSON, Vercel runtime logs, request/delivery correlation
Sandbox runtime	`channel_sandbox_runtime`	`npx sandbox` or app admin SSH fallback, process/port/config/log evidence
Workflow state	`channel_workflow_state`	Project targeting proof, `npx workflow inspect runs --backend vercel`, drain workflow state, fallback log correlation
Channel specialist	`channel_<channel>`	Channel route semantics, signatures/raw body, dedup, boot message, terminal-path audit

No fix may be proposed until the merge gate is satisfied:

Each lane has returned a handoff, or the lane is marked unavailable with the attempted fallback.
At least one runtime edge is verified-bad.
Contradictory lane evidence has been added to the hypothesis table.
Prior known fixes have been compared against current evidence.

Project Targeting Preflight

Before any vercel, npx sandbox, or npx workflow investigation, prove the command is targeting the intended Vercel project and team.

Always inspect .vercel/project.json and compare it to the incident target. If they differ, do not rely on inferred project context. Use explicit project/team/deployment targeting and record the mismatch in the handoff.

Known sharp edge: this repo may be linked to release 45 in .vercel/project.json (projectName: vercel-openclaw-45, projectId: prj_ag6Uzj9b4deNK98jVS5SO0H2Shmx). For release 46, use explicit target context (projectName: vercel-openclaw-46, projectId: prj_JSzrXyJiMzT6F7BUA76Naa7nkjRa, team vercel-internal-playground) rather than trusting .vercel inference.

If a tool prints that it inferred the project from .vercel, treat the output as suspect until the inferred project is proven to match the incident target. This is especially important for npx workflow, which can silently inspect the wrong project when run from a repo linked to a different release.

Required Admin Surfaces

Collect these first:

bash

GET /api/admin/why-not-ready
GET /api/channels/summary
GET /api/admin/sandbox-diag
GET /api/admin/logs

Save the raw JSON before continuing. Logs are a ring buffer and can evict important events.

Readiness Triad

Report these separately:

route-ready: platform route/native route appears registered.
native-accepted: lastForward.ok true with classification:"accepted", or equivalent handler acceptance evidence.
user-visible-reply: real user saw a Slack/Telegram/Discord/WhatsApp reply or status update.

Never collapse these into connected.

Deployment Proof

Run or request equivalent evidence:

bash

git rev-parse HEAD
git ls-remote origin main
curl "$URL/api/admin/sandbox-diag"

If the deployed runtime cannot be tied to the source being read, say so and stop code-level conclusions.

Evidence Artifact Rule

Write evidence under:

text

.agent-runs/channel-debug/<timestamp>/<channel>/

Do not commit runtime evidence. Redact admin secrets, bypass secrets, bot tokens, webhook secrets, and platform access tokens.

Release Env Files

When the incident references a release-specific env file, such as .env.45, use it only to investigate that release's live run.

Allowed uses:

deployment URL / app URL
Vercel project/team/deployment context
Vercel token for logs/workflow/sandbox CLI
ADMIN_SECRET
Deployment Protection bypass
platform credentials required to verify the specific channel run

Rules:

Source the file; do not print it.
Do not copy it into artifacts.
Do not include raw values in handoffs.
Record only the file name and variable names used.
Treat env files as credential/context input, not deployment proof. Deployment proof still comes from git, project targeting proof, and live runtime signals.

Show full SKILL.md (295 more words)Show less

Sandbox Runtime Probe

The sandbox lane must first identify the actual Vercel Sandbox runtime ID. Use /api/admin/sandbox-diag and /api/channels/summary before CLI access.

If the ID is oc-prj*, prj_*, OPENCLAW_INSTANCE_ID, or VERCEL_PROJECT_ID, do not pass it as <sandbox_id> to sandbox exec or sandbox connect.

When npx sandbox / sandbox works, collect read-only evidence:

bash

sandbox exec "$SANDBOX_ID" sh -lc '
  set -eu
  echo "== process =="
  ps -eo pid,ppid,comm,args | grep -E "[o]penclaw|[n]ode" || true
  echo "== ports =="
  (ss -ltnp || netstat -ltnp) 2>/dev/null | grep -E ":(3000|8787)\\b" || true
  echo "== openclaw logs =="
  tail -200 /tmp/openclaw/openclaw-*.log 2>/dev/null || true
'

For config, print only shape, never secrets:

bash

sandbox exec "$SANDBOX_ID" node - <<'NODE'
const fs = require("fs");
const p = "/home/vercel-sandbox/.openclaw/openclaw.json";
const j = JSON.parse(fs.readFileSync(p, "utf8"));
console.log(JSON.stringify({
  channels: Object.keys(j.channels || {}),
  pluginAllow: j.plugins?.allow || null,
  hasSlack: Boolean(j.channels?.slack),
  hasTelegram: Boolean(j.channels?.telegram),
  hasDiscord: Boolean(j.channels?.discord),
  hasWhatsApp: Boolean(j.channels?.whatsapp),
}, null, 2));
NODE

If CLI access fails because the ID is incompatible or auth cannot resolve the sandbox, save the CLI failure and switch to the app admin SSH/exec fallback. The fallback must run the same read-only probes.

