Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 437 files from 1 744 authors, of which 61 785 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Prepare a Quarterly Business Review. Use when: building QBR presentations, client performance reviews, or strategy updates.
Generate quality trends report. Use when: reviewing eval scores over time, content type performance, or regression alerts.
Monitor keyword rankings and SERP features. Use when: tracking keyword positions, detecting ranking drops, alerting on position changes, or tracking SERP-feature presence (AI Overviews, snippets, PAA, local pack).
Recall marketing learnings. Use when: querying what we know about a channel, audience, objective, or past campaign.
Manage URL redirects. Use when: creating 301/302 redirects, auditing chains, fixing loops, or deploying via CMS MCP.
Configure regional settings. Use when: setting timezone, language, compliance rules, currency, or local preferences.
Manage brand reputation. Use when: handling reviews, crisis comms, negative press, sentiment, or recovery plans.
Design retargeting strategy. Use when: planning cross-platform remarketing, audience segmentation, or ad sequencing.
Respond to online reviews. Use when: drafting replies for Google, Yelp, G2, or building review response templates.
Calculate marketing ROI. Use when: measuring campaign ROAS, CAC, CPL, LTV, or multi-channel attribution returns.
Save brand knowledge to memory. Use when: persisting campaign learnings, guidelines, or competitive intel for retrieval.
Schedule social media posts. Use when: publishing to Twitter/X, Instagram, LinkedIn, TikTok, YouTube, or Pinterest.
Search stored brand knowledge. Use when: recalling past learnings, voice guidelines, or competitor insights via semantic search.
Create audience segments. Use when: building or updating CRM or email platform segments for campaign targeting.
Send email campaigns. Use when: deploying via SendGrid, Klaviyo, Customer.io, Brevo, or Mailchimp with A/B testing.
Send team notifications. Use when: pushing campaign updates, alerts, or approval requests via Slack or Intercom.
Deliver performance reports. Use when: sending KPI summaries via Slack, email, or Google Sheets with analysis.
Send SMS or WhatsApp messages. Use when: deploying marketing messages via Twilio or Brevo with compliance checks.
Run comprehensive SEO audit. Use when: checking technical health, on-page, content quality, E-E-A-T, or link profile.
Compare two SEO snapshots (GSC, GSC AI Performance, rank tracker, AEO probe) and surface biggest movers per metric — impressions, clicks, position, AI citations. Use when: monthly performance reviews, post-Core-Update triage, AI Mode citation tracking, or before/after content-refresh evaluation.
Execute SEO changes. Use when: updating meta tags, schema markup, canonicals, redirects, or indexing via CMS MCP.
Build SEO strategy and roadmap. Use when: planning site architecture, content strategy, or phased implementation.
Deprecated — merged into rank-monitor. Use /digital-marketing-pro:rank-monitor --features for SERP-feature tracking (AI Overviews, snippets, PAA, local pack).
Measure share of voice. Use when: comparing keyword visibility, SERP presence, ad share, or AI citations vs competitors.
Simulate revenue impact via Monte Carlo. Use when: testing channel mix changes, budget shifts, or new channel launches.
Manage XML sitemaps. Use when: auditing sitemap health, generating sitemaps, or planning sitemap architecture.
Build social media strategy. Use when: defining content pillars, posting cadence, engagement tactics, or growth plans.
Manage agency SOPs. Use when: creating, assigning, versioning, or auditing standard operating procedures.
Show a unified status snapshot of the active brand: profile, active engagements with current part, recent insights, recent compliance violations, Python dependency mode.
Switch active brand profile. Use when: changing brand context in multi-client or agency workflows.
Batch sync session learnings to memory. Use when: persisting campaign insights and performance history across sessions.
Assign tasks to team members. Use when: distributing work by role, expertise, and capacity, or managing workloads.
Run technical SEO audit. Use when: checking Core Web Vitals, crawlability, indexation, speed, or structured data.
Deep technical SEO analysis. Use when: optimizing crawlability, Core Web Vitals, rendering, redirects, or sitemaps.
Translate marketing content. Use when: localizing with brand voice preservation, quality scoring, or transcreation.
Validate content structure. Use when: checking schema compliance, required sections, word count, or placeholders.
Validate a brand profile end-to-end — required fields, voice/audience completeness, connector reachability, credentials health, and compliance prerequisites — without exposing credential values. Run after any credential change or brand-profile edit.
Verify marketing claims. Use when: cross-checking statistics, awards, certifications, or performance claims with sources.
Write video scripts. Use when: creating YouTube, TikTok, Reels, LinkedIn, demo, or explainer video content.
Plan webinars and virtual events. Use when: designing promotion, content, registration, and post-event follow-up.
Compare budget scenarios side-by-side. Use when: testing 2-4 allocation variants with projected outcomes.
Produce the 12-month operational Yearly Planner — the calendar companion to the Growth Plan in Part 8. Translates strategy into month-by-month execution.
> How to add a new ingestion warning type to the event ingestion pipeline. Use when emitting a new warning from nodejs ingestion code (emitIngestionWarning, captureIngestionWarning, pipeline `warnings` arrays, `drop()` with warnings), when adding a warning type, category, or severity, or when a typecheck error says a string is not assignable to IngestionWarningType. Covers the INGESTION_WARNING_TYPES registry (the single source of truth for type, category, and severity), the details-key conventions that ClickHouse v2 materializes into columns, debouncing, and the downstream surfaces to keep in sync (v1 UI map, resolving-ingestion-warnings skill, docs, v2 API).
Use when migrating frontend code from manual API client calls (`api.get`, `api.create`, `api.surveys.get`, `api.dashboards.list`, `new ApiRequest()`) and handwritten TypeScript interfaces to generated API functions and types. Triggers on files importing from `lib/api`, files with `api.get<`, `api.create<`, `api.<entity>.<method>`, manual interface definitions that duplicate backend serializers, or any frontend file that constructs API URLs by hand. Covers the full replacement workflow — finding the generated equivalent, swapping imports, adapting call sites, and removing dead manual types.
> Guide for adding a new RPC to personhog-replica and personhog-router. Covers eligibility checks, proto definition, code generation for Python and Node.js clients, Rust implementation (storage trait, postgres queries, service handler, router wiring), and index compatibility validation. Use when adding a new gRPC endpoint to personhog, migrating a Django ORM query to personhog, or extending the personhog service API.
> Pull and interpret production experiment query-performance data from the staff-only slowest experiment queries, precompute read/build health, and preaggregation cache footprint. and response field semantics (exception codes, exposure paths, precompute skip reasons, job states). Use when investigating slow or failing experiment queries, precompute regressions, 307/159/241 errors, preaggregation table growth, or when asked how experiment query performance or the precompute rollout is doing in production.
> Recommended repo-engineering guide when adding alerting to a PostHog product or extending the shared alerts platform. Routes lifecycle state machines, AlertPolicy, destinations, HogFunction dispatch, email, fixed-cadence and calendar scheduling, insight evaluation, the AlertWizard, and shared alert editor components. Use for product alert implementations, shared destination types, lifecycle or scheduling options, advanced alert settings, and platform alert infrastructure. Not for configuring alerts in an existing product.
How to gate a PostHog API endpoint with project secret API key (PSAK) auth — a project-scoped, user-less service credential. Use when adding PSAK support to a viewset action, allowing a new scope for PSAKs, handling synthetic users (ProjectSecretAPIKeyUser), or choosing PSAK-aware rate throttles. Trigger terms: PSAK, ProjectSecretAPIKey, project secret API key, phs_ token, service auth, programmatic endpoint auth.
Add a new warehouse-backed source to the PostHog Desktop Self-driving Inbox (the feature that ships GitHub, Linear, Zendesk, pganalyze, Jira). A source syncs one warehouse table (issues/tickets/conversations) and a cloud "signals scout" watches it and emits findings. Use when asked to "add a new inbox/self-driving source", "wire up <Jira/GitLab/Sentry/Intercom/Freshdesk/Front/Gorgias/etc> as a signal source", or to extend the source-toggle grid. Covers all three surfaces (posthog/posthog scout emitter + posthog/code UI wiring + the context-mill self-driving wizard skill that offers the source in `npx @posthog/wizard self-driving`), the deploy ordering between them, and created_via attribution.
Add a third-party MCP server (Linear, Notion, GitHub, ...) to the PostHog MCP store catalog. Use when asked to "add X to the MCP store", expand the MCP server marketplace, or fix a broken catalog entry. Covers finding the vendor's remote MCP endpoint, probing it (handshake, OAuth discovery, DCR), authoring the catalog entry in products/mcp_store/backend/catalog.py, verification tiers, and the operator handoff for servers without Dynamic Client Registration.
> PRs that conflict with master, resolve the trivial conflicts (generated artifacts deterministically, source conflicts with judgment), land a single signed commit on the PR head, and flag everything else for a human. Use when running as the "Autoresolve PR conflicts" Loop, when asked to sweep or auto-resolve merge conflicts against master, or when asked to bring a conflicting PR up to date merge conflicts, conflicting PRs, bring PR up to date, restack.
Guide for adding a product setup empty state — the skippable first-run screen a product scene shows until real data arrives, built on the shared ProductEmptyState component. Use when adding an empty state or first-run/setup screen to a product scene, declaring `emptyState` on a `SceneExport`, writing a product setup-status detection logic, building an animated example-data preview widget, or migrating away from the deprecated `ProductIntroduction` component. Covers the `productSetupStatusLogic` single-layer contract, real-data detection rules, local-only skip semantics, wizard commands, and design tokens.
Audit already-implemented Data warehouse import sources for endpoints, schemas, and tables the vendor's API offers but we never wired up. Use when asked whether a source is missing endpoints, to find new endpoints a vendor has added since a source was built, to refresh COVERAGE_GAPS.md, to prioritize which source to deepen next, or to check coverage before an integration review. Covers dumping our real endpoint inventory credential-free, ranking sources by production adoption, diffing against vendor OpenAPI/GraphQL specs, and recording findings. Not for implementing a source (use implementing-warehouse-sources), adding a vendor API version (warehouse-source-new-version), or writing source docs (documenting-warehouse-sources).
> Analyze PostHog insights, dashboards, or teams beyond the current project by querying the prod Postgres replicas synced into the dogfood data warehouse (US project 2, "PostHog App + Website"). Use when asked to analyze insights across all teams or projects, another team's insights, or fleet-wide insight/dashboard usage — cases where `system.insights` only returns the current project's rows and the agent would otherwise report the data as inaccessible. Covers the synced table names for US and EU and the column-verification workflow.
> Use when adding or editing a GitHub Actions workflow, composite action, or reusable workflow under `.github/` — new CI jobs, triggers, matrices, checkout/clone tuning, action pinning, GitHub App token auth, concurrency groups, `timeout-minutes`, `paths` filters, caching, or runner choice. Not for debugging red CI (use debugging-ci-failures) or wiring a new secret end to end (use managing-github-actions-secrets).
> Debugs failing GitHub Actions CI runs for PostHog PRs, commits, and branches, and answers broad CI-health questions ("is CI red?", "is master green today?", "what's broken right now?"). Use when the user asks why CI is red, asks for the current CI or master status, or mentions a failing check, GitHub Actions run, Depot runner, workflow, job, shard, flaky test, lint failure, typecheck failure, snapshot diff, migration check, generated types drift, or skills CI intelligence), then guides read-only inspection, failure classification, smallest local reproduction with hogli, and safe reporting without rerunning CI or posting to GitHub.
ClickHouse migration patterns and rules. Use when creating or modifying ClickHouse migrations.
Debug the output of local PostHog task runs — the wizard cloud-run path that executes inside a Docker sandbox under the local Temporal `process-task` workflow (the wizard that integrates PostHog, then the coding agent that commits and opens the PR). Use when a local run looks stuck, failed, or silent, or when you need to read the wizard or agent logs. Covers the `.env.local` keys + `ai_features` intent required for cloud runs locally, finding the task UUID (docker ps, temporal CLI, Temporal UI at localhost:8081), tailing live logs inside the sandbox container (`/tmp/posthog-wizard.log`, `/tmp/agent-server.log`), and reading the durable per-run console log from object storage after the sandbox is torn down. Trigger terms: task-sandbox, run_wizard, agent-server, process-task, SANDBOX_PROVIDER, LLM_GATEWAY, cloud_run, posthog-wizard.log.
Write or update the user-facing posthog.com documentation for a PostHog Data warehouse import source. Use when adding a new source doc, fixing an inconsistent or stub source doc, or standardizing the docs at contents/docs/cdp/sources. Covers the canonical template, shared snippets, the auto-rendered <SourceParameters /> and <SourceTables /> components, frontmatter, and the docsUrl/slug rule that prevents 404s.
> Configures Depot-managed GitHub Actions runners as a drop-in replacement for GitHub-hosted runners. Use when setting up or migrating GitHub Actions workflows to use Depot runners, choosing runner sizes (CPU/RAM), configuring runs-on labels, setting up ARM or Windows or macOS runners, troubleshooting GitHub Actions runner issues, configuring egress filtering, using Depot Cache with GitHub Actions, or running Dagger/Dependabot on Depot runners. Also use when the user mentions depot-ubuntu, depot-windows, depot-macos runner labels, or asks about faster/cheaper GitHub Actions runners.
Claude Skills — questions
Answers built from the skills we actually parsed.