Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Maintain documentation for the ai-dev framework and ai-dev-skills collection. Use when code or skill changes affect documented behavior, commands, agents, plugins, version releases, repository structure, README content, or changelogs. Applies to requests written in English or Chinese.
The read-only morning audit: last 7 complete days vs the prior 7, wasted budget, fading ads, starved tests, pixel problems, one next test. Max 5 recommendations, changes nothing. Use every morning, or right now on any account you suspect is leaking.
Queries various types of data, including exchange rates, the lunar calendar, historical events, encyclopedia entries, oil prices, gold prices, and chemical elements. Use when users need exchange rates, lunar calendar, historical events, encyclopedia, commodity prices, or chemical element information.
Use the `date` command via Bash tool whenever you or the user mention time, dates, or temporal concepts. Verify current date/time before ANY temporal response, as environment context may be outdated. Parse expressions like "tomorrow", "next week", "3 days", "in 2 weeks", "next Monday at 3pm". Proactively invoke for deadlines, schedules, time-sensitive tasks, week numbers, or any date/time reference.
Audit concurrency correctness — transaction isolation level, lost-update / read-modify-write races, queue-worker contention (SKIP LOCKED), and idempotency for key-value / document / wide-column writes. Module M14. Feeds the Performance & Scale score.
Audit data-integrity constraints — missing NOT NULL on required columns, absent CHECK constraints for domain rules, missing UNIQUE on natural keys, and the over-nullable UNIQUE trap where NULLs silently permit duplicates. Module M5. Feeds the Design & Integrity score (Constraints category).
Audit column defaults and generated columns — application-side timestamps that should be DB defaults, non-deterministic or wrong defaults, derived values that should be GENERATED ALWAYS / computed columns instead of drift-prone duplicated data, and identity/sequence defaults. Module M6. Feeds the Design & Integrity score (Tipos category, shared with M4).
Engine selection (M0) — at design/start time, recommends a database paradigm and engine for a described workload (access patterns, consistency needs, scale, team, platform), and names the runner-up with the trade-off you're accepting. M0 is a RECOMMENDATION, not a scored audit module — it emits no findings and never contributes to the Design or Performance score. Walks the decision tree in references/engine-selection-tree.md and is honest about lock-in and operability instead of fabricating benchmarks.
Audit primary-key strategy — missing PK (severity 5), surrogate vs natural keys, UUIDv4 index fragmentation vs time-ordered UUIDv7/ULID/bigint, and int4/serial exhaustion on high-volume tables. Module M2. Feeds both the Design & Integrity (Llaves) and Performance & Scale (Escala) scores.
Migration-safety lint (M22) — the static contract the migration-safety auditor (MSA) and db-migration-writer enforce on a candidate migration BEFORE it runs. Checks reversibility (down migration present / expand-contract), lock level (does it take ACCESS EXCLUSIVE on a hot table), table rewrite (full-table rewrites on type/default changes), destructive ops (DROP COLUMN/TABLE, TRUNCATE), unsafe enum mutation, NOT NULL without default on a large table, and schema drift between the declarative artifact and migration history. Feeds the Performance & Scale score.
Audit naming conventions — inconsistent table/column casing and pluralization, ambiguous or reserved-word identifiers, untyped/opaque columns, inconsistent FK and boolean naming, and identifiers that fight the engine's case-folding rules. Module M7. Feeds the Design & Integrity score (Naming category, low weight).
Orchestrates a full database audit — detects the stack(s), dispatches read-only auditor subagents in parallel by paradigm, merges and dedupes their findings, computes the two never-blended scores (Design & Integrity + Performance & Scale) via score.mjs, and renders the report. Invoked by the audit command; not usually called directly.
Audit foreign-key integrity — missing FKs that allow orphan rows (financial/auth = severity 5), absent or unsafe ON DELETE/ON UPDATE actions, reference cycles, and composite-FK column/order mismatches. Module M3. Feeds both the Design & Integrity (Integridad referencial) and Performance & Scale (Query) scores.
