Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Optimize Django and pytest-django test execution in CI with cache configuration, slow-test splitting, database reuse strategy, parallel workers, pytest-xdist, CircleCI/GitHub Actions/Jenkins/Travis patterns, and full-coverage safeguards. Use when CI test jobs are slow, flaky under parallelism, missing slow-test coverage, or need a local-vs-CI test command design.
Expert Django backend development guidance. Use when creating Django models, views, serializers, or APIs; debugging ORM queries or migrations; optimizing database performance; implementing authentication; writing tests; or working with Django REST Framework. Follows Django best practices and modern patterns.
Mock Django test boundaries safely with override_settings, pytest settings, autospecced unittest.mock objects, output/input capture, requests-mock, VCR.py, outbound HTTP blocking, and time-freezing tools. Use when tests need to replace settings, HTTP calls, time, command output, stdin, or external services without broad fragile MagicMock patches.
Safely parallelize Django and pytest-django test suites with Django --parallel, pytest-xdist, test isolation checks, randomized order detection, shared-resource sharding, locks, and load balancing. Use when enabling parallel tests, diagnosing failures under parallel execution, handling flaky Django tests, or making caches, files, queues, and external resources safe across workers.
Profile and measure slow Django test suites with Django's runner, pytest-django, shell timing, py-spy, cProfile, pytest durations, and profiler visualizations. Use when a Django project has slow tests, unclear test-runtime bottlenecks, CI timing problems, startup overhead, database setup overhead, or a request to find the slowest tests before optimizing.
Search the Grounded Docs MCP Server documentation index. Covers listing indexed libraries, searching documentation content, and resolving library versions. Use when you need to look up API references, find code examples, or check which documentation is available in the local index.
Extract images from Word (.docx) and PDF (.pdf) documents and save them to a specified folder. Use cases include: (1) extracting images from Word documents, (2) extracting images from PDF documents, (3) batch-extracting images from multiple documents, (4) extracting all image assets from a document
Write or update technical documentation grounded in the real codebase. Use when the user asks for README, API docs, architecture guides, user guides, CONTRIBUTING docs, migration notes, or JSDoc/code comments, or wants technical docs rewritten into natural Chinese with correct terminology. Not for general prose, marketing or social copy, or non-technical localization.
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
Build high-leverage sales messages that attract qualified buyers and repel poor-fit prospects. Use when writing or diagnosing headlines, landing pages, outreach, ads, sales letters, lead magnets, or B2B messages where urgency, qualification, and conversion matter.
Segment customers and lists by 80/20 value, responsiveness, recency, frequency, and money. Use when identifying best customers, prioritizing follow-up, finding high-value buyers, pruning low-value accounts, or deciding what customer data to measure.
Diagnose and prioritize sales funnel improvements by economics, conversion, split testing, and high-value customer potential. Use when optimizing funnels, deciding what to test, improving CAC or profit, evaluating upsells, or choosing the few metrics that matter now.
Find hyper-responsive buyers and disqualify weak markets using 80/20 Sales and Marketing. Use when choosing a target segment, validating demand, screening prospects, finding urgent buyer problems, or deciding whether a market is worth sales and marketing effort.
Apply 80/20 power-curve thinking to sales, marketing, customers, offers, traffic, time, and operations. Use when finding leverage, diagnosing uneven results, prioritizing high-upside segments, or replacing average-based reasoning with Pareto and power-law analysis.
Apply 80/20 leverage to time, talent, assistants, outsourcing, hiring, salespeople, and low-value work. Use when deciding what to delegate, outsource, stop doing, hire for, trial, or remove so high-value people spend more time on their strongest work.
Prioritize traffic, media, lists, and audience sources with an 80/20 lens. Use when choosing acquisition media, deciding which traffic source to master, evaluating rented or owned lists, sequencing channel expansion, or shifting budget toward higher-leverage sources.
Deploy an Encore.ts or Encore.go app to Encore Cloud by pushing to the Encore git remote or a linked GitHub repository, deploy changes again, and fix deploys that fail or never start. Covers which environments a push deploys to and secrets per environment. For linking an app first, see `encore-link-app`.
Detect CLOUD_AGENT vs LOCAL_WORKSPACE and apply the matching agent constraints. Use at session start when choosing tests, credentials, Hub continuity fallback, or whether local skill CLIs (e.g. graphify) exist. Hub MCP unavailable (not runtime alone) triggers the forge `[ADHD]` issue mailbox; never invent Hub or graphify state.
Record domain events and dispatch to inbox handlers for side effects, audit trails, and activity feeds. Use when building activity logs, syncing external services, or decoupling event creation from processing. Triggers on event recording, audit trails, activity feeds, or inbox patterns.
