В каталоге 185 367 навыков в 14 категориях.
Automate Instantly cold email outreach -- manage campaigns, sending accounts, lead lists, bulk lead imports, and campaig...
Configure Instantly CI/CD integration with GitHub Actions and testing. Use when setting up automated testing, configurin...
Diagnose and fix Instantly common errors and exceptions. Use when encountering Instantly errors, debugging failed reques...
Create a minimal working Instantly example. Use when starting a new Instantly integration, testing your setup, or learni...
Install and configure Instantly SDK/CLI authentication. Use when setting up a new Instantly integration, configuring API...
Configure Instantly across development, staging, and production environments. Use when setting up multi-environment depl...
Execute Instantly production deployment checklist and rollback procedures. Use when deploying Instantly integrations to...
Apply production-ready Instantly SDK patterns for TypeScript and Python. Use when implementing Instantly integrations, r...
The Skill primitive is the first formally-specified Layer-3 required functional primitive from the framework-functional-...
Instar-specific development skill used by the instar-developing agent (Echo, or any agent assigned instar-dev responsibi...
Instar has a built-in feedback system that routes issues and feature requests directly to the instar maintainers. Your a...
Instar's identity system gives agents a continuous self that survives context compaction, session restarts, and autonomo...
Register, inspect, and drive multi-spec projects via the instar /projects API. Twelve subcommands cover the full Phase 1...
Instar's job scheduler lets you define tasks that run automatically on a cron schedule. Each job spawns a real Claude Co...
Instar lets you spawn, monitor, and communicate with Claude Code sessions running as background processes in tmux. Each...
Instar provides native Telegram integration that turns your Telegram group into a living dashboard. Each scheduled job g...
Học hành vi từ session thực tế — tạo atomic instincts với confidence scoring, tự động activate khi gặp pattern tương tự....
Cluster related instincts into skills, commands, or agents
Export instincts for team sharing
Use when the user wants to share or back up learned instincts — validates the local instincts file, allowlists the six k...
Export learned instincts for cross-project sharing
Export instincts for sharing with teammates or other projects
다중 세션 transcript에서 반복 실패 패턴(instinct)을 자동 채굴하여 신규 skill candidate 생성
Import instincts from teammate
Use when the user brings an exported instincts JSON to merge into the local store — treats trigger and action as inert d...
Import instincts from other projects or exports
Import instincts from teammates, Skill Creator, or other sources
View learned instinct patterns with confidence scores
Use when the user wants to see what learned instincts exist, their confidence scores and how current they are — reads th...
Display learned instincts with confidence bars grouped by domain. Shows personal and inherited instincts, observation co...
Show all learned instincts with their confidence levels
Complete guide for implementing institution-based data filtering in JKKN COE pages. This skill should be used when creat...
识别机构持仓变化、共识强化与调仓方向,帮助判断哪些公司或行业正在被增配、减配或重新定价。适用于13F、基金季报、机构持仓复盘与风格验证。
Smart money tracker. Analyzes institutional investor behavior through 13F filings, Form 4 insider transactions, and larg...
Use this skill to track institutional investor ownership changes and portfolio flows using 13F filings data. Analyzes he...
Use this skill to ingest user-authorized institutional views, consensus exports, target-price summaries, or licensed res...
Use when instruction drift is likely: multi-step tasks, mid-task detours (tooling upgrades), or when agents must consult...
曖昧な指示を明確・具体的・実行可能な形式へ変換するスキル。「適切に」「よろしく」といった不明瞭な表現を、測定可能な成功基準と段階的ステップへ分解します。 Anchors: • Made to Stick (Heath) / 適用: 簡潔性...
Create and manage high-quality custom instruction files for GitHub Copilot. Use when you need to define new project-spec...
Design Solana/Anchor instructions with clear inputs, constraints, authority checks, and invariants. Use when defining or...
Use when: (1) constructing prompts for subagents, (2) invoking the Task tool, or (3) writing/improving skill instruction...
Onboard an AI agent to an unknown codebase by generating a comprehensive instructions file. Use when asked to analyze a...
Search memex for user feedback patterns (frustration, corrections, praise, successful outcomes) to identify recurring mi...
Manages and synchronizes AI instructions (global and project-level) across various tools (Gemini, Claude, Copilot, etc.)...
Use when instruction files (skills, prompts, CLAUDE.md) are too long or need token reduction while preserving capability...
Decide where to persist anything meant for future agent sessions, in any project. Use before saving a rule, preference,...
Review a project's instruction file (CLAUDE.md or AGENTS.md) against recent work and propose a minimal evidence-backed d...
Write and optimize instructions for Claude Code (skills, slash commands, memory files, CLAUDE.md). **ALWAYS use before c...
Design learner-focused training materials and playbooks for pilot processes. Use when creating user guides, workshops, o...
This skill should be used when the user asks to "create CLAUDE.md", "initialize CLAUDE.md", "sync CLAUDE.md with code",...
Structured LLM outputs validated with Pydantic.
Structured outputs with Instructor. Extract typed data from LLMs using Pydantic models and validation. Use for data extr...
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse compl...
Use when extracting structured data (JSON, typed objects) from LLM responses with validation and retries. Triggers on: '...
Map, explain, and lint repository-scoped coding-agent instructions before changing code.
将实验室仪器输出文件(PDF、CSV、Excel、TXT)转换为 Allotrope Simple Model (ASM) JSON 格式或扁平化 2D CSV。适用于科学家将仪器数据标准化以导入 LIMS 系统、数据湖或下游分析。支持自动...
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flatten...
Gate application code behind an existing Harness FME feature flag. Detect the app's language, framework and any existing...
Use this when adding tracing/observability to an LLM or AI-agent application - capturing prompts, tool calls, token usag...
Add PostHog log capture to track application logs. Use after implementing features or reviewing PRs to ensure meaningful...
Wire up a track() call for a metric's event, placed at the real outcome, and verify it arrives. Doesn't create the metri...
Use when defining events, fields, and governance for GTM analytics pipelines.
Implement deep instrumentation pipelines for tracing, metrics, and real-user monitoring of React apps.
Plan instrumentation strategy before implementation, covering what to instrument, naming conventions, cardinality manage...
<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->
Instruments AI agents to produce observable telemetry — what to log at each agent step, which metrics signal health vs....
Sets up observability for the Vercel + Supabase + n8n + Anthropic stack. Live operational path runs through PostHog (MCP...
Local-first insurance record organizer for tracking policies, renewals, claims logs, and related insurance records. Use...
Assembles a project insurance program recommendation: which policy types the project needs, what each one covers, the wr...
Insurance policy analysis, claims evaluation, coverage assessment, and risk management for individuals and businesses
Find insurance payments, total annual premiums, and compare to benchmarks.
保险经纪人 / 保险代理人 (中国保险经纪人/代理人 (从业者视角)) Master OS — automated mastery of 中国保险经纪人/代理人 (从业者视角): top builders' mental models, t...
Write a clear insurance claim letter or appeal that supports a payout. Use when asked to write an insurance claim, file...
Appeal a denied insurance claim — read the real reason for the denial, find the strongest grounds, and draft the appeal...
---
Prueft estate interest in policies, D&O proceeds, coverage disputes, stay, settlements and mass tort insurance: eigenstä...
Expert-level insurance systems, underwriting, claims processing, actuarial analysis, risk assessment, and insurtech solu...
Analyzes and compares health insurance plans (individual vs group), calculates costs, verifies networks, and generates f...
Decode a home, renters, or auto insurance policy into what's actually covered, what's excluded, and what the payout math...
Promote the approved insurance-waiver working set into one authoritative backup-ready packet and record the fixed endpoi...
Approve the exact insurance-waiver field edits, separate selected from non-selected candidates, and keep the PDF pending...
华安保险车险周报自动生成器(麦肯锡风格)。将周度车险数据(支持Excel/CSV/JSON/DuckDB)转化为12-13页董事会级经营分析报告。采用问题导向标题、16:9宽屏、四象限/气泡图可视化、深红#a02724配色。报告结构:经营概...
Grassroots-first campaign design for anyone being outspent — startups vs. incumbents, NGOs vs. corporate comms, movement...
Expert en insurtech avancé (parametric insurance, claims automation, pricing, telematics, DZ context)
Use when working in Go and you need DataList/DataTable-style data wrangling, quick previews, parallel transforms, file I...
General SOP for common requests related to int, if, output.
This skill should be used when the user says "client sent edits", "merge client feedback", "клиент прислал правки", "раз...
Wenn es um Intake und Eingangstriage in Kanzlei-Allgemein geht: klärt Rolle, Ziel, Frist, Unterlagen und den passenden n...
Step 1 of the content pipeline. Use when a raw filmed clip needs to enter the system — the user drops a camera file and...
Pre-planning ticket ingestion. Given a ticket ID or URL, reads the full ticket via MCP or CLI, follows all referenced li...
Draft a Workflow Phase 1 intake document capturing a new request — the problem, the desired outcome, constraints, and te...
Use when Forge receives a new project request. CEO evaluates feasibility, scope, and information completeness before sta...
Convert the user's raw description into a clinically precise intake note suitable for handoff to another agent or human....
Turn pasted feedback (a message, an email, a bug report, in any language) into one English GitHub issue per topic on the...
Strukturiert jeden Kanzlei-Eingang aus Brief Fax beA E-Mail SMS iMessage WhatsApp Telegram Teams Screenshot Upload oder...
Turn a goal, meeting notes, a transcript, an email or a `distill` candidate into decision records, specification changes...
The intake form (the lead-capture page at /intake). Title, description, and the questions visitors answer. Per-vertical...