Communication Skills

> How to author, edit, and adapt PostHog Signals scouts — the scheduled agents that scan a project and emit findings into the Signals inbox. Use when a user wants to customize a canonical scout for their own setup (narrow its scope, retune its thresholds, add disqualifiers), tweak a scout's schedule or dry-run posture, or write a brand-new scout from scratch for a specific use case (a custom event, a product surface no canonical scout covers). Covers the scout SKILL.md anatomy, the emit contract, the dedupe + scratchpad-memory conventions, the per-team skills-store path vs the canonical in-repo path, and the emit-and-inspect test loop (with dry-run as an optional safety net). Trigger on "write/edit/customize a signals scout", "new scout for X", "tune my scout schedule", "make a scout that watches <event>".

> How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and emit findings into the Signals inbox. Use when a user wants to understand what scouts they have, how each one is behaving, and whether the fleet is actually working. Covers surveying the fleet and its schedules, reading recent scout runs and drilling into a single run's reasoning, inspecting the durable scratchpad memory the fleet has built up, tracing a run to the findings it emitted, and assessing a scout's health and performance over time (cadence, success rate, emit rate, signal-to-noise). Read-only and exploratory — to write or tune a scout, use `authoring-signals-scouts` instead. Trigger on "what are my scouts doing", "how is my <x> scout performing", "show me recent scout runs", "why did this scout find/emit nothing", "what has the fleet learned", "explore scout run <id>", "is my scout working".

> Set up an LLM-judge evaluation that extracts canonical use cases for a PostHog feature at scale and streams the results to a Slack channel as a live feed. Use when someone wants to understand how users are actually using a specific AI/LLM-powered feature in production — what they're investigating, what questions they're trying to answer, and what patterns surface — without manually reading hundreds of traces. Assumes the feature emits `$ai_generation` and `$ai_evaluation` events with `$session_id` linkage to the trigger user's recording (the standard setup post the session-summary linkage PRs).

> Explore PostHog's Inbox — the surface where signal reports surface as actionable issues and trends. Use when the user asks "what's in my inbox?", "what should I look at?", "which reports are actionable?", "what's PostHog flagged recently?", asks about a specific report by ID or title, or wants to see which signal sources are configured. Covers listing, filtering, and drilling into reports, plus pointers to the deeper `signals` skill when raw signals or semantic search are needed.

> Focused Signals scout for PostHog projects moving data through pipelines. Watches the three delivery surfaces — CDP destinations and transformations (hog functions), batch exports, and hog flows (workflows/messaging) — for contradictions between configured rates stepping above a pipeline's own baseline, batch export runs failing or stalling (a growing data gap), and active flows failing for the people they trigger on. Emits findings only when they clear the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet — no dependencies on other skills.

> General Signals scout for PostHog projects. Cross-product explorer that scans a team's project and emits findings into the Signals inbox. Sibling signals-scout-* specialists each watch a single product surface in depth; this scout looks for cross-product correlations and explores the surfaces no specialist covers. Each scout runs on its own schedule (default hourly), so general fires independently of the specialists over time.

> Follow-up scout for the Signals inbox itself. Watches reports that recently transitioned to resolved (an implementation PR merged) and, after a deployment soak window, re-measures the underlying problem to check the fix actually held — plus a strictly-gated escalation check on recently dismissed reports. Emits findings only when a shipped fix demonstrably didn't hold; confirmations and unverifiable verdicts become durable memory and an empty close-out. Self-contained peer in the signals-scout-* fleet — no dependencies on other skills.

> Focused Signals scout for PostHog projects running Replay Vision scanners — the standing LLM probes that watch session recordings and write `$recording_observed` events. Watches cliffs, exhausted quota — a silent watch gap), and that what the scanners see in aggregate gets surfaced (a monitor's `yes`-rate or a scorer's score stepping away from its own baseline, a classifier tag or a recurring summarizer theme concentrating across many `emits_signals` already emit one signal per session into this same inbox, so this scout never repeats them — it adds the cross-session shape the per-session probe can't see. Emits findings only when they clear the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet.

Build the case for converting a PostHog monthly/PAYG customer to an annual prepaid credit plan. Pulls 12-24 months of invoice history from the data warehouse, runs the handbook eligibility check, projects forward growth, applies the handbook discount tiers, scans recent customer touchpoints (Slack, Gmail, Granola) for confounding variables, fetches customer momentum signals via Exa, emulates the rep's own writing voice, and emits a succinct briefing plus a plain-text Slack draft. Trigger on "annual conversion math for [account]", "monthly to annual for [account]", "draft annual nudge for [account]", or "credit-discount math for [account]".

Deep dive on a PostHog user by email address. Analyze what they do, where they spend time, and what products they use.

Evaluate and respond to inbound PostHog sales leads from Salesforce. Use this skill when any PostHog TAE needs to triage an inbound lead — deciding whether to qualify for a call, route to self-serve, or disqualify — and then draft an appropriate response email. Checks Vitally for existing account context before qualifying. Triggers on "respond to this lead", "triage this inbound", "write a response to this lead", "disposition this lead", "evaluate this Salesforce lead", or any request involving an inbound sales inquiry that needs qualification and a reply. Also trigger when a TAE pastes or describes lead details and asks what to do with them.