Use this skill for Customware existing-project migration tasks that move uploaded customer apps from other builders into the standard Customware stack while preserving the source product's routes, workflows, UI, UX, and styling with no intentional user-facing changes while replacing only the runtime foundation. This skill covers both `Migration build` and `Migration verify` and includes self-grading quality gates that must pass before the task can complete.
Execute one bounded research experiment branch in the current session with ponytail-for-experiments taste. Use when explicitly requested, or for a single coherent batch of runs with known configuration (one method × dataset × budget, or one ablation branch of a campaign). First check the branch was not already pruned or answered, grill only unresolved config decisions, preflight environment and resources, run per project conventions, and land metrics in the shared table in a shape the final figures can use directly. Prefer exp-discuss when the idea is still fuzzy and needs talking through; prefer exp-campaign when the work needs staged pruning across branches; prefer exp-probe for one-off spot checks.
Design a staged, prunable research experiment campaign for a researcher's idea, hypothesis, or optimization direction, with ponytail-for-experiments taste. Use when explicitly requested, or when a researcher proposes a direction that needs many experiments, ablation branches, or cross-factor sweeps. Observe existing results, grill the researcher to shared understanding, enumerate the maximal experiment space, then prune it with cheap probe experiments whose outcomes decide which cells never run; deliver a decision-tree plan with observation gates and the final metrics/figure design, and hand execution to exp-batch per stage. For a single bounded experiment branch use exp-batch; for one-off spot checks use exp-probe.
Run one-off research spot experiments with minimal ceremony. Use when explicitly requested, or for a missing datapoint, a rerun after failure (OOM, crash), a sanity check of one configuration, a minimal bug reproduction, or a cheap measurement that a campaign needs before deciding. At most one focused question; run, record, report in one line. Escalate to exp-batch if the spot check turns into a branch, or exp-campaign if it reveals a decision tree; if the question itself is still fuzzy, route back to exp-discuss.
Explains code with visual diagrams and analogies. Use when explaining how code works, walking through a codebase area, or when the user asks "how does this work?" Don't use for modifying code, fixing bugs, generating new implementations, or multi-session concept learning (use /teach).
Predict the smallest atomic next engineering action from current workspace state, evidence gates, and mutation freshness with situational silence. Use when evaluating what immediate atomic step to take next, checking situational awareness, or determining if the current state requires action or silence — even if the user does not explicitly say "fable-spark" (e.g. "what is my next move", "spark hint", "check next action", "what should I do now"). Do NOT use as a substitute for broad architectural planning (use fable-plan).
Use when user requests Chinese terminology conversion, checking, or ensuring terminology - "使用繁體中文", "使用台灣用語", "轉換成台灣用語", "確保都是台灣用語", "統一台灣用語", "改成台灣用語", "用台灣的說法", "簡體轉繁體", "繁體轉簡體", "全部改成繁體", "轉成台灣繁體", check/ensure Taiwan/Hong Kong/China terminology, simplified/traditional conversion, or phonetic transcription (Pinyin/Bopomofo)
Track feature implementation status against requirements documents. Provides hierarchical FR code tracking, phase management, task tracking, and sync with TODO.md. Use when the user works with FR codes like FR1.2.1, manages phase-based development progress, links features to PRDs via feature-tracker.json, or needs to recalculate completion statistics.
Extract a design system from vibe-coded production apps that never had one: inventory components, mine de-facto styling into DTCG tokens, scaffold a Storybook package, port components, and optionally round-trip tokens/components into Figma. Use when the user wants to 'extract a design system', 'create a design system from this app/codebase', 'reverse-engineer our components into Storybook', 'turn our app styles into tokens', or 'consolidate the UI of several AI-built products'. Works best with the figma-console-mcp local server connected (figma_ds_* tools); includes an agent-driven fallback.
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.
Plan, audit, or revise the figures, tables, captions, and visual evidence for a research paper. Use this skill whenever the user asks what figures or tables they need, whether a result should be a plot or table, how to present experiments, how to design ablation tables, how to make captions self-contained, what belongs in the appendix, or whether the current visual evidence supports the paper's claims. This skill is especially useful after experiment design and before writing the Results section.
Comprehensive financial research agent for market data, news analysis, technical indicators, and report generation. Use when Codex needs to: research stocks/crypto/macro data, analyze market trends, scan financial news, generate investment theses, or produce structured research reports. Integrates with Polymarket for price tracking and supports multiple data sources (Yahoo Finance, CoinGecko, etc.).
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.