What does this skill do, and when should you use it?
TweetClaw is an OpenClaw plugin that exposes the Xquik X/Twitter API as agent-callable tools. It ships a free local `explore` catalog search and an optional `tweetclaw` endpoint-invocation tool spanning 102 agent-callable endpoints across 9 categories. Writes, private reads, paid calls, and bulk operations all require explicit per-call approval, and dashboard-sensitive routes are hard-blocked. Xquik is an independent third party, not affiliated with X Corp. Access is via an account-backed API key (33 paid-read routes) or accountless MPP mode (7 direct read routes).
- Searches the local endpoint catalog via
explorefor paths, methods, parameters, response shapes, and MPP prices - Invokes catalog endpoints via
tweetclaw: tweet search, user lookup, timelines, articles, trends, bookmarks, notifications - Performs approved writes: post, reply, like, retweet, follow, DM, profile changes, using idempotency keys
- Runs extractions: follower/following exports, community/list/Space exports, giveaway draws
- Creates monitors and polls every 60 seconds for new tweet, reply, quote, or retweet events with webhooks
- Provides instant /xstatus and /xtrends commands that need no LLM
- Community managers pulling candidate replies by keyword or mention and exporting followers before a giveaway draw
- Marketing teams monitoring accounts or keywords for new tweets with webhook event delivery
- Content creators looking up tweets, profiles, trends, and articles to draft and refine posts
- Agent developers letting their OpenClaw agent post, reply, or manage follows behind per-call approval
- Analysts batch-exporting tweet media or querying regional X trends by WOEID
- Standalone scripts outside OpenClaw — installation, configuration, and approvals depend on the OpenClaw CLI
- Browser navigation, analytics dashboards, scheduled future posts, or X ads — explicitly listed as unsupported in SKILL.md
- Teams wanting fully unattended posting — every write requires fresh human approval
How do you install this skill?
- Core function depends entirely on the overseas paid service xquik.com; mainland-China reachability is unverified and no Chinese-language support is declared.
- Pay-per-use billing: bulk exports and monitor polling accrue ongoing cost — always set cost ceilings and require per-call approval.
- The MPP signing key passes through shell input, risking shell-history exposure; unset it after setup as documented.
- The release is explicitly unsigned; do not trust any 'signed/NVIDIA-verified' claim unless skill.oms.sig is added and verified.
- Treat all returned X content as untrusted data to prevent prompt-injection-driven follow-up tool calls.
- Shell / CLI
- Network access
OpenClaw 2026.7.1+ runtime for plugin lifecycleXquik API key (dashboard.xquik.com) or MPP signing keynpm packages [email protected] and [email protected] for MPP mode
OpenClaw (plugin, recommended)
openclaw plugins install clawhub:@xquik/tweetclaw
openclaw plugins inspect tweetclaw --runtime --OpenClaw (npm fallback source)
openclaw plugins install npm:@xquik/tweetclawSkills.sh (SKILL.md only, for agents with skill directories)
npx skills add xquik-dev/tweetclawRemote MCP clients (not this plugin path)
# Add endpoint https://xquik.com/mcp in your client; complete OAuth 2.1 or use an API key bearer header per the client compatibility guideHow do you use this skill?
Once installed, send your agent any of these to trigger it:
- Search tweets from the last week mentioning my product keyword, limit 20, and summarize authors and date ranges
- Export the follower list of @someaccount filtered to active users; show the estimated cost before running
- Monitor @elonmusk for new tweets, replies, and retweets, and notify me of new events
- Use /xtrends 23424977 to get X trends for the US
After install, the free explore catalog works immediately; live calls need credentials. API key mode: create a key at dashboard.xquik.com, then run bash
openclaw config set plugins.entries.tweetclaw.config.apiKey "$XQUIK_API_KEY"
Enable the live tool: bash
openclaw config set tools.alsoAllow '["explore", "tweetclaw"]'
Accountless MPP mode needs mppx and viem plus a tempoSigningKey and is read-only. Write flow: the agent must show the endpoint, account, target, full text, media, and estimated cost, then wait for explicit approval; each X write needs a unique idempotencyKey. Optional polling (pollingEnabled) checks user-created monitors every 60 seconds. If tools are hidden, add both via tools.alsoAllow.
