@zack-dev-cm

openclaw-cws-publisher audits chrome extension repos for cws readiness across packaging, manifest validation, leak detection, design gates, seo compliance, and competitor positioning before submission, enforcing reproducible release hygiene.

interactive-doc-mapper generates self-contained HTML workflow diagrams from JSON source, rendering package boundaries, action handoffs, and payload annotations as clickable single-page documentation artifacts for architecture review.

skill-sprint-pack-builder transforms raw notes, workflows, or upstream skill ideas into public-safe, installable skill artifacts with proof checklists, redaction guidance, and reusable card formats for multiple runtimes.

doubt-driven-development provides a structured workflow to surface and test risky assumptions before shipping high-impact changes. it forces falsifiable claims, disconfirming evidence-gathering, and explicit decision gates (proceed, patch first, stop) rather than defaulting to confidence.

github-clawhub-launcher guides structured review of release plans, metadata, and risk surface for github and clawhub packages without executing publish commands or handling credentials.

agentic-codex-dev performs scoped review of development plans and release readiness for codex/github/clawhub work, rendering verdicts without executing state changes. text-only analysis layer focused on scope, public surfaces, and verification gates.

telegram-miniapp-security-auditor runs static analysis on telegram mini app projects to identify blocking and review-level security issues before production launch, with explicit triage rules for common vulnerabilities.

agentic-video-production-publisher audits ai-generated video packages against platform policy, metadata integrity, and disclosure requirements before human-controlled publishing, returning a four-level readiness verdict without operating accounts or uploading media.

affiliate-video-campaign-operator reviews affiliate video plans for disclosure compliance, unsupported claims, creative provenance, and platform fit before human publication decision, returning a verdict and actionable checklist.

community-topic-scout guides creators through selecting a community topic, name, and launch strategy by mapping creator skills to audience pain points, generating scored name candidates, and defining a 7-day proof challenge before monetization.

trusted-clawhub-install-gate audits local skill artifacts before installation, classifies findings as pass/review/block, assesses active-project impact, and gates installation behind explicit user approval with staged safety defaults.

skool-trust-ladder-builder structures free-course onboarding funnels through progressive value delivery (challenges, audits, templates, reviews, modules) with explicit guardrails against scraping, credential handling, and outcome guarantees.

x-algo-claim-auditor classifies public claims about X's algorithm against open-source evidence, producing verdicts (supported, misleading, unsupported, not_public_repo) with explicit boundaries on what public repositories cannot prove about live platform behavior.

tinytroupe-feed-research-lab runs bounded synthetic audience testing on draft posts and feed experiments using persona-driven reactions. outputs are research signals and hypothesis generators, not live algorithm predictions or reach forecasts.

skool-member-activation-concierge generates consent-first onboarding templates and weekly operator checklists to move new community members from join to first action, without automating private outreach or scraping member data.

meshmcp-remotescreen plans consent-based support checklists for android devices by capturing user context, enforcing privacy boundaries, and producing supervised next steps without requesting sensitive credentials.

gstack-review-stack adapts upstream gstack review discipline for codex workflows across product, engineering, design, and qa gates. it routes requests to narrowly-scoped review modes and loads reference files conditionally, with explicit approval gates for irreversible changes.

youtube-openclaw-creator prepares youtube upload metadata for human review, validating title-description-thumbnail alignment, policy compliance, and content claims before final upload handoff.

avito-outreach-manager reviews seller message drafts for tone, clarity, consent framing, and safe checkout language, then outputs a revised message with a human checklist before send.

Install, wire, audit, and harden AgentMemory for AI coding agents and project workspaces. Use when Codex needs to adopt rohitg00/agentmemory, configure Codex...

Offline random coffee skill for ranking opt-in people and preparing consent-first intro packets. It creates local reports only; any external communication st...

Design a public-safe 7-day Skool challenge. Use when the user wants to invite member action, collect comments, produce visible proof, test demand, or turn re...

Improve a Skool community's public discovery page for search clarity, trust signals, and free-course activation. Use when the user wants a better Skool name,...

Route ambiguous agent work to the right skill, command style, and effort level. Use when a task mentions skills, agents, workflows, lifecycle commands, revie...

Audit an upstream agent skill, SKILL.md, skill repository, or lifecycle workflow before adapting it for ClawHub, Codex, Claude Code, or a public Skool skill...

Convert one portable skill idea into a runtime-neutral SKILL.md core plus safe adapter notes for Codex, Claude Code, ClawHub, and OpenClaw, without installin...

Use when studying or normalizing Chinese lesson transcript/subtitle inputs with bundled public lesson data, learner docs, local export bundles, and pilot-fir...

Strictly review any new skill, browser extension, app, community, course, template, or micro-product before building or launching it. Use when the user wants...

Public OpenClaw skill for generating reproducible PPTX decks from project notes, status bullets, and screenshots. Use when the user wants a stakeholder-ready...

Design, prototype, build, QA, and ship Chrome extensions across separate plugin, template, and product repos with explicit publish lanes.

Plan a public-safe offline message test checklist for owned Android devices, including consent boundaries, non-sensitive sample text, success criteria, and h...

Run a proportional delivery lifecycle for software or skill work: clarify scope, create a concise plan, implement, verify, review, and ship. Use when the use...

Review open feed recommendation repositories with source-backed evidence, artifact-readiness checks, and cautious architecture summaries. Use when a user ask...

Review HH.ru application packets for clarity, consent, and public-safe wording before a human submits them.

Review computer-vision experiment reproducibility evidence, dataset readiness, metric gates, and launch risk. Use when a user asks for a cautious CV experime...

Create public-safe Skool growth teardown posts from validated public community snapshots. Use when generating posts, copy-paste reply packs, consultation CTA...

Plan AI video scenes from a creator's concept into character sheets, scene plates, multi-shot prompt briefs, credit-aware run plans, and review checklists fo...

Plan compliant affiliate UGC test campaigns from a product or niche into disclosure-safe hooks, short-form video briefs, carousel briefs, platform routing, c...

Build source-backed research claim ledgers from drafts, literature matrices, notes, citation lists, PDFs, source packets, or reviewer comments. Use when the...

AI-readable gift, artist story, hours, event, and lead handoff surface for an artisan gallery pilot in Stowe, Vermont.

Audit Claude, Codex, OpenClaw, and ClawHub skill packages before publishing; produce concrete fix lists, trust scores, and shareable proof cards.

Generate shareable SVG and Markdown proof cards from a skill audit or release metadata for GitHub READMEs, landing pages, and ClawHub listings.

Generate install commands, GitHub README snippets, website cards, and copy text for a published ClawHub or Codex skill.