← Back to Skills Marketplace
X Algo Claim Reviewer
by
Zakhar Pashkin
· GitHub ↗
· v1.0.2
· MIT-0
133
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install x-algo-claim-auditor
Description
Review public claims about xai-org/x-algorithm, the X For You algorithm, Phoenix, Grox, Home Mixer, engagement weights, filters, ads blending, or viral algor...
README (SKILL.md)
X Algo Claim Auditor
Use this skill to review public claims against public X algorithm source evidence. The goal is a defensible verdict, not growth advice or live-platform prediction.
Review Workflow
- Extract the exact claim from the user, screenshot text, public post, or pasted text.
- Identify which public repository, commit, file, or public citation is being used as evidence.
- Classify the claim as
supported,misleading,unsupported, ornot_public_repo. - Cite the strongest public evidence and state what the evidence does not prove.
- Flag overclaims about exact multipliers, production equivalence, private thresholds, account treatment, shadowbans, or draft-post reach prediction.
- If the user wants a share card or public summary, keep it cautious and avoid implying that the public repo fully predicts live platform behavior.
Verdict Meanings
supported: public source directly supports the narrow claim.misleading: public source supports a weaker statement, but the claim overstates precision, production equivalence, or causality.unsupported: no public source evidence was found for the claim.not_public_repo: the claim depends on production configs, private thresholds, account state, or live ranking behavior absent from public source.
Boundaries
- Do not claim that the public repo is the full live production system.
- Do not score draft posts, promise reach, or diagnose account-specific boosting or suppression.
- Do not request private account data, authenticated pages, non-public analytics, or account access.
- Do not upload, release, schedule, or operate authenticated sessions as part of this review.
- Do not execute local scripts or clone repositories unless the user separately asks for engineering work.
Output Shape
Return:
Claim: the exact claim being reviewed.Verdict:supported,misleading,unsupported, ornot_public_repo.Evidence: source-backed points, with paths or public citations when available.Boundary: what the evidence does not prove.Public wording: a safer public-safe rewrite when useful.
Use open-feed-recsys-lab when the task is broader repository verification, Phoenix artifact readiness, or architecture mapping. Use tinytroupe-feed-research-lab when the task is draft comparison or synthetic audience reaction review.
Usage Guidance
This looks safe to install for public-source claim review. Users should still verify cited sources themselves and avoid providing private account data, authenticated pages, or non-public analytics, which the skill itself says not to request.
Capability Analysis
Type: OpenClaw Skill
Name: x-algo-claim-auditor
Version: 1.0.2
The skill bundle is designed for auditing public claims regarding the X algorithm based on public source code. The instructions in SKILL.md include explicit safety boundaries that prohibit requesting private data, accessing authenticated sessions, or executing local scripts. No indicators of malicious intent, data exfiltration, or unauthorized access were found in the provided files.
Capability Assessment
Purpose & Capability
The stated purpose and instructions align: review public claims using public evidence and provide cautious verdicts rather than account analysis or growth advice.
Instruction Scope
The skill sets clear boundaries against private account data, authenticated pages, account operations, reach prediction, and local script execution unless separately requested as engineering work.
Install Mechanism
There is no install spec, no code package, no required binaries, and no package or script execution path.
Credentials
No environment variables, credentials, config paths, or capability tags are required, which is proportionate for an instruction-only public-claim review skill.
Persistence & Privilege
The artifacts show no persistence mechanism, privileged access, background behavior, account access, or stored memory use.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install x-algo-claim-auditor - After installation, invoke the skill by name or use
/x-algo-claim-auditor - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
Republish public package as instruction-only claim review.
v1.0.1
Clarify that draft-post pretesting should route to tinytroupe-feed-research-lab, not claim auditing.
v1.0.0
Initial release: audit viral X algorithm claims against public source with verdicts, evidence ledgers, and share cards.
Metadata
Frequently Asked Questions
What is X Algo Claim Reviewer?
Review public claims about xai-org/x-algorithm, the X For You algorithm, Phoenix, Grox, Home Mixer, engagement weights, filters, ads blending, or viral algor... It is an AI Agent Skill for Claude Code / OpenClaw, with 133 downloads so far.
How do I install X Algo Claim Reviewer?
Run "/install x-algo-claim-auditor" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is X Algo Claim Reviewer free?
Yes, X Algo Claim Reviewer is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does X Algo Claim Reviewer support?
X Algo Claim Reviewer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created X Algo Claim Reviewer?
It is built and maintained by Zakhar Pashkin (@zack-dev-cm); the current version is v1.0.2.
More Skills