Nexu E2E Test
nexu-io/nexu
A skill your agent uses when verifying OpenClaw gateway fixes end-to-end, testing skill loading after restart, or running integration tests against the local Nexu+OpenClaw stack.
Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing.
Install Discord E2E
$ npx skills add openclaw/openclaw --skill discord-e2e -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install openclaw/openclaw discord-e2e --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/openclaw/openclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/discord-e2e .claude/skills/discord-e2e && 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 "discord-e2e" agent skill from https://github.com/openclaw/openclaw/tree/main/.agents/skills/discord-e2e into .claude/skills/discord-e2e/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "discord-e2e", 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/openclaw/openclaw/tree/main/.agents/skills/discord-e2eType 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 openclaw/openclaw --skill discord-e2e -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install openclaw/openclaw discord-e2e --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openclaw/openclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/discord-e2e .agents/skills/discord-e2e && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "discord-e2e" agent skill from https://github.com/openclaw/openclaw/tree/main/.agents/skills/discord-e2e into .agents/skills/discord-e2e/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "discord-e2e", 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 openclaw/openclaw --skill discord-e2e -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install openclaw/openclaw discord-e2e --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openclaw/openclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/discord-e2e .cursor/skills/discord-e2e && 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 "discord-e2e" agent skill from https://github.com/openclaw/openclaw/tree/main/.agents/skills/discord-e2e into .cursor/skills/discord-e2e/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "discord-e2e", 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/openclaw/openclaw.git --path .agents/skills/discord-e2e--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 openclaw/openclaw --skill discord-e2e -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install openclaw/openclaw discord-e2e --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openclaw/openclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/discord-e2e .gemini/skills/discord-e2e && 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 "discord-e2e" agent skill from https://github.com/openclaw/openclaw/tree/main/.agents/skills/discord-e2e into .gemini/skills/discord-e2e/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "discord-e2e", 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 openclaw/openclaw discord-e2eInstalls 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 openclaw/openclaw --skill discord-e2e -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/openclaw/openclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/discord-e2e .github/skills/discord-e2e && 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 "discord-e2e" agent skill from https://github.com/openclaw/openclaw/tree/main/.agents/skills/discord-e2e into .github/skills/discord-e2e/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "discord-e2e", 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 openclaw/openclaw --skill discord-e2e -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install openclaw/openclaw discord-e2e --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openclaw/openclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/discord-e2e .opencode/skills/discord-e2e && 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 "discord-e2e" agent skill from https://github.com/openclaw/openclaw/tree/main/.agents/skills/discord-e2e into .opencode/skills/discord-e2e/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "discord-e2e", 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
discord-e2e- GitHub stars
- 392k
- Token cost
- ~1.6k tokens
- SKILL.md length
- 757 words
- Files
- 5 (incl. scripts)
- Skills in repo
- 93
- Repo updated
- First seen
- Licence
- MIT
At a glance
Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing.
- Works in 4 steps: Choose the evidence → Prepare and check the current lease → Run one scoped proof → …
- Tasks that involve End-to-end testing
- SKILL.md covers 1. Choose the evidence, 2. Prepare and check the…, 3. Run one scoped proof and 4. Judge and report
- Runs JavaScript scripts from its folder; calls pnpm, node and bunx
What it does
Discord E2E is an agent skill from openclaw/openclaw. Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and Gateway evidence from manual user interactions.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts (for example `bot-api.md`, `features.md` and `runtime.md`).
It sits in Testing & QA, covering End-to-end testing. It works with Discord. The repository describes itself as: The AI that really does things. Any OS. Any Platform. The lobster way. 🦞. The licence is MIT.
When your agent uses it
- Tasks that involve End-to-end testing
Example prompts
- “/discord-e2e”
Requirements
- Node.js
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 1eb5970. 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/ (JavaScript), which the agent can run.
Shell commands in SKILL.md call:
pnpmnodebunx
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
support.discord.com
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.
Context cost
Discord E2E loads about 1.6k tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 757 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.
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); the scripts in this folder are not scanned.
SKILL.md
The full file from openclaw/openclaw at commit 1eb5970, republished under its MIT licence (© openclaw). 757 words, ~1,605 tokens.
Download SKILL.mdSave it as
.claude/skills/discord-e2e/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- discord-e2e
- description
- Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and Gateway evidence from manual user interactions.
