Run experiments and papers in a PenguinHarness research organization — fix the harness and the metric first, run an autoresearch-style loop (one editable surface, the same time budget per experiment, a results log, keep only improvements) inside a resource envelope the board approved in the all-hands channel, and put every claim through adversarial review by a reviewer who is not its author.
Create a company-mode organization together with the user — collect its id, name, mission, shared workspace, model and CEO budget one question at a time, confirm the whole thing in one summary, then run penguin org create and hand the user over to company mode.
Compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI. Use when building Compose or Jetpack Compose UI, state, navigation, or theming in a KMP project.
Step-by-step agent workflow to configure the OpenAI Codex CLI on any machine (Linux, macOS, Windows) to use OmniRoute as an OpenAI-compatible backend. Detects OS and shell, writes config.toml and 7 named profiles, sets environment variables, and verifies the setup.
[DEPRECATED - use continuous-learning-v2] Legacy v1 stop-hook skill extractor. v2 is a strict superset with instinct-based, project-scoped, hook-reliable learning. Do not invoke v1: when continuous learning, session learning, or pattern extraction is requested, route to continuous-learning-v2 instead.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination. Use when capturing lessons from a session, managing instincts, or promoting them into skills, commands, or agents.
Add one optional external Codex critique after the existing council has produced a decision draft. Use when an ambiguous, high-consequence decision would benefit from a separate model invocation's attempt to break the synthesis. Requires explicit consent before sending the compact draft and disagreement to OpenAI, labels same-provider reviews honestly, and marks the review absent when the adapter is unavailable.
Guide for creating effective skills. Use when creating a new skill or updating an existing one that extends Letta Code's capabilities with specialized knowledge, workflows, or tool integrations, whether a user asks for it or a reusable workflow is worth capturing.
Scaffold and build new tool integrations in tools/. Use when asked to create a new tool, add an API integration, or build a new client for an external service.
Cross-validate documentation and artifacts across the codebase for consistency, conflicts, and contradictions. Use when users ask to "cross-validate", "validate docs", "check documentation consistency", "audit documentation", or find conflicts/contradictions in docs. Supports automatic fixing with "validate and fix" argument. Runs parallel subagents for efficient validation across categories (domain-models, agent-system, tech-stack, architecture, cli-commands). Part of the Shep autonomous SDLC platform — https://shep.bot
C# and .NET testing patterns with xUnit, FluentAssertions, mocking, integration tests, and test organization best practices. Use when writing or reviewing xUnit tests, mocks, or integration tests in a C# / .NET project.
Guides developers through client library installation and authentication setup steps for the Data Manager API. Use this skill when a user is getting started with the Data Manager API and needs to setup their local environment, install the client library, or setup access to the API. Don't use for implementing audience or event ingestion logic (use the data-manager-api-audience-ingestion or data-manager-api-event-ingestion skills instead).
Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Runs on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.
Safe, reversible database migration patterns: forward-only production changes, expand-contract zero-downtime renames, concurrent indexes, batched backfills, and per-tool workflows for PostgreSQL, Prisma, Drizzle, Kysely, Django, and golang-migrate. Use when writing a schema or data migration, adding a column or index to a large table, planning a rollback, or preparing a zero-downtime deploy.
Summarizes data lineage graphs on Google Cloud to help users debug data quality issues and understand data provenance for BigQuery and Cloud Storage. Use when summarizing upstream and downstream data flows, and presenting complex lineage data as an intuitive Markdown report. Don't use for generic BigQuery queries, editing lineage relationships, or downstream deprecation. Don't use for downstream blast-radius impact analysis (use datalineage-bigquery-asset-impact-analysis skill instead).
Produce cited research reports from multiple web sources using firecrawl and exa MCP tools — plan sub-questions, search and deep-read sources, then synthesize findings with inline citations and confidence levels. Use when the user asks to research a topic in depth, run a deep dive or investigation, or do competitive analysis, technology evaluation, market sizing, or due diligence on a company.
Use when a DeerFlow maintainer needs comment-only GitHub issue or PR handling: resolve issue/PR scopes with gh, analyze issues, post or draft issue comments, perform PR review comments, review PR or issue batches, compare competing PRs that target the same issue, give fix strategy, risk classification, and validation guidance. Intended for maintainers and trusted local agents, not general contributors.
Define, review, or update SECURITY.md guidance for a repository or component. Use when the user wants to clarify what Codex Security should review, what is out of scope, which security properties must hold, or whether existing guidance still matches the code.
Stop hook that blocks Claude from finishing until quality checks pass. Detects rationalization patterns (surface text heuristics), stale learning logs (filesystem mtime), and low disk space. Complements self-audit by mechanically enforcing learning capture habits. Use when Claude should be mechanically blocked from declaring work finished before quality checks and learning capture actually pass.
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up CI/CD, containerizing an app, or checking production readiness before a release.
Lay out, review and iterate on a product's screens on a Nuphos Design canvas — pages of live HTML frames, sections, notes and flow arrows that the team edits beside you. Use whenever asked to design screens, mock up a UI, put screens on a canvas, build a user flow, or change a frame on an open design.
Extract design tokens (color / typography / spacing) from imported source code, screenshots, or Figma exports into the canonical token bag token-map consumes.
Provides guidance and instructions on managing remote devices on Developer Device Platform (DDP). Use when reserving remote Android devices, establishing connection tunnels, checking session status, or extending/cancelling leases. Don't use for iOS or local device/hardware inquiries.
Develop AI-powered applications using Genkit in Go. Use when the user asks to build AI features, agents, flows, or tools in Go using Genkit, or when working with Genkit Go code involving generation, prompts, streaming, tool calling, or model providers.