Specialized-engine fitness (M20) — checks whether a vector, time-series/OLAP, graph, or search store is configured correctly for its job. M20a vector (dimensions match the embedding model, distance metric matches how the model was trained, HNSW/IVFFlat params present), M20b time-series/OLAP (hypertable/partition fit, continuous aggregates, compression), M20c graph (edge modeling, supernode risk, index-backed lookups), M20d search (analyzer/mapping, FTS config). Feeds the Design & Integrity AND Performance & Scale scores per sub-module.
Guides DBeaver usage for database connection management, SQL development, data import/export, and ER diagram generation across MySQL, PostgreSQL, Oracle, MongoDB, and other databases. Use when the user needs to configure DBeaver connections, write queries in the SQL editor, export data, or generate ER diagrams.
Use when the user wants concrete code that realizes a DDD pattern — phrases like "scaffold an entity for X", "write the Aggregate for Y", "give me the repository interface", "implement this value object". Drives the conversation through naming + invariants and then delegates code generation to a language adapter skill (e.g., ddd-kotlin-idioms for Kotlin). Do NOT use for refactoring (route to ddd-refactor), review (route to ddd-review), or design from scratch (route to ddd-design)
Conduct deep adaptive interviews to extract and organize knowledge into structured files and folders. Use when user says "interview me about X", "deep interview", "extract my knowledge", "build knowledge base from interview", "ask me questions about X", or wants to systematically capture expertise on any topic through guided questioning.
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.
Generates a delivery timeline from a completed milestones.yaml. Asks for a production deploy date, QA rounds, and days per QA session. Updates each milestone with estimated_days, produces timeline.yaml with a complete relative-day schedule, and appends a workback block mapping every item to a real calendar date working backwards from the production deploy date.
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use for identifying cancer-specific vulnerabilities, synthetic lethal interactions, and validating oncology drug targets.
Greenfield database design — pick the right engine for a new project, compare it against the boring default, and hand back a starter data model with a diagram. Recommendation mode (module M0); never scored, never destructive. Use when the user is starting fresh and asks what database to use, how to model a new app, which engine fits, or for a schema/data-model from scratch.
Current award-winning design patterns and emerging techniques in web design (Q1/Q2 2026). Covers motion, typography, color, layout innovations, and interaction patterns derived from Awwwards, CSSDA, Godly, and SiteInspire analysis. Structured for periodic updates.
Extract cognitive patterns and thinking fingerprints from any text. Use this skill when the user wants to analyze how someone thinks, understand cognitive style, profile writing or speech patterns, compare thinking styles between people, asks "what's my thinking style", "analyze how this person reasons", "cognitive profile", "thinking pattern", "DHDNA", "digital DNA", or wants to understand the mind behind any text. Also trigger when the user provides text and wants deeper insight into the author's reasoning patterns, decision-making style, or cognitive signature.
Distill each day's raw activity into a daily report. Ensures ~/.Life exists, pulls the day's activity via Luci, writes an objective report under ~/.Life/reflections/daily/, and writes new entities under ~/.Life/entities/. Use when the user says "distill", "distill my life", "catch up on daily reports", "summarize the last few days", or first needs the life folders created.
Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file storage in settings.py. Configures the Django 4.2+ STORAGES dict, public/private custom backends, presigned GET/POST URLs, IAM policies, and S3 mocking for tests. Trigger terms: django-storages, S3, boto3, S3Boto3Storage, STORAGES, presigned URL, CloudFront, media files, collectstatic, AWS_STORAGE_BUCKET_NAME.