Workflow State Probe

The workflow lane must inspect Vercel Workflow state before treating the workflow path as healthy or broken:

bash

npx workflow inspect runs --backend vercel > "$ART/workflow/runs.txt" 2> "$ART/workflow/runs.stderr.txt"

Correlate by channel, incident time, request ID, delivery ID, platform event ID, and drainChannelWorkflow.

Collect workflow run ID, status, current/last step, retry count or repeated step evidence, terminal error, whether native forward attempts happened, and whether channels.forward_outcome was written.

If npx workflow is unavailable or cannot inspect Vercel state, save the failure and fall back to Vercel logs filtered to workflow/channel events, /api/admin/logs, and /api/channels/summary.lastForward. Do not use local workflow data as evidence for production behavior.

Prior Fix Comparison

Before proposing a patch, compare current evidence to known prior fixes and failure signatures:

Prior fix / failure mode	Current matching evidence	Current contradicting evidence	Match?
openclaw-42 zero-plugin gateway wedge
stale sandbox public URL / sandbox-not-listening
workflow retry exhaustion
route-ready vs native-accepted mismatch
recent accepted-forward override of stale configSync failure
channel-specific signature/raw-body/secret issue

A repeated operator-facing message is not enough. Match on runtime signals: status codes, route probes, process/log evidence, Workflow state, and lastForward.

Fallback When Live Access Is Unavailable

If you cannot call the deployed endpoints, produce a static code-path audit and mark runtime edges unknown. Do not claim runtime behavior from code alone.

Files

SKILL.md and 4 other files (scripts, references) in .agents/skills/channel-debug-core of vercel-labs/vercel-openclaw-archived.

SKILL.md
references/handoff-template.md
references/readiness-glossary.md
references/terminal-path-checklist.md
scripts/collect-channel-evidence.sh

Open the folder on GitHubat commit d592f7b

Compare with similar skills

Channel Debug Core 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.

Channel Debug Core compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Channel Debug Core this skillvercel-labs/vercel-openclaw-archived	117	—	~2k	Automated safety check: Notes	MIT	4 mo ago
Frontmcp Channelsagentfront/frontmcp	146	—	~3.7k	Automated safety check: Pass	Apache-2.0	yesterday
Integration WebhooksBuilderIO/agent-native	7.1k	—	~5.3k	Automated safety check: Pass	None	today
Hitl ProtocolLeoYeAI/openclaw-master-skills	2.2k	—	~5.3k	Automated safety check: Pass	Apache-2.0	2 mo ago
Add Channel Connect Buttonnovuhq/novu	40k	—	~1.6k	Automated safety check: Pass	Custom licence	today
Workspace APIfriday-platform/friday-studio	104	—	~9.3k	Automated safety check: Notes	Custom licence	1 mo ago

Similar skills

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
Hitl Protocol
LeoYeAI/openclaw-master-skills
HITL Protocol — the open standard for human decisions in autonomous agent workflows.
2.2k GitHub stars~5.3k tokensUpdated 2 mo ago
Agent WorkflowsAuto-check passed
Add Channel Connect Button
novuhq/novu
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
Workspace API
friday-platform/friday-studio
Create, list, update, delete, and clean up workspaces via the daemon HTTP API at $FRIDAYDURL.
104 GitHub stars~9.3k tokensUpdated 1 mo ago
Backend & APIsAuto-check: notes
Configure Notifications
yangyuan-zhen/PolyWeather
[OMX] Configure OMX notifications - unified entry point for all platforms
315 GitHub stars~2.7k tokensUpdated 17 days ago
Backend & APIsAuto-check passed

