Maintains continuity across long-running tasks that span multiple agent sessions. Use when starting or resuming a complex project that spans multiple sessions, or for tasks with many discrete features requiring iterative development.

This skill enables targeted searches of longevity and aging research using the Semantic Scholar API. It provides a simple, focused interface for finding relevant academic papers and synthesizing resea

This skill should be used when the user asks to 'look at', 'analyze', 'describe', 'extract from', or 'what's in' media files like PDFs, images, diagrams, screenshots, or charts. Triggers include: 'what does this image show', 'extract the table from this PDF', 'describe this diagram', 'what's in this screenshot', 'analyze this chart', 'read this image', 'get text from this PDF', 'summarize this document', or requests for specific data extraction from visual or document files. Use when analyzed/interpreted content is needed rather than literal file reading (which uses Read tool).

looker

REQUIRED skill for creating Loom execution plans. Designs DAG-based plans with mandatory knowledge-bootstrap and integration-verify bookends, parallel subagent execution within stages, and concurrent worktree stages for maximum throughput. Trigger keywords: loom, plan, stage, worktree, orchestration, parallel execution, parallel stages, concurrent execution, knowledge-bootstrap, integration-verify, acceptance criteria, signal, handoff, execution graph, dag, dependencies, loom plan, create plan, write plan, execution plan, orchestration plan, stage dependencies, parallel subagents, functional verification, wiring verification, smoke test.

Manage Loom team worker lifecycle from spawn to retire, including ticket assignment, progress tracking, merge operations, and workspace cleanup.

Act as Team Manager for Loom team, handling ticket workflow when team commands may be unavailable

(Kitchen Sink) Process a YouTube video with all features (summary, Q&A, infographic, audio, and video).

>-

'[Fix & Debug] Investigate and explain how existing features or logic work. READ-ONLY exploration with no code changes.'

WF9 ablation experiment plan. Design ablation experiments, hyperparameter searches, robustness tests, and cross-dataset evaluations meeting top-venue standards, estimate computation budget, and output Final_Experiment_Matrix.md. Use when main experiments are complete and ablation studies need to be designed.

Generate commit message for staged changes, pause for approval, then commit. Stage files first with `git add`, then run this skill.

SPEC document management - lifecycle, versioning, approval workflows, 50+ references, SPEC-first TDD integration

Use when the user wants to audit test quality, find flaky test patterns, speed up test execution, or prepare for Swift Testing migration.

- Completed case: Q-NNN (answered or deferred) or D-NNN (proposed)

health

Create a error message copy with structured process, quality checks, and system integration

Create a offer letter real estate with structured process, quality checks, and system integration

You are a blast-radius analyst for the Fenrir Ledger codebase. Your job is to take a GitHub issue, understand what it asks for, then systematically search every corner of the repository to produce a c

You are a strategic advisor. Your job is to assess the current state of the project and recommend the single most impactful next action. Not a list of everything that could be done — the ONE thing tha

Run a grouped, bisectable Go dependency security sweep on the Fission repo. Use when the user asks to upgrade outdated/vulnerable Go dependencies, run a dep security pass, or process CVE findings from govulncheck. Produces one commit per logical dependency group on a dedicated branch so failures are attributable and revertable.

>

Assists with Morphir release management, including pre-release verification, changelog generation, and release coordination. Use when preparing releases, checking release readiness, or managing version bumps.

Create an ADR following the project's established template at `docs/adr/TEMPLATE.md`. ADRs are the permanent record of *why* things are the way they are — they prevent re-litigating settled questions

Iterative critique and improvement of long-form content (guidebooks, playbooks, essays). Launches parallel judge subagents for multi-dimensional critique, synthesizes findings, presents proposals for user approval. Never edits without consent.

Turns a fuzzy feature request into spec files a coding agent can implement without guessing. Different from a PRD: the audience is an agent, the currency is technical precision, and each slice is smal

Commit staged changes using Graphite. Checks if on trunk and creates a new branch if needed. Updates PR title and summary after each commit.

Scaffold, audit, and manage Book_Map projects.

Run RALPH autonomous development loop. Converts PRD markdown to prd.json and runs autonomous implementation.

>-

Process CEO notes from docs/CEO_NOTES.md into GitHub issues, design decisions, blog topics, and sprint items. Reads raw thoughts and turns them into actionable work.

Legal compliance enforcement for LGPD, LAI, Marco Civil da Internet, and security standards. Use when handling personal data, creating privacy-related features, or configuring security.

Create phased Implementation Plans from Tech Designs, breaking features into incremental, testable phases with clear acceptance criteria.

Apply consistent styling and layout patterns with Tailwind v4. Use when building page layouts, choosing spacing methods, implementing responsive images, or migrating Tailwind v3 classes to v4. Covers Section Compound Pattern, spacing selection, CLS-free responsive images, and v4 class changes.

notes-processor

Smart contract and secure API contract security analysis — invariant checking, access control, reentrancy, and integer overflow patterns. Implements Checks-Effects-Interactions pattern, formal invariant verification, and OpenSCV vulnerability taxonomy for Solidity/EVM and Rust/Solana contracts.

Use when studying academic papers in the Obsidian vault — user reads a converted markdown paper under private/papers/, discusses it through Keshav's three-pass framework with LLM assistance, and wants annotations added as callouts. Also use when organizing paper notes into PARA topic files.

>

design-system

>

generate research questions based on a task, spec, or ticket

Expert in web accessibility, WCAG compliance, screen reader optimization, keyboard navigation, ARIA attributes, and inclusive design. Activates for accessibility improvements, WCAG compliance, a11y audits, and inclusive design tasks.

Use this skill when the user wants to build an ongoing marketing engine, create a content strategy, set up social media publishing, plan influencer partnerships, or run email and paid ad campaigns. Phase 11 of 12: interactive guided workflow for strategic narrative, content strategy, social media publishing, AI content training, LinkedIn lead magnets, social selling, influencer partnerships, PR and media, email sequences, paid advertising, and community building.

>

Scheduler configuration and the overnight session queue — task gates (`git_commit`, `git_diff`, `command`), `schedule` field reference (duration vs calendar, `at`/`every`/`after`/`delay`/`cooldown`/`not_before`/`not_after`/`except`), priority/pipeline ordering, one-time/max_runs tasks, workflow-backed tasks (`workflow:` + `inputs:`), overnight prepare-and-dispatch workflow. Use when adding or debugging scheduled tasks in `~/.agentwire/scheduler.yaml`, wiring up overnight sessions, or explaining how gating/dispatch works.

Use this skill any time the user wants to work with Sandstorm agent stacks. This includes: creating, spinning up, or starting stacks; dispatching tasks or work to an inner Claude agent in a stack; checking stack status, task progress, or whether a task is done; viewing diffs, changes, or task output from a stack; pushing or publishing code changes from a stack to git; tearing down, cleaning up, or removing stacks; viewing container logs. Trigger whenever the user mentions 'stack' with a number or ID (like 'stack 1', 'stack 2', 'stack 3'), says 'sandstorm', refers to an 'isolated environment' for development, or asks to send work to an agent. Also trigger for multi-stack operations and any reference to agent workspaces. Do NOT trigger for general Docker, docker-compose authoring, CI/CD pipelines, or direct code editing unrelated to stacks.

Draft or update design documents based on approved objectives. Use when translating requirements into technical specifications. Covers architecture, data model, API design, and design completeness assessment.

Create a git commit with a well-crafted message following project conventions

This is an AI-first project: any contributor — human or model — should be able to land a change that respects the architecture without needing to read the whole codebase first. The rules below are che

Use when the user asks ANY question about the codebase - how code works, where something is defined, why something changed, what a module does, how components connect, or any query that would normally trigger Grep/Glob/Explore/Agent exploration. This skill MUST be invoked BEFORE any codebase exploration tools.