Gate 7 - Document final decision, rationale, and commit to artifact

Gate 3 - Web search, document analysis, reference class, gather evidence

Use when invalid data causes failures deep in execution - validates at every layer data passes through to make bugs structurally impossible rather than temporarily fixed

Scan project dependencies for known vulnerabilities and CVEs

Backup dev environment to S3

This skill should be used when the user asks to "set up a project", "initialize a new app", "create a new project", "bootstrap a project", "set up my dev environment", or wants to start a new personal web application. Also use when the user says "init project", "new project", or wants to complement an existing project with missing tooling and configuration.

Monitor blood glucose via Dexcom G7/G6 CGM

Open the diffity diff viewer in the browser to see your changes

Open the diffity file tree browser to browse and comment on repository files

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Generate or update project documentation based on recent changes

Static site generators, documentation platforms, and deployment workflows for technical documentation

This skill should be used when working with Verify snapshot tests in .NET projects. Use when updating verified snapshots after intentional code changes, accepting new snapshots, discovering verify tests, or troubleshooting snapshot mismatches. Trigger phrases include "verify tests", "update snapshots", "accept snapshots", "verified files", ".verified.txt".

Example skill loaded from resources_discover

Control Eight Sleep pods (status, temperature, alarms, schedules).

Control Eight Sleep pods (status, temperature, alarms, schedules).

Control Eight Sleep pods (status, temperature, alarms, schedules).

Query Elasticsearch — search, index management, aggregations, and cluster health.

Best practices for Laravel Eloquent ORM including query optimization, relationship management, and avoiding common pitfalls like N+1 queries.

Embedded systems firmware, microcontrollers (ESP32, STM32, Arduino, Raspberry Pi), RTOS (FreeRTOS, Zephyr), IoT protocols (MQTT, CoAP, BLE), bare-metal C/C++, and hardware peripheral interfaces (I2C, SPI, UART, GPIO). Use when developing firmware, working with microcontrollers, or building IoT devices.

TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.

Bubbletea/Lipgloss quality rules for Engram TUI. Trigger: Changes in model, update, view, navigation, or rendering.

Creates consistent error handling with custom error classes, HTTP status mapping, structured logging, safe client messages, and error taxonomy. Use when standardizing "error handling", "logging", "error responses", or "exception management".

Estimate implementation complexity for features and technical tasks

Distill repeated work into Eve skillpacks by creating or updating skills with concise instructions and references. Use when a workflow repeats or knowledge should be shared across agents.

Use when determining how far to push motion beyond realism, calibrating animation intensity for context, or making key moments register with audiences.

Show federation health — peers, sessions, trust levels, and message metrics

Catch up on your RSS feed — highlights up top, full browse below

Customize your social feed preferences and neurochemical optimization weights

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Show spec dependency graph and execution order. Use when asking 'what's blocking what', 'execution order', 'dependency graph', 'what order should specs run', 'critical path', 'which specs can run in parallel'.

Show all available Product Forge agents, skills, and commands

Run Marty Cagan's Four Risks assessment on an issue (value, usability, feasibility, viability). Use when evaluating features before building.

Generate candlestick price charts for any asset from existing OHLC data, without handling data fetching.

Use when searching GitHub via CLI for issues, PRs, repos, code, or commits - provides correct syntax for exclusions, qualifiers, quoting, and platform-specific handling to avoid command failures

MANDATORY: Use instead of `git rebase` - provides automatic backup and conflict recovery

GitHub CLI - manage repositories, issues, pull requests, actions, releases, and more from the command line.

Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?", "Trace this bug"

Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "How does X work?", "What calls this function?", "Show me the auth flow"

Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?", "What depends on this?", "What will break?"

Detect drift between git manifests and what's deployed in clusters

Sync manifests from a git repository to clusters

Use when determining which accessibility law applies to an organization, comparing requirements across jurisdictions (US, EU, Canada, Japan), or planning multi-country accessibility compliance strategy.

Install and verify the Go toolchain on macOS, Linux, and Windows. Use when Go is required but not present, or when a specific Go version must be installed. Prefer system package managers (homebrew, apt, etc.) and fall back to official Go downloads when needed.