Create high-converting email sequences for sales, launches, and nurture campaigns. Use when the user needs email sequences, drip campaigns, launch emails, or automated email workflows.

Create custom tools for Vapi voice assistants including function tools, API request tools, transfer call tools, end call tools, and integrations with Google Calendar, Sheets, Slack, and more. Use when adding capabilities to voice agents, building tool servers, or integrating external APIs.

Prepare for meetings by gathering context and creating comprehensive agendas

Formats all Telegram bot replies to be short, scannable, and properly styled with MarkdownV2. Use when replying to Telegram messages via the Telegram MCP plugin — ensures bold, emojis, bullet points, and correct special character escaping.

Build a Mentor & Sponsor Plan: target list, outreach scripts, meeting agenda, tracking cadence.

Create a Positioning & Messaging Pack (positioning statement, messaging hierarchy, value prop, copy set).

Produce a 1:1 Operating System Pack (agendas, coaching prompts, career conversation plan). See also: running-effective-meetings (group meetings).

Run effective meetings: brief, agenda, facilitation script, decision log. See also: running-effective-1-1s (1:1s), running-offsites (offsites).

Draft and edit written artifacts (email, memo, doc) with a quality gate.

Export a claude.ai (Claude Desktop / web) conversation and convert it to a Claude Code CLI JSONL session so it becomes resumable via `claude -r <sessionId>`. Use when the user wants to: (1) continue a claude.ai/Claude Desktop chat in Claude Code CLI, (2) import a web conversation into CC, (3) archive a claude.ai conversation locally with images and attachments, (4) unfreeze a claude.ai chat that hit its context limit, or (5) convert conversation.json from the claude.ai API to CC's JSONL envelope format. Triggers on mentions of exporting/importing Claude Desktop chats, resuming a web chat in CLI, conversation.json → JSONL, or claude.ai chat archival.

File-based task tracker for projects: tasks live as markdown files in a tasks/ folder, state = folder location (root = inbox, in-progress/, waiting/, done/, cancelled/, decisions/ for open choices), agents manage tasks by moving the files; plus a zero-dependency local board UI (tasx serve) where the user changes states, answers decisions, and leaves comments that are written straight back into the md files and nudge the owning agent via agent-chat. Use when: (1) the user asks to set up / init a task tracker or tasks folder in a project, (2) the user or agent needs to create, list, move, complete, cancel, or comment on tasks in a repo that has a tasks/ folder, (3) the user asks 'what's in progress', 'what needs me', 'what's stale', or wants a task board / dashboard served, (4) starting a work session in a repo with tasks/ (run tasx doctor and reconcile), (5) a task is blocked on the user's feedback or on a decision — file it as waiting/ or a decision instead of asking and losing the thread, (6) generalizing/migrating older ad-hoc task folders (myhdd-style) onto the shared convention. Triggers on: tasks folder, task tracker, task board, tasx, kanban, what's in progress, needs my feedback, stale tasks, task dashboard.

>- End-to-end testing of email-dependent flows — signup confirmation, password reset, magic-link login, OTP/MFA codes, and notification emails. Covers the capture-inbox decision tree (Mailpit, Mailosaur, MailSlurp, Ethereal), Playwright polling without fixed sleeps, regex extraction of links/OTPs from the email body, deterministic per-test addresses (plus-addressing, per-inbox), subject/from/header/link assertions, and SPF/DKIM/DMARC deliverability checks as a separate suite. "magic-link login test," "capture OTP from email," "Mailpit," "Mailosaur," "MailSlurp," "email arrives flaky in CI," "assert email subject/from/links." an email provider — those are api-testing / app concerns. Email HTML rendering across clients (Outlook/Gmail dark mode) is out of scope (note it as a gap; use visual-testing or Litmus).

| Finds qualified candidates for a role by searching LinkedIn, Indeed, GitHub, and other professional platforms using Nimble Web Search Agents. Accepts a job description, role title, or freeform request and returns a ranked candidate list with profiles, skills, and contact signals. Use this skill when the user wants to find, source, or recruit candidates for "who can I hire for", "find me a [role]", "recruiting for", "talent search", "find a [role] in [city]", "build a candidate list", "sourcing for [role]", "who's available for", "find potential hires". Also triggers on a pasted job description followed by a sourcing request. Do NOT use for job market research or salary benchmarking — use market-finder instead. Do NOT use for researching a single known person — use company-deep-dive or meeting-prep instead.

| Researches meeting attendees and their companies before any meeting using real-time web data. Surfaces roles, recent activity, company context, and talking points — then maps cross-attendee relationships. Use this skill when the user asks to prepare for a meeting, research someone for my meeting", "who am I meeting with", "research this person", "meeting prep", "brief me on [person]", "I have a meeting with [person/company]", "get me ready for my call", "what should I know about [person]", "background on [person] before our meeting", "attendee research". Requires the Nimble CLI (nimble search, nimble extract) for live web data. Do NOT use for multi-company competitor monitoring (use competitor-intel) or single-company deep dives without attendees (use company-deep-dive).