Discord E2E
Choose the smallest boundary that proves the requested behavior:
| Goal | Entry point | What it proves |
|---|---|---|
| Check the shared bot pair and channel | Read-only command below | Bot identities, pinned SUT, guild text channel, and history access |
| Exercise bot-authored mutations | Existing channelE2e lifecycle | Owned messages, reactions, files, threads, and cleanup |
| Prove OpenClaw behavior | Existing QA Lab flow | Real Discord events, an isolated SUT Gateway, and the selected model lane |
| Prove human interactions or rendering | Authorized manual Discord client | Actual user action or inspected client capture |
The API probe starts no Gateway, event recorder, or model. QA Lab remains the owner for product E2E: it controls its lease, temporary Gateway, provider, cancellation, and cleanup. Neither path changes app permissions or provisions credentials.
1. Choose the evidence
Read feature recipes for the changed behavior. Native fixture calls prove Discord API operations, not that a model invoked a tool. A SUT round trip additionally proves Gateway ingress and a stored public reply. Model-tool claims also require the tool trace and provider request evidence.
Human slash commands, component clicks, modals, ephemeral interactions, and
human-to-bot DMs need an authorized manual client. A bot posting /status sends
text, not a slash interaction. Use official bot tokens from the lease only.
Discord prohibits user-token/self-bot automation;
Slack's user OAuth route has no equivalent here.
2. Prepare and check the current lease
Use the dependency-ready OpenClaw checkout under test. The setup prerequisite is
an existing authenticated Convex CLI with access to the published QA broker.
The existing shared lease helper discovers the repository's broker binding and
CI credential in memory; you do not need to copy bot tokens, guild IDs, or broker secrets. If authentication
is absent, have the operator run convex login (or the already cached
bunx --no-install convex login) once. Do not install a CLI or log in on the
operator's behalf. Network/permission errors are not evidence that another
login is needed.
For a fast check without QA Lab:
node .agents/skills/discord-e2e/scripts/bot-readiness.mjsThe check is read-only in Discord, but it acquires, renews, and releases a Convex lease. It creates no Discord objects and has no mutation mode. Read bot API readiness for the payload, permission limits, private result, and failure handling.
This probe does not verify Gateway intents, event delivery, model behavior, or all native fixture permissions. For an OpenClaw claim, continue with QA Lab:
pnpm openclaw qa discord --list-scenarios
pnpm openclaw qa discord --doctor \
--output-dir .artifacts/qa-e2e/discord-doctorRequire a passing QA Lab doctor for this lane. It sends no fixture messages; it checks the leased identities, guild text channel, effective permissions, driver Gateway intents, and connected SUT Gateway. Every scenario repeats readiness on its own lease; a released doctor's result never qualifies a later run.
--doctor and --scenario-file default to Convex, CI role, and mock-openai.
Existing explicit credential/provider flags still work; ordinary curated
qa discord defaults remain unchanged. Preprovisioned private broker environment
variables are an alternative to discovery, not a prerequisite.
Show full SKILL.md (288 more words)Show less
3. Run one scoped proof
For a native lifecycle plus real Gateway reply:
pnpm openclaw qa discord \
--scenario-file qa/scenarios/channels/discord-e2e-lifecycle.yaml \
--output-dir .artifacts/qa-e2e/discord-lifecycleFor a changed feature, adapt that YAML using feature recipes.
--scenario-file is repeatable and uses the existing QA flow schema. Set
retryCount: 0 for native write scenarios. Use a new output directory for each
proof. These examples are opt-in, not additions to the curated default suite.
Read runtime and recovery when changing config, restarting the SUT, choosing a real provider, diagnosing cancellation, or reconciling failed cleanup.
4. Judge and report
For the API probe, require status: ready and leaseReleased: true.
An empty history list is inconclusive (exit 2): it can mean an empty channel
or missing Read Message History permission. Use QA Lab doctor to distinguish
those cases; do not call either one a proven permission failure.
Report a ready result as bot identity and observed read-access proof, not
mutation or Gateway E2E. Private result.json contains leased identities and
check statuses, not tokens or history.
For QA Lab, inspect qa-suite-summary.json, qa-suite-report.md, the Gateway/provider
artifacts, and each private discord-e2e-*/events.ndjson under the output directory.
Join native receipts to recorder rows by message ID; use actor: sut, channel,
sequence, and trigger correlation for SUT claims. A marker alone does not prove
edits, reactions, typing, deletion, formatting, or a model tool call. Event logs
are not visual proof; visual claims need an actual Discord client screenshot.
Completion requires the requested evidence and successful owned cleanup after Gateway stop, before lease release. Existing permissions decide whether owned threads are deleted or archived; report the recorded disposition, never call archival deletion. Preserve private evidence on failure. Report the sanitized command, exact revision, claim, relevant evidence, manual-only gaps, and cleanup outcome. Redact identities, unrelated content, private paths, and credentials before sharing artifacts.
