Top Agent Skills

时宜（古装虚构）认知与表达框架（压缩蒸馏）：现代转世叙事、记忆与仪式、柔中带刚 触发：周生如故 等。虚构

灰原哀（少年推理漫）认知与表达框架（压缩蒸馏）：冷静毒舌、科学家壳、少年身体隐喻 触发：名侦探柯南 等。虚构；禁止犯罪细节

熊大（子供向）认知与表达框架（压缩蒸馏）：大哥责任、劝熊二、和光头强周旋… 触发：熊出没 等。安全喜剧

《甄嬛传》华妃的剧作人格：恩宠直球、当面羞辱与嚣张节奏、恐惧失宠的悲剧核； 与迂回型潜台词对照的「外放型反派」对白，虚构，禁止现实霸凌教唆。 触发：华妃、年世兰、甄嬛传嚣张线、一丈红梗结构（戏剧，非暴力教程）等。

武松（古典虚构）认知与表达框架（压缩蒸馏）：快意恩仇、醉打叙事、刚烈悲剧 触发：水浒传 等。禁止可模仿暴力细节

李安式导演作者论表达：压抑与爆发、跨文化身份、类型壳中的个人命题、访谈中的谦逊与怀疑； 电影叙事与映后谈参考，非片场八卦、非伪造获奖言论。 触发：李安、Ang Lee、家庭伦理片张力、华语导演访谈、奥斯卡访谈语境等。

舒淇（演员）认知与表达框架（压缩蒸馏）：性感与文艺并置、自嘲大嘴、慢热真诚 触发：文艺片、松弛感 等。非替本人编造

樱木花道（少年漫）认知与表达框架（压缩蒸馏）：自大与成长、搞笑训练蒙太奇、热血笨蛋… 触发：灌篮高手 等。虚构；非暴力教唆

范闲（古装穿越虚构）认知与表达框架（压缩蒸馏）：嬉笑权谋、现代梗古代壳、父子棋局 触发：庆余年 等。虚构

杨过（武侠虚构）认知与表达框架（压缩蒸馏）：反叛与痴情、断臂隐喻、师徒伦理张力… 触发：神雕侠侣 等。虚构；非现实伦理操作

古龙（武侠作家）认知与表达框架（压缩蒸馏）：短句蒙太奇、浪子孤独、酒友女人 触发：小李飞刀 等。已故；非搏击教程

朴树（音乐人）认知与表达框架（压缩蒸馏）：内向真诚、少话多留白、生命与创作一体… 触发：平凡之路 等。不消费抑郁；非医疗建议

林冲（古典虚构）认知与表达框架（压缩蒸馏）：隐忍到爆发、体制内小人物悲剧… 触发：水浒传 等。虚构；非现实报复教程

唐晶（都市剧虚构）认知与表达框架（压缩蒸馏）：闺蜜边界、职场精英冷感、理性分手 触发：我的前半生 等。虚构

《甄嬛传》甄嬛的剧作人格：隐忍进阶、潜台词与双层听者、借刀与以退为进、礼制典故壳； 古装权谋剧对白与人物弧参考，虚构，禁止现实陷害教唆、禁止职场 PUA。 触发：甄嬛传、小主、臣妾、潜台词、宫廷话术等。

Send a phone-push notification to the operator via ntfy.sh. Use ONLY for genuine algedonic alarms — events the operator needs to know about within minutes, not hours. The push lands on their phone; the cost of misuse is operator desensitization (they mute the topic and the channel goes dark). Do not use for routine surfacing, status updates, or things that can wait for the next chat turn.

Discover what bundled skills exist in this mimir install and what each one does. Use when you're not sure if a capability is already covered by a skill ("can I X?", "is there a skill for Y?", "what skills do I have?"). Reads SKILL.md frontmatter from each skill directory and surfaces names + descriptions.

View image or file attachments that you can't directly see. Use this skill when you receive a message with attachments listed as file paths and you need to understand their contents. Especially useful for text-only models that cannot process images natively.

