Каталог навыков агентов

Review who attended a Google Meet conference and for how long.

Find Google Tasks that are past due and need attention.

Attaching a Rhai script and proving it RAN — the snapshot-in/effects-out contract, what mem does and does not prove, the...

Judge a finished bind with numbers and repair what the numbers find — the five rig judges in the order they must run, wh...

Find Gmail messages with attachments and save them to a Google Drive folder.

Save a Gmail message body into a Google Doc for archival or reference.

Scale recipes across portions, batch size, equipment, timing, heat transfer, seasoning, and service workflow without bli...

Recreate a reference image as a 3D scene — intake, in-context decomposition, build-vs-buy routing, clean capture, numeri...

Create a recurring Google Calendar event with attendees.

Send a team announcement via both Gmail and a Google Chat space.

Share a Google Docs document with edit access and email collaborators the link.

Share Google Drive files with all attendees of a Google Calendar event.

Share a Google Drive folder and all its contents with a list of collaborators.

Creates a complete SwiftUI shop for iPhone Duo, Apple's foldable, that sells digital packs and a subscription with Store...

Use the project's Git or Lore repository like a careful teammate — status first, lock binary assets before editing, save...

Export Google Contacts directory to a Google Sheets spreadsheet.

Weather a terrain with real erosion — which of the four sims to pick, why pipe is the default, the knob to turn before a...

Turn a heightfield into the finite BLOCK terrain tools present (extrude down an axis, never solidify), then shade it fro...

Terrain and world-graph authoring — units are world metres, surface-chain routing and mask topology, cook settle polling...

Author a procedural material from a reference image — one-call graph spec, contact-sheet debugging to find the stage whe...

Creates a complete two-player, one-phone SwiftUI game for iPhone Duo, Apple's foldable, where each player gets half the...

Update existing design documents (Design Doc / PRD / ADR) with review

Recreate a reference effect (fire, a jet, smoke, sparks) from an image — intake, decomposition, the physical bake loop,...

Subscribe to change notifications on a Google Drive file or folder.

Expert in test-first development of production-quality OpenRewrite recipes for automated code refactoring. Automatically...

Generate meal plans and recipes from optimization results. Use when user wants recipes, meal ideas, cooking instructions...

Audit and reclaim disk space cautiously on a development Mac, especially when storage is nearly full, caches and build a...

Refactor CLAUDE.md files to follow progressive disclosure principles. Use when CLAUDE.md is too long or disorganized.

Prompt-level recoding-decoding — break out of modal responses through systematic perturbation, clustering, and long-tail...

Guide for running ReCodeAgent-Codex-TB2 Harbor ENV Run terminal-bench-2 BENCHMARK Evaluate TASKs Operation Guide

Эксперт employee recognition. Используй для программ признания, награждения и employee engagement.

Comprehensive guide to recoil. Master the concepts, implementation, best practices, and real-world applications of recoi...

Manages Git worktrees for Recollect development. Creates worktrees in .worktrees/, copies .env.local, and runs pnpm inst...

Reads ~/worklog journal pages to recollect todos, insights, and open problems. Use for "what was I doing", catch-up, pos...

Change only a named object or PNG element to a target color while preserving shape, material texture, luminance, highlig...

Create original short videos using the 分组对话覆盖｜两边接力后全桌合流 Creative DNA for MiniMax H3 or Seedance 2.0. Use when the user w...

Motor de recomendacao de enredo, nomes e referencias literarias com busca paralela vetorial, grafo e notas fundidas com...

Get research-backed architecture advice for your knowledge system. Describe your use case, constraints, and goals — get...

Produce the MVP recommendation artifact at .garura/product/scope/mvp-recommendation.md. Narrows the capability walk by s...

Evaluate an AI product idea across outcomes, hypotheses, risks, and positioning. Use when deciding whether an AI solutio...

Build recommendation systems with collaborative filtering, matrix factorization, hybrid approaches. Use for product reco...

Deploy production recommendation systems with feature stores, caching, A/B testing. Use for personalization APIs, low la...

Enforces specific folder structure at root level.

Analyzes codebase to find gaps in rule coverage and suggests rule improvements. Compares codebase against all indexed ru...

Regenerate and post-process all agentic workflows. Use when gh-aw is updated, workflow .md files change, or when asked t...

Map an unfamiliar repository (or area within one) so you know where to start.

Run the DigitalOcean ephemeral-droplet recon pipeline over a list of IPs, CIDRs, or wildcard domains. Use when target-in...

Trace an existing system end to end — entry points, call paths, every read and write of the state involved, the contract...

Discover and invoke the canonical recon CLI for durable, reusable external-source analysis of repositories, websites, do...

