Top Agent Skills

樊登（讲书人）认知与表达框架（压缩蒸馏）：拆书三段论、行动号召、温和说服… 触发：樊登读书 等。非替代原著阅读；非心理咨询

Maintain a structured wiki under state/wiki/ — ingest raw sources from state/raw/, synthesize cross-linked pages, and lint for health. Use this skill whenever you need to build durable, graph-shaped knowledge with cross-references (entities with relationships, topics that recur, concepts you trace across many sources).

Use when a high-priority signal needs to reach the operator but doesn't fit the current conversation (off-hours wake, urgent error needing eyes, scheduled-tick discovery worth surfacing now). Routes via MIMIR_OPERATOR_ALERT_CHANNEL.

Review a pull request and POST the review to GitHub via `gh pr review`. Use when asked to review a PR, or when the github-activity poller fires a PR-opened / PR-review-requested event. Always submits after drafting — a review that stays in turn output and never reaches GitHub is a non-review.

The menu of non-grit moves available when you'd otherwise reach for "I'll do better next time." Use when you catch yourself resolving to "be more careful," "remember to X," or "try harder" — those resolutions die at the turn boundary. The right shape is always a structural change with a verifiable diff: edit a memory file, edit a skill that misled you, log a chainlink interest item, add a poller for the missed signal, file a five-whys. The artifact must outlive the turn.

Turn "block until condition X is met" into an agent wake-up via the bash_async tool. Use when you need to wait for a one-shot event without burning context — a webhook arriving, a CI pipeline finishing, a file appearing, a long shell command completing — AND you want this conversation to resume with full context when the event fires. Distinct from pollers (recurring) and the synchronous Bash tool (blocks the turn). The completion event lands as a fresh turn on the spawning channel; no polling needed.

A catalog of pollers worth building — the underused half of being a long-running agent. Use when something you care about could change without anyone telling you (a CI pipeline, a competitor's release, a friend's status, a config drift, a dependency CVE) and you want to be the first to notice. Companion to the `pollers` skill, which covers mechanics. This file is the menu of *what's worth polling.*

Recognize when you're in a runaway loop and stop yourself. Use when the same tool call has repeated 3× with the same args, when the same error class has fired 3× in a turn, when you've been told the same correction twice, when "let me try one more variation" is the third small variation, or when a refinement loop is orbiting rather than converging. The right move on a trip is to switch from action to inquiry — read events.jsonl, list assumptions, look for contradictions, ask the human, file a chainlink — not to retry harder.

Layer alternative channels / scrapers / data sources with explicit fall-through, where each rung covers a different failure mode. Use when interacting with the world (sending a notification, fetching from a third party, detecting a state change, authenticating) and the single canonical path could fail in known ways. Distinct from retrying — retries handle transient failures; fallback chains handle modal ones (channel down, API gone, cookie expired). Three layers tops; the terminal rung is loud.

Run shell commands in the background with output capture and completion callbacks. Use when a command might take more than ~30 seconds (builds, tests, deployments, data processing) and you want to keep working while it runs.

Watch the main branch of one or more GitHub repositories for new CI (GitHub Actions) workflow-run failures — emits a fresh turn the moment a build breaks and stays silent while CI is green. Use when mimir maintains repos whose CI it should react to (e.g. a failing build on main after a merge it landed). Seen-set deduped so each failed run is reported exactly once. Companion to the ``pollers`` framework skill (mechanics) and the ``world-scanning`` skill (catalog of what's worth polling). Opt-in: copy this directory into ``<home>/skills/github-ci-watch/`` then set the env vars below.

Optional low-priority poller that inventories Worklink tool pins from <home>/worklink.yaml and files/reuses Chainlink bump issues when upstream versions drift. Opt-in: copy this directory into <home>/skills/worklink-tool-pins/ and configure tool_pins in worklink.yaml.

Processes a PR's review comments (Copilot or human), classifies them, applies the fixes that belong, replies to each thread, and pushes. Use whenever the user says "address the review", "fix what Copilot said", "handle the comments", mentions Copilot already reviewed a PR, or passes a PR number/URL with pending reviews — or in Spanish "revisá los comentarios", "arreglá lo que dijo Copilot", "atendé el review".