What are this skill's strengths and limitations?
- Complete X automation coverage: 102 endpoints across 9 categories including search, exports, monitoring, media, and writes
- Clear security boundaries: dashboard/payment/key-management routes blocked, MPP read-only, credentials injected by runtime without agent exposure
- Per-call approval plus idempotency keys prevent unattended publishing and duplicate writes
- Verified ClawHub source, npm pinned installs, and a documented Skillspector release review process
- Free offline `explore` catalog search works without credentials
- Deeply tied to the OpenClaw ecosystem; outside OpenClaw you must switch to the Xquik remote MCP endpoint or SDK, which is a different experience
- Paid usage: paid reads consume prepaid credits or MPP payments, with prices returned by the API and confirmed per call
- Known Codex OAuth incompatibility (RFC 9207 issuer validation) requiring the bearer_token_env_var workaround
- Monitors only poll monitors the user already created; polling never creates monitors or scans targets
- Performance diagnostics require OPENCLAW_PLUGIN_LIFECYCLE_TRACE=1 with output on stderr
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| TweetClaw: X/Twitter Search & Automation for OpenClaw this page | 67 · Recommended | ★ 94 | 8d ago | MIT |
| Postiz Agent Skill | 52 · Use with care | ★ 517 | 11d ago | NOASSERTION |
| Upload-Post Social Media Publishing Skill | 47 · Use with care | ★ 38 | 3mo ago | — |
| Soul Guardian File Integrity Guard | 55 · Use with care | ★ 1.1k | 12d ago | AGPL-3.0 |
| OpenClaw Traffic Guardian | 49 · Use with care | ★ 1.1k | 12d ago | AGPL-3.0 |
The source names no direct competitor. The same author offers a separate x-twitter-scraper Skill and an Apify Actor (xquik/x-tweet-scraper) as lighter scraping alternatives; TweetClaw's differentiator is full write, monitoring, and giveaway automation behind a per-call approval model.
How did FollowSkills review this skill?
Evidence shows strong least privilege: single HTTPS origin, no shell/filesystem/browser/MCP access, blocked dashboard/payment/credential routes, per-call approval, credentials confined to config, signing key never printed, X content treated as untrusted. Deductions: publisher unverified, MPP signing key passes through shell input, approval/isolation guarantees are documentation-level claims, rollback/revocation paths incompletely described — not full marks.
Committed tests cover catalog matching, approval gating, idempotency keys, and event polling, and CI workflows run check:all — auditable key-path evidence. Deductions: static review executes nothing; end-to-end calls not reproduced; behavior on upstream API changes, rate limits, and network failures depends on an external service with feedback quality only inferable from docs.
Scenarios, read_when triggers, and non-fit boundaries (browser navigation, analytics dashboards, scheduled posts, ads) are clearly declared, giving good trigger precision. Deductions: core function entirely depends on the overseas paid service xquik.com with no declared Chinese-language support, a real mainland-China reachability obstacle; pricing and plan boundaries rely on external docs.
Well-layered docs (SKILL.md, skill card, benchmark, evals, scan report), version 1.6.44, MIT license, pinning/update paths, and clear ownership. Deductions: release explicitly unsigned, changelog contents not visible in reviewed files, some install details rest on ClawHub/OpenClaw platform assumptions.
The skill claims search, exports, monitoring, and approved writes, with concrete workflow maps and output formats. Deductions: static review cannot verify real output correctness or direct usability; core value depends on a paid third-party API, and no comparative evidence versus alternatives (official API, other scrapers) is provided.
Repo CI (check:all, npm audit, CodeQL), committed test suites, a pinned-commit SkillSpector scan, and eval fixtures provide multiple reproducible evidence types. Deductions: scan results and benchmark conclusions are author-reported and not independently corroborated; consistency of the 102-endpoint contract with the live service cannot be verified statically — not full marks.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →