Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Guides work on `packages/frontend/editor-ui` experiments. Use when creating, extending, wiring, testing, reviewing, or retiring editor-ui experiments, PostHog feature flags, experiment key indexes, variants, stores/composables, persisted experiment state, or experiment telemetry.
Look up Banuba Video and Photo Editor SDKs reference docs, guides, and configuration pages. Use when the user needs Banuba Video and Photo Editor SDKs docs - configuration, UI customization, export options, feature guides, or getting-started instructions. Also trigger with "Banuba Video Editor SDK", "Banuba Photo Editor SDK", "Video Editor", "Photo Editor", or "Banuba SDK" when the user needs an existing doc page. Not for writing code or building projects - use the build-video-editor or build-photo-editor skills for that.
Explore PostHog MCP intent clusters — agent goals grouped by semantic similarity, with each cluster's tool distribution and error rates, plus the tool-centric pivot (capture rate per intent, discovery rate against the advertised catalog, description fit, tool overlaps). Use when the user asks "what are agents trying to do with the MCP?", "group the intents", "which goals fail most?", "what does each cluster route to?", "when agents have this intent do they find my tool?", "which tools get mixed up?", wants to recompute the clustering, or pastes an MCP analytics intent-clustering URL.
Investigate individual PostHog MCP sessions — the sequence of tool calls a single agent made in one run, what it was trying to do, and where it went wrong. Use when the user asks "what did this MCP session do?", "show me the tool calls for session X", "what was the agent's goal?", "which sessions had errors?", "who is connecting to my MCP?", or pastes an MCP analytics sessions URL.
Build a starting-point taxonomy for an MCP tool — what users were trying to accomplish before they reached the tool — and publish it as a PostHog notebook. Reconstructs each session's goal from its opening tool calls, then clusters those goals into named categories with size, share, and facet mix. Use when the user asks "why do people use this tool?", "what are users actually trying to do?", "what problem brings people here?", "where do these sessions start?", "segment usage of <tool> by goal", or wants a Clio-style taxonomy of MCP usage. Complements exploring-mcp-intent-clusters, which groups what agents did per call rather than why the session began. The agent running this skill writes the goal labels itself, reading the corpus query output session by session — the bundled scripts cover the mechanical facets but measurably lose the goal's altitude, so do not delegate that field to them.
Investigate the quality of PostHog MCP tool calls — error rates, latency, reach, and which tools are failing or slow. Use when the user asks "which MCP tool has the highest error rate?", "what's the slowest tool?", "which tools fail most often?", "how reliable is tool X?", wants a tool-quality matrix, or pastes an MCP analytics tool-quality / dashboard URL and asks what it shows.
Guides agents through pulling a Replay Vision scanner's observations, reading the findings, and acting on them — summarizing patterns across sessions, drilling into individual recordings, and turning real, corroborated issues into PostHog tasks, insights, or an investigating-replay hand-off.\nTRIGGER when: user wants to pull/read/triage Replay Vision observations, asks \"what has my scanner found\", wants to act on or summarize scanner findings, turn observations into tasks/work, or points at a /replay-vision/<scanner-id> URL.\nDO NOT TRIGGER when: creating or sizing a scanner (use creating-replay-vision-scanners), running a one-off scan you don't then analyse, or authoring a signals scout.
Extended thinking (ultrathink) configuration for Claude API. Activate for complex reasoning tasks, deep analysis, multi-step problem solving, and tasks requiring careful deliberation. Enables Claude's internal reasoning with configurable thinking budgets.
Generate landing pages/webpages with the Felo Landing Page Task API in Claude Code. Use when users ask to create/make/generate a landing page, marketing page, single-page website, AI webpage, HTML page result, or when explicit commands like /felo-landingpage are used. Handles API key check, task creation, polling shared task history, and final ai_page_html output.
Richard Feynman’s thinking framework and communication style. Based on in-depth research across 40+ primary sources, distilling 5 core mental models, 8 decision heuristics, and a complete communication DNA. Use as a thinking adviser to analyze problems, examine decisions, and provide feedback from Feynman’s perspective. Trigger when the user mentions “from Feynman’s perspective,” “what would Feynman think,” “Feynman mode,” “feynman perspective,” or “Feynman technique.” It can also trigger when the user asks whether something is “cargo cult,” says “naming isn’t understanding,” asks whether a demonstration can replace an argument, or wonders “do I really understand, or have I just memorized the name?” Do not trigger for general requests such as “explain this” or “put it simply”—activate only for Feynman-style verification (cargo-cult detection, naming vs. understanding, and resisting self-deception).
Orchestrate a complete PhD / research-program application package end-to-end — from reading the applicant's materials through CV, program & faculty fit, SOP, recommender strategy, professor outreach, a final package audit, and interview preparation once shortlists arrive. Use whenever the user wants to drive the whole application rather than one piece: "help me with my PhD applications", "where do I start with my application", "manage my application process", "I'm applying to PhD programs, what's the plan", "get my materials ready", or hands over a folder of CV/transcripts/notes and asks for the path to submission. This is a ROUTER that sequences existing singleton skills with stage gates; it does not write the SOP, CV, or emails itself. For a single piece, invoke that skill directly (e.g. apply-sop-writer, apply-cv-builder). For driving a research paper use flow-paper-lifecycle.
Fonts for Decentraland SDK7 text: the three built-in faces and custom `.ttf` fonts shipped with the scene (`fontSrc`), for 3D and UI text. Use when the user wants a custom or branded typeface, wants to change a text's font, ships a `.ttf`, or asks why a custom font isn't showing. For text layout, see build-ui; for placing 3D text, see advanced-rendering
Connects a website or app form to Forminit (forminit.com), the headless form backend, creates one when there is none (a paste-ready HTML form when there is no code to edit), or fixes a broken Forminit integration. Works with HTML, React, Next.js, Vue, Nuxt, Svelte, SvelteKit and Astro: maps each input to fi-* field names such as fi-sender-email and fi-checkbox-topics[], wires the submit with the forminit SDK and keeps the existing design and logic. Use when the user mentions Forminit, gives a Forminit Form ID, pastes a Forminit setup prompt, has forminit.com/f/ URLs or fi-* names in code, or hits Forminit errors like FORM_NOT_FOUND. Also use when a contact, lead, quote, booking, RSVP, feedback, waitlist or job application form on a static or AI-built site must deliver submissions without a backend. Not for login, account signup, password, payment or search forms.
Expert in Freshdesk helpdesk API for building integrations, extracting support data, managing tickets/contacts/companies, and automating support workflows. Use when working with Freshdesk, building helpdesk integrations, analyzing support ticket data, or creating customer support applications.
Classical end-to-end empirical analysis workflow in the traditional Stata ecosystem — native Stata + reghdfe + ivreg2 + csdid + did_imputation + eventstudyinteract + sdid + rdrobust + rddensity + synth + synth_runner + psmatch2 + teffects + ebalance + coefplot + esttab + asdoc + binscatter. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) — every run produces a publication-ready output set with a multi-column regression table (M1→M6 progressive controls/FE) as the centerpiece, plus Table 1 (descriptives), mechanism / heterogeneity / robustness tables, and event-study + coefficient + trend figures. Covers the full 8-step Stata pipeline an applied economist runs on every paper — (1) data import & cleaning (use/import, destring, misstable, duplicates, merge assert), (2) variable construction (gen/egen/winsor2/xtile/xtset with L./F./D.), (3) descriptive statistics & Table 1 (tabstat/balancetable/asdoc), (4) classical diagnostic tests (sktest/swilk/hettest/imtest/xtserial/xttest3/vif/dfuller/kpss/hausman/estat overid), (5) baseline modeling (reg/xtreg/reghdfe/ivreg2/ivregress/csdid/did_imputation/eventstudyinteract/sdid/rdrobust/synth/psmatch2/teffects/heckman/qreg/ppmlhdfe), (6) robustness battery (bacondecomp/honestdid/rwolf/ritest/wildbootstrap/oster), (7) further analysis (subgroup/triple-diff/interactions/medsem/marginsplot/binscatter by group), (8) publication-ready tables & figures (esttab/outreg2/estout/coefplot/marginsplot/rdplot/twoway combined). **Also covers two parallel domain modes that share the same 8-step scaffolding** — **Mode A — Epidemiology / public health** (target-trial emulation, IPTW + g-formula + TMLE doubly-robust triplet via `teffects ipw` / `teffects ipwra` / `teffects aipw` / `eltmle`, Mendelian randomization via `mrrobust` (IVW / Egger / weighted median) and `mregger` / `mrpresso`, KM / Cox / AFT / RMST survival via `sts` / `stcox` / `streg` / `strmst2`, E-value sensitivity via `evalue` (Linden-Mathur), principal stratification — STROBE / TRIPOD reporting), and **Mode B — ML causal inference** (DML via `ddml` / `pdslasso`, S/T/X/R/DR meta-learners via `crforest` and `ddml interactive`, causal forest via `crforest` / `cforest`, BART/BCF via `bart` / `bartCause`-style externals, CATE distribution + policy tree via `crforest`, off-policy evaluation, conformal causal externals, fairness audit, DAG learning via `pcalg` / external Python callouts). Use when the user asks for a complete Stata empirical analysis, wants a reproducible .do-file pipeline, needs a Stata counterpart to the Python StatsPAI / Full-empirical-analysis-skill, or names a specific Stata step in isolation ("run reghdfe with two-way clustering", "csdid event study", "winsor2 at 1%", "esttab to LaTeX", "coefplot with CI", "ivreg2 weak-IV test", "synth_runner placebos", "teffects psmatch balance check"). Mode A triggers on "target trial emulation Stata", "teffects ipw aipw", "eltmle", "mrrobust", "mregger weighted median", "stcox AFT survival", "strmst2", "evalue Stata", "STROBE Stata", "公共健康 Stata", "流行病学 Stata". Mode B triggers on "ddml Stata", "pdslasso", "crforest causal forest Stata", "policy tree Stata", "因果机器学习 Stata".