Record and live-transcribe a meeting or live conversation from a Codex thread on macOS, saving streaming transcript text to the workspace with OpenAI Realtime transcription, then summarize notes in-thread. Use when the user asks to start, stop, capture, transcribe, ask questions about, or summarize a meeting recording from the current thread.

Use this agent when you receive a bug report or issue description and need to verify whether the reported behavior is actually a bug. This agent will attempt to reproduce the issue systematically, validate the steps to reproduce, and confirm whether the behavior deviates from expected functionality. <example>\\nContext: The user has reported a potential bug in the application.\\nuser: \"Users are reporting that the email processing fails when there are special characters in the subject line\"\\nassistant: \"I'll use the bug-reproduction-validator agent to verify if this is an actual bug by attempting to reproduce it\"\\n<commentary>\\nSince there's a bug report about email processing with special characters, use the bug-reproduction-validator agent to systematically reproduce and validate the issue.\\n</commentary>\\n</example>\\n<example>\\nContext: An issue has been raised about unexpected behavior.\\nuser: \"There's a report that the brief summary isn't including all emails from today\"\\nassistant: \"Let me launch the b...

ACCESS-GATED beta. Deepline Monitors are provider event feeds (job posts, email replies, funding, intent) that stream into your warehouse and trigger plays. Only use if you have monitor access: run `deepline monitors status` first; if it reports no access, do NOT use this recipe — tell the user to contact the Deepline team.

Convert current chat session into a reusable skill. Use when user says "/chat-to-skill", "save this as skill", "create skill from chat", "turn this into a skill", or wants to preserve learnings from the conversation as long-term memory.

> Conduct deep OSINT research on individuals. Build full digital footprint, psychoprofile (MBTI/Big Five), career history, social graph with confidence scores. Recursive self-evaluation until completeness threshold is met. Includes internal intelligence (Telegram history, email, vault contacts) before going external. "разведка", "due diligence", "background check", "digital footprint", "найди всё про", "собери информацию", "кто это", "профиль человека". market research, content generation, or general web scraping tasks.

Ensure user-facing errors and empty states are clear, actionable, and HIG-aligned. Covers alerts, ContentUnavailableView, retry flows, and permission guidance.

Run developer customer discovery via a Technical Advisory Board (TAB). Use when the founder has never interviewed a user who isn't a friend, is inventing messaging from a conference room, or is guessing at the roadmap instead of hearing the pain firsthand.

Write a developer value proposition that is specific, provable, and free of puffery. Use when the messaging leans on \"powerful,\" \"better,\" \"seamless,\" or \"best-in-class,\" when claims have no proof, or when the same line is supposed to reach both the developer and the buyer.

Build a positioning and narrative where the developer is the hero and a real trend is the villain. Use when the messaging describes the product instead of the problem, sounds like every competitor, or has no urgency because nothing is at stake.

>- Summarize meeting transcripts into structured notes with action items. Use when asked to process, summarize, or extract action items from meetings.

冷邮件诊断助手适合销售、市场营销、运营、software在用户提出“客户为什么不回我”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成转化问题优先级、可复制改稿、实验或跟进行动清单。

转化实验助手适合内容创作者、市场营销、运营、内容媒体在用户提出“这个改动值得测吗”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成邮件节奏诊断、主题行建议、改写稿。

会议待办整理助手适合运营、产品、销售、software在用户提出“会议后该做什么”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成待办拆解、决策摘要、风险和跟进清单。

邮件序列助手适合市场营销、运营、产品、销售在用户提出“邮件能让人行动吗”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。

业务诊断助手适合运营、产品、technical、销售在用户提出“这件事该怎么做”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。

资料整理助手适合运营、产品、technical、销售在用户提出“这份材料重点是什么”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。

销售增长助手适合销售、市场营销、运营、产品在用户提出“客户为什么不推进”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。

Extract and organize Claude Code session history into project .chats directory. Use when users want to document their Claude sessions, export conversation inputs, or maintain a log of instructions given to Claude.

Audit and harden your SaaS tool stack — enforce SSO, review OAuth grants, manage shadow IT, and secure admin accounts across Slack, GitHub, Google Workspace, and AWS. Use when tightening security across company SaaS tools.

Apply CIS benchmarks and secure Linux servers. Configure SSH, manage users, implement firewall rules, and enable security features. Use when hardening Linux systems for production or meeting security compliance requirements.

Scan container images for vulnerabilities using Trivy, Grype, and cloud-native tools. Identify security issues in base images, packages, and configurations. Use when implementing container security, building secure images, or meeting compliance requirements.

The 10x10 method — generate breadth, then converge with human judgment. Use whenever a single AI output won't nail it and quality matters (design, copy, naming, posters, messaging, strategy options, code approaches), OR when the user says '10x10', 'ten by ten', 'give me 10 options', 'show me variations', or asks to refine/tighten an output instead of round-after-round corrections.