Opens a conversational planning session for a feature, bug, or ticket. Investigates the repo, discusses the approach with the user until a solution is agreed, and only then writes the plan to docs/plans/. Use whenever the user invokes it, describes a problem to solve, pastes a ticket, mentions an incident, or asks to plan a non-trivial change. Also on "plan this", "analyze this first", "what would we need to touch", "let's start with this" — or in Spanish "planeá", "analizá esto antes", "qué habría que tocar", "arranquemos con esto".

Takes an approved plan from docs/plans/ and drives it to an open PR. Implements it by milestones, commits per milestone in the repo's style, and opens the PR against the repo's base branch. Use whenever the user approves a plan, says "ship it", "go", "start", "implement it", "do it", or asks to open a PR for already-planned work — or in Spanish "dale", "arrancá", "implementalo", "hacelo".

Harness Compound

Documentation and capabilities reference for Daily

Track Apple devices/AirTags via FindMy.app on macOS.

Build ultra-fast web APIs and full-stack apps with Hono — runs on Cloudflare Workers, Deno, Bun, Node.js, and any WinterCG-compatible runtime.

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

Use this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks including solving equations algebraically, performing calculus operations (derivatives, integrals, limits), manipulating algebraic expressions, working...

ALWAYS use this skill when committing code changes — never commit directly without it. Creates commits following Sentry conventions with proper conventional commit format and issue references. Trigger on any commit, git commit, save changes, or commit message task.

Video and audio perception, indexing, and editing. Ingest files/URLs/live streams, build visual/spoken indexes, search with timestamps, edit timelines, add overlays/subtitles, generate media, and create real-time alerts.

Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum...

Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens, higher compliance.

Interactive visualization library. Use when you need hover info, zoom, pan, or web-embeddable charts. Best for dashboards, exploratory analysis, and presentations. For static publication figures use matplotlib or scientific-visualization.

Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.

Build content-focused websites with Astro — zero JS by default, islands architecture, multi-framework components, and Markdown/MDX support.

Perform comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates detailed report of issues with severity ratings and recommendations.

Generate walkthrough videos from Stitch projects using Remotion with smooth transitions, zooming, and text overlays

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.

GraphQL gives clients exactly the data they need - no more, no less. One endpoint, typed schema, introspection. But the flexibility that makes it powerful also makes it dangerous. Without proper co...

Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers. Use when: inngest, serverless background job, event-driven wor...

Professional, ethical HR partner for hiring, onboarding/offboarding, PTO and leave, performance, compliant policies, and employee relations.

AI image generation skill powered by Google Gemini, enabling seamless visual content creation for UI placeholders, documentation, and design assets.

Throwaway HTML mockups: 2-3 design variants to compare.

Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly;...

Email infrastructure for AI agents. Create accounts, send/receive emails, manage webhooks, and check karma balance via the AgentMail API.

Manages shadcn/ui components and projects, providing context, documentation, and usage patterns for building modern design systems.

Text-to-speech and speech-to-text using fal.ai audio models

IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware...

Database development and operations workflow covering SQL, NoSQL, database design, migrations, optimization, and data engineering.

Firebase gives you a complete backend in minutes - auth, database, storage, functions, hosting. But the ease of setup hides real complexity. Security rules are your last line of defense, and they'r...

Generate images, video, and audio via diffusion workflows.

Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting...

Modern Angular (v20+) expert with deep knowledge of Signals, Standalone Components, Zoneless applications, SSR/Hydration, and reactive patterns.

Review a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight.

Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean.

Extract and consolidate reusable components, design tokens, and patterns into your design system. Identifies opportunities for systematic reuse and enriches your component library.

Generate favicons from a source image

Tone down overly bold or visually aggressive designs. Reduces intensity while maintaining design quality and impact.

Alias for sentry-skills:pr-writer. Use when users explicitly ask for "create-pr" or reference the legacy skill name. Redirects to the canonical PR writing workflow.

Master of defensive Bash scripting for production automation, CI/CD pipelines, and system utilities. Expert in safe, portable, and testable shell scripts.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

Deliberative consultation with Kimi API. Ask, evaluate, critique, iterate until workable agreement.

Optimize any form that is NOT signup or account registration — including lead capture, contact, demo request, application, survey, quote, and checkout forms.

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

Improve interface performance across loading speed, rendering, animations, images, and bundle size. Makes experiences faster and smoother.

Best practices for Remotion - Video creation in React

2D game development principles. Sprites, tilemaps, physics, camera.