Skill rating

Strip AI writing patterns from text — em dashes, stock phrases, promotional inflation, performed authenticity, rule-of-three lists. Use when user says "humanize this", "make it sound human", "strip AI

Query wallet addresses and on-chain balances on OpenAnt. Use when the agent or user wants to check wallet address, view balance, see how much SOL or ETH they have, check token holdings, look up USDC b

Create, join, and manage teams on OpenAnt. Use when the agent wants to discover public teams, join a team, create a new team, add or remove members, or get team details. Covers "find teams", "join a t

Search and browse tasks on OpenAnt. Use when the agent or user wants to find available work, discover bounties, list open tasks, filter by skills or tags, check what tasks are available, or look up a

Send and receive direct messages on OpenAnt. Use when the agent needs to communicate privately with another user, check for new messages, read conversations, reply to someone, or start a chat. Covers

Accept or apply for a task on OpenAnt. Use when the agent wants to take on work, accept a bounty, apply for a job, pick up a task, or volunteer for an assignment. Handles both OPEN mode (direct accept

Cancel a task on OpenAnt and reclaim escrowed funds. Only the task creator can cancel. Use when the user wants to abort a task, take it down, withdraw the bounty, stop accepting applications, shut dow

Create a new task with a crypto bounty on OpenAnt. Use when the agent or user wants to post a job, create a bounty, hire someone, post work, or use AI to parse a task description. Covers "create task"

Register and configure an AI agent on OpenAnt. Use when setting up a new agent identity, registering with OpenClaw or another platform, configuring agent heartbeat, or performing one-time agent onboar

Submit completed work for a task on OpenAnt. Submission = text description + files. IMPORTANT — before submitting, always check if your work produced any files and upload them first. Use when the agen

Leave or unassign from a task you accepted on OpenAnt. Use when the agent or user wants to give up a task, drop an assignment, withdraw from work they took on, quit a task, or free a task back to the

Send USDC to an Ethereum address or ENS name. Use when you or the user want to send money, pay someone, transfer USDC, tip, donate, or send funds to a wallet address or .eth name. Covers phrases like

View your personal task history and status on OpenAnt. Use when the user wants to see their own tasks, check what they've completed, review their task history, see active work, list tasks they created

Creates AI-generated videos from text scripts, URLs, or PPT/PDF documents using Visla. Use when the user asks to generate a video, turn a webpage into a video, or convert a PPT/PDF into a video, or wh

管理驾驶舱技能：基于录音 AI 总结内容，生成管理者日报 HTML 报表。 通过分页接口获取录音的 ai_summary_content，使用 LLM 分析生成包含团队资产、外勤效能、 合规监控、RM 排行、线索转化、管理建议六大板块的可视化报表。 MUST resolve agentId via session_status (sessionKey=current) before APIs. M

Generate UK/EU GDPR compliance documents — privacy policies, cookie policies, DPIAs, ROPA, DSAR responses, data breach notifications, and consent forms. Use when a business needs GDPR documentation, d

When a constraint is treated as fixed, separate physics from convention, keep only independently supported primitives, and rebuild the simplest solution that satisfies real constraints.

R&D project initiation pre-screen and proposal audit for go/no-go decisions, public novelty boundary review, innovation-point assessment, and evidence-backed project rating. Use when the user asks for

Evidence-backed comparison of two or more technical routes, architectures, or solution paths. Use when the user asks for technical pre-research, technical route comparison, route selection, TRL assess

Blockchain security API for AI agents. Scan tokens, simulate transactions, check addresses for threats.

Tasker docstore task management via tool-dispatch. Use for task lists, due today/overdue, week planning, add/move/complete, or explicit /task commands.

Reviews AI/ML model supply chains for security risks including model provenance verification, training data lineage, fine-tuning pipeline integrity, inference dependency review, and backdoor detection

基于Sorftime MCP的深度选品调研。通过LLM Agent执行多维度分析：数据采集→属性标注→交叉分析→竞品VOC→壁垒评估→选品决策评估。交互式执行，输出Markdown报告和Dashboard看板。

Opinionated AI code reviewer — not a yes-machine. 6-layer deep review (logic, edge cases, performance, security, maintainability, architecture) with Devil's Advocate mode and standardized MUST FIX / S

Summarize the current session into a precise, file-saved handoff document covering goals, files changed, commands run, errors, decisions, and next steps. Use mid-session or at end of session when hand

Use when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prior→likelihood→posterior on evidence, and factor unmeasured quantities into order-of-magnitude bounds.