A very complex description that spans multiple lines and contains weird chars: !@#$%^&*()

Build, sign, and package Android apps with Gradle before uploading to Google Play. Use when asked to create an APK or AAB, configure signing, or set up build pipelines.

Configure ignore patterns in GrepAI. Use this skill when excluding files and directories from indexing.

Get started with GrepAI in 5 minutes. Use this skill for a complete walkthrough from installation to first search.

Configure GOB local file storage for GrepAI. Use this skill for simple, single-machine setups.

Queries Polymarket market data and CLOB state, and manages CLOB orders via the Grimoire venue CLI wrapper backed by the official Polymarket CLI.

Add phase to end of current milestone in roadmap

Generate tests for a completed phase based on UAT criteria and implementation

Execute all plans in a phase with wave-based parallelization

Diagnose planning directory health and optionally repair issues

Insert urgent work as decimal phase (e.g., 72.1) between existing phases

Surface Claude s assumptions about a phase approach before planning

Initialize a new project with deep context gathering and PROJECT.md

Create context handoff when pausing work mid-phase

Check project progress, show context, and route to next action (execute or plan)

Remove a future phase from roadmap and renumber subsequent phases

Resume work from previous session with full context restoration

Switch model profile for GSD agents (quality balanced budget)

Configure GSD workflow toggles and model profile

Update GSD to latest version with changelog display

Validate built features through conversational UAT

Create a go-to-market strategy covering marketing channels, messaging, success metrics, and launch timeline. Use when planning a product launch, creating a GTM plan from scratch, or defining a launch strategy for a new market.

Save session state to .rulebook/handoff/_pending.md for cross-session continuity

Search helix memory by meaning. Returns relevant insights ranked by relevance × causal effectiveness.

Show Inference Confidenz help and documentation

Display help for the session management system

Use for German statutory accounting, bookkeeping, month-end or year-end close, journal entries, provisions, accruals, depreciation, balance sheets, or profit and loss statements under HGB. Trigger on terms like Buchung, Buchungssatz, Rueckstellung, Abschluss, Jahresabschluss, Bilanz, GuV, AfA, Rechnungsabgrenzung, and on German legal forms like GmbH, UG, AG, KG, OHG, e.K.

Hopper debugging: macOS/iOS binaries, ObjC/Swift symbols, dyld, LLDB.

Use when searching for or transforming code patterns structurally - provides ast-grep CLI syntax, metavariable patterns, and language-specific examples for precise AST-based code search and rewriting

Use when designing AI features and the real opportunity may be perception support, not delegated conversational work.

Use when the user asks to brainstorm features, expand a project, or "what should I build next" / "give me ideas for X" / "how could we extend Y". Memory-aware — pulls prior decisions and avoids re-suggesting rejected ideas.

Asynchronous job processing with named queues, retries, FIFO ordering, and dead-letter support, plus durable topic pub/sub. Reach for it when every consumer must reliably process every message.

Executes update of theme to the next Gesso 5 release

iMessage/SMS CLI for listing chats, history, watch, and sending.

iMessage/SMS CLI for listing chats, history, watch, and sending.

Creates step-by-step incident response runbooks for common outages with actions, owners, rollback procedures, and communication templates. Use for "incident runbook", "outage response", "incident management", or "on-call procedures".

Display an overview of the Potenlab plugin ecosystem. Use for "info", "ecosystem", "about potenlab".

Initialize a new repository with AGENTS.md

Initialize project context document for faster AL development workflows. One-time setup that reduces workflow runtime by 40-60%.

Detect and classify telemetry anomalies on Cognitum Seed devices

Orchestrate firmware rollouts with canary deployment and anomaly-gated advancement

Create and manage Cognitum Seed device fleets with firmware policies

Verify witness chain integrity and detect provenance gaps

Updates GitHub issues with planning info, status changes, and progress, ensuring proper tagging and documentation throughout development.

Pattern for progressively refining context retrieval to solve the subagent context problem

Pattern for progressively refining context retrieval to solve the subagent context problem