Generate comprehensive technical documentation including API docs (OpenAPI/Swagger), code documentation (TypeDoc/Sphinx), documentation sites (Docusaurus/MkDocs), Architecture Decision Records (ADRs), and diagrams (Mermaid/PlantUML). Use when documenting APIs, libraries, systems architecture, or building developer-facing documentation sites.
Systematic visual geolocation reasoning from images. [VAD] Analyzes photos, street views, or satellite imagery to determine location. Uses visual clue extraction, hypothesis formation, and web verification. [NÄR] Use when: geolocate, identify location, where is this, find this place, geographic analysis, location from image, OSINT geolocation [EXPERTISE] Visual analysis, geographic indicators, verification strategies
Turn scattered point measurements into continuous surfaces with quantified uncertainty: variogram modeling, ordinary/universal/regression kriging, IDW, and spatially honest cross-validation. Use when unobserved values must be estimated from sparse samples such as stations, wells, or soundings. Trigger on "interpolate", "kriging", "variogram", or "IDW"; a named interpolation method is sufficient even when the requested surface is described informally as a heatmap. Do not use for point-density heatmaps, zonal aggregation, or raster resampling without value interpolation.
Fetch and analyze Bolna call execution data, raw logs, transcripts, recordings, costs, statuses, hangup details, extracted data, agent history, and batch executions. Use for debugging failed calls, analytics export, CRM sync, webhook reconciliation, and call monitoring.
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
Gang of Four design patterns reference. Use this skill when implementing, discussing, or choosing object-oriented design patterns. Auto-activates for architecture decisions, refactoring, and decoupling concerns. Comprehensive coverage of all 23 GoF patterns with pseudocode examples.
Use when refactoring existing code toward a known GoF pattern — phrases like "refactor this to use Strategy", "extract a Decorator from these flags", "this switch should be State", "replace conditional with polymorphism", "introduce a Factory here". Sequences small behavior-preserving refactor steps and links to the destination pattern skill.
Complete collection of Google's official style guides for 17 languages. Includes TypeScript, JavaScript, Python, Java, Go, C++, C#, Swift, Objective-C, HTML/CSS, AngularJS, Shell, R, Common Lisp, Vim Script, JSON, and Markdown. Production-ready coding standards used across Google's engineering organization, formatted for AI agent consumption.
Recommend which GPT-5.6 model tier (Luna/Terra/Sol) and reasoning effort (Low..Ultra) fits a task, learn from the user's own successes and failures, diagnose quality problems, and report the live session's model and effort. Advisory — it proposes a grounded starting point and an escalation rule; the human decides and switches. Load when the user asks which model or effort to use, starts a substantial task without deliberately choosing a tier, reports a poor or unsatisfying result, wants to reduce cost without losing quality, or asks what model the session is running. Triggers — "which model", "which effort", "reasoning effort", "cut cost", "is a bigger model worth it", "do I need max/ultra", "result is bad", "quality dropped", "what model am I on", "record this combo".
Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.
Technical article writing, polishing older drafts, and restoring the author's voice. Suitable for in-depth technical articles, hands-on tool retrospectives, FAQs/Q&As, methodologies, and long-form public-account posts; also checks the style and AI feel of drafts intended for social media. Triggers: write an article, write in my style, restore the human feel of the original, polish, review a social draft, check for AI feel
Drives a Dart or Flutter package fully green through a verify-fix-rerun loop across four gates: analyze, format, test, coverage. It owns gate configuration, so plan-only questions belong here: which tool and arguments run each gate, in what order, the coverage target, and what leaves the coverage denominator. Use it for "green gate", "make it green", "get CI green", fixing all analyze and test failures, cleaning a package up before a PR, bringing coverage to 100, looping until everything passes, or confirming a package is green. Use it too when the user wants a gate weakened or skipped: lowering the coverage threshold, coverage ignore comments on untested or generated code, skipping analyze and format because they passed earlier, calling a 94% package done, or retrying while the same failures repeat. Prefer it over the single-gate testing or analysis skills.
Build or review Nuxt 3/4 animation: GSAP pageTransition and layoutTransition hooks, component enter/exit, scroll effects, keepalive, and cleanup. Use for interrupted navigation, missing done callbacks, or choosing Vue CSS and View Transitions, even when GSAP is unnamed. Also covers hidden-content recovery and first-load performance. Not for plain Vue or isolated GSAP API questions.
Build or review SvelteKit animation on Svelte 5: GSAP page transitions, component enter/exit, scroll effects, route reuse, and cleanup. Use for interrupted navigation or choosing GSAP, Svelte transitions, or View Transitions, even when GSAP is unnamed. Also covers hidden-content recovery and first-load performance. Not for plain Svelte or isolated GSAP API questions
Build or review TanStack Router for React and TanStack Start animation: GSAP page transitions, component enter/exit, scroll effects, useBlocker, pending UI, route reuse, and cleanup. Use even when GSAP is unnamed, including choosing viewTransition. Also covers hidden-content recovery and first-load performance. Not for Solid, other routers, React without routing, or isolated GSAP API questions.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.