When two design requirements seem mutually exclusive, name the contradiction, separate conflicting states, then invent a concrete no-compromise resolution.

When a real test is too rare, large, or irreversible, run a controlled counterfactual: isolate one variable, fix conditions, trace the mechanistic chain, and bound what the result implies.

Before committing to a plan or launch, assume it already failed and reason backward through concrete causes — convert failure paths into mitigations, gates, and stop checks.

Use under time pressure when the situation is still changing and you must act before certainty — cycle Observe→Orient→Decide→Act on ~70% confidence, then re-observe.

Use when a selective defect needs IS/IS-NOT difference analysis or a consequential option choice needs must/want weighting and adverse-consequence comparison.

Сформировать функцию `СведенияОВнешнейОбработке` в модуле объекта обработки — описание для подключения через подсистему БСП «Дополнительные отчёты и обработки». Используй когда нужно сделать обработку

Under genuine uncertainty with no reliable forecast, inventory means, cap downside at affordable loss, act for commitments, and let goals emerge from controllable moves.

Generate landing page content from PRD — hero section, features, A/B headline variants, CTA, and SEO meta tags. Use when user says "create landing page", "write landing copy", "hero section", "A/B hea

SEO health check for any URL — analyzes meta tags, OG, JSON-LD, sitemap, robots.txt, SERP positions, and scores 0-100. Use when user says "check SEO", "audit this page", "SEO score", "check meta tags"

Meta-skill: evaluate any Factory Droid skill against the current project codebase and suggest concrete improvements. Use when: a skill feels incomplete, produces suboptimal results, doesn't cover edge

Launch automated multi-skill pipeline that chains skills into a loop. Use when user says "run pipeline", "automate research to PRD", "full pipeline", "research and validate", "scaffold to build", "loo

Score startup idea through S.E.E.D. niche check + STREAM 6-layer analysis + Devil's Advocate inversion, auto-pick stack, and generate PRD with acceptance criteria. Use when user says "validate idea",

AI-native OCR platform that turns documents into high-accuracy data in minutes. Using multi-model consensus, DeepRead achieves 97%+ accuracy and flags only uncertain fields for Human-in-the-Loop (HIL)

Auto-generate project workflow config (docs/workflow.md) from existing PRD and CLAUDE.md with zero questions. Use when user says "set up workflow", "configure TDD", "wire up dev workflow", or after ru

Generate memes, image macros, and meme URLs from the terminal using the Memegen.link API. Use when creating memes, picking meme templates, generating funny images, or building meme URLs from text. Sup

Lightweight PIV workflow - discovery-driven feature builder. No PRD needed. Asks quick questions, generates PRP, executes with validation loop. For small-to-medium features when you want to skip PRD c

PIV workflow orchestrator - Plan, Implement, Validate loop for systematic multi-phase software development. Use when building features phase-by-phase with PRPs, automated validation loops, or multi-ag

Verify a crypto token before buying. Input a symbol or contract address (Base or Solana). Returns PASS/WATCH/FLAG verdict with kill switches (honeypot, mint/freeze authority, buy/sell tax >50%), auto-

Pay for APIs and services, receive payments, and manage agent wallets using Mag3nt USDC virtual cards. Activate when the agent needs to pay for a resource, encounters an HTTP 402 response, a payment c

Address the latest reviewer comments on a PR with a pre-commit self-audit (consistency, regression-vs-history, staleness), then commit, push, and reply point-by-point. Accepts a PR number. Loop-aware

Build a change in its own worktree, prove it with mutation testing, self-audit before pushing, open the PR with a body that states what it does NOT prove, then stop and hand off to the review loop. Us

Single-source-of-truth drift auditor for documentation-heavy repos. Use when asked to "check for drift," "find copies of this number," "audit the docs for stale facts," or "set up an SSOT manifest." F

Podcast-appearance research for guest booking. Use when asked to "map someone's podcast circuit," "where has X podcasted," "research X before guest outreach," or "find an unclaimed angle for X." Sweep

Runs SQL queries on CloudWatch Logs data exported as Apache Iceberg tables in S3 Tables. Covers VPC Flow Logs, WAF logs, CloudFront access logs, Route 53 resolver logs, Network Firewall logs, EKS audi