More from vercel-labs/vercel-openclaw-archived

All 16 skills in this repo

Lat Md
vercel-labs/vercel-openclaw-archived
Official
Writing and maintaining lat.md documentation files — structured markdown that describes a project's architecture, design decisions, and test specs.
117 GitHub starsUsed in 1 repo~1.2k tokens
Auto-check passed
Cron Watchdog Debug
vercel-labs/vercel-openclaw-archived
Official
Cron and watchdog debugging for vercel-openclaw: Vercel Cron auth, persisted OpenClaw jobs, cron wake keys, token refresh, restore oracle, hot spare, and watchdog reports.
117 GitHub stars~1.6k tokensUpdated 4 mo ago
Auto-check passed
Auth Store Debug
vercel-labs/vercel-openclaw-archived
Official
Auth and store debugging for vercel-openclaw: admin-secret mode, Sign in with Vercel, session cookies, CSRF, LOCALREADONLY, Redis vs memory store, keyspace namespacing, and metadata shape migrations.
117 GitHub stars~465 tokensUpdated 4 mo ago
Auto-check passed
Firewall AI Gateway Debug
vercel-labs/vercel-openclaw-archived
Official
Firewall and Vercel AI Gateway debugging for vercel-openclaw: network policy allowlists, OIDC token refresh, AI Gateway transform rules, firewall learning/enforcement, and sandbox.update…
117 GitHub stars~550 tokensUpdated 4 mo ago
Auto-check passed
Gateway Proxy Debug
vercel-labs/vercel-openclaw-archived
Official
Gateway and proxy debugging for vercel-openclaw: /gateway routing, HTML injection, WebSocket rewrite, gateway-token handoff, waiting page, status heartbeat, sandbox port URL cache, and proxy auth.
117 GitHub stars~573 tokensUpdated 4 mo ago
Auto-check passed
Openclaw Bootstrap Debug
vercel-labs/vercel-openclaw-archived
Official
OpenClaw bootstrap, bundle, config, and restore-asset debugging for vercel-openclaw: openclaw.bundle sidecars, plugin discovery, channel catalog, restart scripts, config hashes, dynamic resume…
117 GitHub stars~494 tokensUpdated 4 mo ago
Auto-check passed

Works with

Questions about Channel Debug Core

What does Channel Debug Core do?

Channel webhook triage for vercel-openclaw Slack/Telegram/Discord/WhatsApp issues: prove deployment state, collect admin readiness endpoints, build evidence-first handoff before fixes. Channel Debug Core is an agent skill from vercel-labs/vercel-openclaw-archived, published by the product's own GitHub organization. Channel webhook triage for vercel-openclaw Slack/Telegram/Discord/WhatsApp issues: prove deployment state, collect admin readiness endpoints, build evidence-first handoff before fixes.

When should I use Channel Debug Core?

Channel Debug Core fits situations like: tasks that involve Deployment; tasks that involve Webhooks.

How do I install Channel Debug Core in Claude Code?

Run `npx skills add vercel-labs/vercel-openclaw-archived --skill channel-debug-core -a claude-code`. Or copy the skill folder (.agents/skills/channel-debug-core in vercel-labs/vercel-openclaw-archived) into .claude/skills/channel-debug-core in your project. Claude Code loads it when a task matches its description.

How do I install Channel Debug Core in Codex?

Run `npx skills add vercel-labs/vercel-openclaw-archived --skill channel-debug-core -a codex`. Or copy the skill folder (.agents/skills/channel-debug-core in vercel-labs/vercel-openclaw-archived) into .agents/skills/channel-debug-core in your project. Codex loads it when a task matches its description.

Can I use Channel Debug Core 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 vercel-labs/vercel-openclaw-archived --skill channel-debug-core -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/channel-debug-core, .gemini/skills/channel-debug-core, .github/skills/channel-debug-core and .opencode/skills/channel-debug-core in your project.

What does Channel Debug Core need to run?

Going by SKILL.md and its folder, Channel Debug Core needs a shell for the scripts in its folder, the command-line tools its instructions call (npx, git, curl and node) and credentials named ADMIN_SECRET. Our summary lists: Node.js; A Bash shell; A credential in ADMIN_SECRET.

Does Channel Debug Core access the network?

SKILL.md contains no URLs. Its commands use npx, git and curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Channel Debug Core safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Channel Debug Core use?

Channel Debug Core is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Channel Debug Core use?

About 2k tokens (SKILL.md is roughly 8k 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 1.7k tokens, read only when the agent opens those files.

What are the alternatives to Channel Debug Core?

Skills that share tags, products or a category with Channel Debug Core: Frontmcp Channels (agentfront/frontmcp, 146 stars), Integration Webhooks (BuilderIO/agent-native, 7.1k stars), Hitl Protocol (LeoYeAI/openclaw-master-skills, 2.2k stars) and Add Channel Connect Button (novuhq/novu, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Channel Debug Core?

vercel-labs (a GitHub organization, an official publisher) maintains it in vercel-labs/vercel-openclaw-archived, which has 117 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on May 15, 2026.

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

Install Channel Debug Core

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Channel Debug Core

Non-Negotiables

Parallel First Rule

Project Targeting Preflight

Required Admin Surfaces

Readiness Triad

Deployment Proof

Evidence Artifact Rule

Release Env Files

Sandbox Runtime Probe

Workflow State Probe

Prior Fix Comparison

Fallback When Live Access Is Unavailable

Files

Compare with similar skills

Similar skills

More from vercel-labs/vercel-openclaw-archived

Related

Questions about Channel Debug Core