© openclaw, MIT. 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 4 other files (scripts) in .agents/skills/discord-e2e of openclaw/openclaw.
- SKILL.md
- bot-api.md
- features.md
- runtime.md
- scripts/bot-readiness.mjs
Open the folder on GitHubat commit 1eb5970
Compare with similar skills
Discord E2E 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 |
|---|---|---|---|---|---|---|
| Discord E2E this skillopenclaw/openclaw | 392k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Nexu E2E Testnexu-io/nexu | 3.3k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Openclaw Parallels SmokeSafeAI-Lab-X/ClawKeeper | 1k | — | ~1.1k | Automated safety check: Pass | None | |
| Electron App Automationvercel-labs/agent-browser | 44k | 5 repos | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Web Application Testinganthropics/skills | 180k | 51 repos | ~966 | Automated safety check: Pass | Apache-2.0 | |
| TDD WorkflowhellangleZ/burn-in-cceverywhere-ralph | 112 | 11 repos | ~2.4k | Automated safety check: Pass | None |
Similar skills
Openclaw Parallels Smoke
SafeAI-Lab-X/ClawKeeper
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests.
- Official
Electron App Automation
vercel-labs/agent-browser
Automates Electron desktop apps such as VS Code, Slack or Discord by connecting agent-browser to their Chrome DevTools Protocol port.
- Official
Web Application Testing
anthropics/skills
Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.
TDD Workflow
hellangleZ/burn-in-cceverywhere-ralph
A skill your agent uses when writing new features, fixing bugs, or refactoring code.
Uloop Replay Input
kurotu/VRCQuestTools
Replay recorded PlayMode keyboard and mouse input. An agent skill from kurotu/VRCQuestTools.
More from openclaw/openclaw
All 93 skills in this repoOpenclaw Live Updater
openclaw/openclaw
Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation.
Tmux
openclaw/openclaw
Control tmux sessions/panes for interactive CLIs: list, capture output, send keys, paste text, monitor prompts.
Feishu Doc
openclaw/openclaw
Feishu document read/write workflows. An agent skill from openclaw/openclaw.
Openclaw PR Maintainer
openclaw/openclaw
Review, triage, repair, or land OpenClaw issues and pull requests with current-source evidence and the native maintainer workflow.
Browser Automation
openclaw/openclaw
A skill your agent uses when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.
Clawsweeper
openclaw/openclaw
A skill your agent uses for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed…
Related
Works with
Categories
Questions about Discord E2E
What does Discord E2E do?
Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Discord E2E is an agent skill from openclaw/openclaw. Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing.
When should I use Discord E2E?
Discord E2E fits situations like: tasks that involve End-to-end testing.
How do I install Discord E2E in Claude Code?
Run `npx skills add openclaw/openclaw --skill discord-e2e -a claude-code`. Or copy the skill folder (.agents/skills/discord-e2e in openclaw/openclaw) into .claude/skills/discord-e2e in your project. Claude Code loads it when a task matches its description.
How do I install Discord E2E in Codex?
Run `npx skills add openclaw/openclaw --skill discord-e2e -a codex`. Or copy the skill folder (.agents/skills/discord-e2e in openclaw/openclaw) into .agents/skills/discord-e2e in your project. Codex loads it when a task matches its description.
Can I use Discord E2E 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 openclaw/openclaw --skill discord-e2e -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/discord-e2e, .gemini/skills/discord-e2e, .github/skills/discord-e2e and .opencode/skills/discord-e2e in your project.
What does Discord E2E need to run?
Going by SKILL.md and its folder, Discord E2E needs JavaScript for the scripts in its folder and the command-line tools its instructions call (pnpm, node and bunx). Our summary lists: Node.js.
Does Discord E2E access the network?
SKILL.md names 1 domain. As links in the text: support.discord.com. This is read from the text; nothing was executed.
Is Discord E2E 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Discord E2E use?
Discord E2E 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 Discord E2E use?
About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Discord E2E?
Skills that share tags, products or a category with Discord E2E: Nexu E2E Test (nexu-io/nexu, 3.3k stars), Openclaw Parallels Smoke (SafeAI-Lab-X/ClawKeeper, 1k stars), Electron App Automation (vercel-labs/agent-browser, 44k stars) and Web Application Testing (anthropics/skills, 180k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Discord E2E?
openclaw (a GitHub organization) maintains it in openclaw/openclaw, which has 391,610 GitHub stars. The repository holds 93 skills in this directory. The repository was last updated on October 8, 2026.
Source: openclaw/openclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.