通用网络与资产信息收集。面向 IP、CIDR、主机名、企业/域名等尚未明确攻击面的目标，完成资产扩展、主机发现、TCP/UDP端口发现、服务/版本/协议识别、只读服务枚举、网络设备识别和漏洞候选研判。Recon only：不执行漏洞利用、口...

Security reconnaissance. USE WHEN recon, reconnaissance, bug bounty, attack surface. SkillSearch('recon') for docs.

- End-to-end passive reconnaissance for a domain, website or IP — builds an asset inventory covering registration, DNS,...

End-to-end passive reconnaissance for a domain, website or IP — builds an asset inventory covering registration, DNS, su...

Use when you have written authorization and need to directly probe the target: DNS zone transfer attempts, authoritative...

One line: port/host/service discovery tool arsenal for authorized engagements. Pack in trigger signals so it auto-loads:...

Governs supplied reconnaissance job manifests with exact authority and scope binding, contact receipts, bounded waves an...

Discover an organization's cloud footprint — buckets, blobs, apps, IP ranges, and services across AWS/GCP/Azure. Load du...

Discover hidden paths, endpoints, params, and JS-exposed routes on a web target. Load after a live host is found, on "di...

Deep DNS analysis for attack surface — record mining, zone transfers, DNSSEC/NSEC walking, and dangling records. Load du...

Automated full-scope reconnaissance starting from a domain or domain list. Performs subdomain enumeration, port scanning...

Two-engine recon for authorized bug bounty / attack-surface mapping. PASSIVE brain (scripts/recon.py, stdlib, no keys, s...

Origin IP discovery behind WAF/CDN via DNS history, subdomain leaks, certificate transparency, and misconfigurations

Entry P1 category router for reconnaissance and methodology. Use when mapping scope, discovering assets, fingerprinting...

Find secrets and internal detail an organisation leaked to public code — GitHub/GitLab repos, gists, and commit history....

Full-stack recon-to-bug pipeline. Runs passive enumeration, attack surface mapping and bug discovery in one continuous f...

Mine JavaScript for endpoints, params, secrets, and hidden functionality. Load on SPAs, heavy JS apps, after crawling, o...

Bug bounty and pentest reconnaissance methodology

Network reconnaissance and security auditing using Nmap for port scanning, service enumeration, and vulnerability detect...

Comprehensive reconnaissance and OSINT — subdomain enumeration, CVE lookup, breach intelligence, DNS history, social pro...

Passive OSINT to expand attack surface without touching the target: dorks, code/secret leaks, Shodan/Censys, cloud asset...

Use when starting authorized reconnaissance on a target domain or organization while staying off the target's own infras...

Triage ASM/recon output for ownership before testing — separate the target's real assets from namespace-collision noise....

Guide authorized external penetration testing from recon through validation and scoped exploitation using free and open-...

Enumerate subdomains and live hosts to build the attack surface for a bug-bounty program or external assessment. Load at...

Passively identify a target's full technology stack — frontend framework, backend runtime, server, CMS, CDN/WAF, cloud,...

Reconcile increment ID collisions after multi-developer merge. Renumbers conflicting increments based on modification da...

Use when two numbers that should agree do not, a report against its source, a rollup against its detail, two systems for...

Audit a project against current plugin conventions and offer to update structure.

Use this skill when the user wants to reconcile learnings into rules, run /reconcile, propose rules from learnings, turn...

Read-only attention reconciliation. Computes actual seven-day project attention from daily notes against explicit Tier-1...

Reconcile advance ship notice data against purchase orders, shipment documents, received counts, and exceptions.

Reconcile existing code with the confirmed VDM-SL specification. Compare spec vs code item-by-item, generate a diff repo...

Update implementation to satisfy added, updated, or deleted tests in the current commit.

Reconcile inventory by comparing counts, system balances, transactions, statuses, and adjustment evidence.

Explain why two or more reports, spreadsheets, or metric totals disagree by aligning definitions and quantifying the dif...

Reconcile returned inventory from return receipt, system balance, disposition, quantities, holds, and source-system reco...

Review a worker session summary and reconcile beads tasks with implementation reality. Use after a worker completes /fin...

Add, update, or delete tests for changes in the current commit

Verify Qdrant vector store is in sync with PostgreSQL extraction state by comparing counts and optionally re-indexing mi...

Reconcile P&L vs KPI data sources. Validates consistency and identifies discrepancies with variance analysis.

Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing ban...

Match bank transactions to invoices and surface unpaid / unmatched items in a Well workspace. Use when the user asks wha...

Use when a bank, control account or subledger reconciliation does not agree: tracing each break from the reconciliation...

Matching rules, tolerances, and escalation logic for reconciling Stripe activity and the bank feed against the invoices...

Use when comparing canonical and observed component catalogs, including casing or spacing differences, and reviewable ad...