This skill should be used when deciding whether a doc should exist, where it belongs, whether something is really an ADR, or whether an architectural decision is missing from the record. PROACTIVELY activate on "should this be an ADR?", "where should I document X?", "is this architecturally significant?", "ADR vs RFC vs design doc vs runbook", "Diátaxis", "audit docs folder", "clean up the decision log", "doc drift", "doc governance", "ADR template selection", "Nygard vs MADR vs Y-statement", "missing ADR", "missing decision record", "undocumented architecture", "implicit decision", "historical documentation clutter", "inherited repo", "large legacy repo", "architecture archaeology", "code archaeology", "scan for decision records", "find decisions not captured in ADRs." Provides: doc placement diagnostic, alternatives catalog, ADR canon, folder audit procedure, and BACKFILL-ADR candidate detection.
Use when YOU (the AI agent) are running on Windows OUTSIDE WSL (Git Bash/MSYS/PowerShell shell) and need to run ANY docker / docker compose command. Docker Desktop runs on the WSL2 engine, so commands must be re-issued INSIDE WSL via wsl.exe -- running them from the Windows shell on a network/SMB drive (Z:, UNC) corrupts bind-mount paths. Does NOT apply if your shell is already inside WSL. Triggers on: docker, docker compose, docker-compose, container, bind mount, volume, 'is a directory', mount source wrong, Windows + Docker Desktop, WSL.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
Python library for accessing, analyzing, and extracting data from SEC EDGAR filings. Use when working with SEC filings, financial statements (income statement, balance sheet, cash flow), XBRL financial data, insider trading (Form 4), institutional holdings (13F), company financials, annual/quarterly reports (10-K, 10-Q), proxy statements (DEF 14A), 8-K current events, company screening by ticker/CIK/industry, multi-period financial analysis, or any SEC regulatory filings.
Guides Elasticsearch usage including index mapping design, query DSL (match, term, bool, aggregations), bulk indexing, cluster management, and performance tuning. Use when the user needs to implement full-text search, design index mappings, write complex search queries, or manage Elasticsearch clusters.
Microsoft Entra Agent ID (preview) for creating OAuth2-capable AI agent identities via Microsoft Graph beta API. Covers Agent Identity Blueprints, BlueprintPrincipals, Agent Identities, required permissions, sponsors, and Workload Identity Federation. Includes Microsoft Entra SDK for AgentID (containerized sidecar) for polyglot agent authentication (Docker/Kubernetes), 3P agent integration, autonomous and interactive agent patterns. Triggers: "agent identity", "agent id", "Agent Identity Blueprint", "BlueprintPrincipal", "entra agent", "agent identity provisioning", "Graph agent identity", "entra sidecar", "agent id sidecar", "auth sidecar", "3P agent", "third-party agent identity", "polyglot agent auth".
Eva Teaching 2.5.0 provides beginner tutorials, benchmark teardowns and study, and manuscript review and editing. Use for /eva-teaching, /eva-new-user, /eva-benchmark-copy, teaching me how to use Eva, tearing down third-party self-media content, or submitting your own draft for review and explanation, teaching me how to revise. Benchmarks default to fast direct output, expand when depth is specified, and invite judgment only when hands-on practice is specified; manuscripts default to explaining problems and editing as authorized. Direct creation, standalone openings or pacing optimization, AI-flavor special topics, pre-publish final checks, published performance reviews, account positioning, and guided learning from materials still use the original entry points.
Use when the user wants proof that finished work meets its acceptance criteria, not just that tests pass: 'verify it is actually done', 'check it against the spec', 'evaluate the run'. Runs mechanical checks, a semantic review per criterion, and multi-model consensus when uncertain. With execution.auto_evolve on (the default), a rejected result with a Seed continues into a Ralph fix loop; pass auto_evolve: false to verify only.
Require fresh verification evidence before claiming work is complete, fixed, passing, committed, PR-ready, or ready for handoff. Use before completion claims, commits, pushes, PR creation, issue status changes, delivery summaries, or agent handoffs; do not use for brainstorming or planning that makes no delivery claim.
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.