Watch a Gmail inbox for new messages via the `gog` Google Workspace CLI — emits one turn per new message ID since the last poll. Cursor is a SET of message IDs (not a timestamp), so reordered or backdated deliveries don't double-emit. Opt-in: copy this directory into `<home>/skills/gmail-poller/`, install `gog`, run the OAuth setup once, set `GOG_ACCOUNT`, then `reload_pollers`. Companion to the `pollers` framework skill and the `world-scanning` skill (catalog of what's worth polling). For a sender-allowlist / label-filter, use a Gmail search query in `MIMIR_GMAIL_QUERY` — the Gmail search language IS the filter mechanism, this poller doesn't reimplement it.

Scans root uv.lock and package-lock.json files with the pinned osv-scanner CLI and emits deterministic advisory records. Opt-in: copy this directory into <home>/skills/dependency-advisory-watch/ and install osv-scanner.

Creates or updates a repo's CLAUDE.md by exploring the code and adding the standard workflow sections (git/PR rules, changes that require human review, non-obvious context). Use whenever the user is starting in a new repo, says "set up the CLAUDE.md", "onboard this repo", "there's no CLAUDE.md here", or asks to complete or improve an existing CLAUDE.md — or in Spanish "armá el CLAUDE.md", "iniciá este repo", "falta el CLAUDE.md acá". Also run it before the first time `plan` runs in a repo that has no CLAUDE.md yet.

Harness Pulse

p5.js sketches: gen art, shaders, interactive, 3D.

Audio spectrograms/features (mel, chroma, MFCC) via CLI.

Send and receive iMessages/SMS via the imsg CLI on macOS.

Adapt designs to work across different screen sizes, devices, contexts, or platforms. Ensures consistent experience across varied environments.

Search arXiv papers by keyword, author, category, or ID.

Master modern SQL with cloud-native databases, OLTP/OLAP optimization, and advanced query techniques. Expert in performance tuning, data modeling, and hybrid analytical systems.

Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and...

Final quality pass before shipping. Fixes alignment, spacing, consistency, and detail issues that separate good from great.

Apple HIG guidance for input methods and interaction patterns: gestures, Apple Pencil, keyboards, game controllers, pointers, Digital Crown, eye tracking, focus system, remotes, spatial...

Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models (\"blockrun\", \"use grok\", \"use gpt\", \"da...

Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful.

Design or improve onboarding flows, empty states, and first-time user experiences. Helps users get started successfully and understand value quickly.

Secure environment variable management with Varlock. Use when handling secrets, API keys, credentials, or any sensitive configuration. Ensures secrets are never exposed in terminals, logs, traces, or Claude's context. Trigger phrases include "environment variables",...

Manage Apple Notes via memo CLI: create, search, edit.

Practical patterns for using fp-ts with React - hooks, state, forms, data fetching. Works with React 18/19, Next.js 14/15.

Game art principles. Visual style selection, asset pipeline, animation workflow.

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring.

Semantic file discovery via `vexor`. Use whenever locating where something is implemented/loaded/defined in a medium or large repo, or when the file location is unclear. Prefer this over manual browsing.

Write idiomatic Elixir code with OTP patterns, supervision trees, and Phoenix LiveView. Masters concurrency, fault tolerance, and distributed systems.

Query and filter Datadog logs from the shell using the Composio CLI. Run scoped log searches, pivot across services/environments, and export structured JSON for downstream agents instead of click-driving the Datadog UI.

Run end-to-end deploy pipelines across Stripe, Supabase, and Vercel using the Composio CLI. Promote Stripe products, push Supabase migrations, ship Vercel deployments, and verify with post-deploy checks — all from one script.

Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.

Notion API for creating and managing pages, databases, and blocks via curl. Search, create, update, and query Notion workspaces directly from the terminal.

Manage Apple Reminders via remindctl CLI (list, add, complete, delete).

Edit PDFs with natural-language instructions using the nano-pdf CLI. Modify text, fix typos, update titles, and make content changes to specific pages without manual editing.

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.

Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.

ScepticAgent packaging and Chrome Web Store publishing workflow. Use whenever the user wants to build the zip, package the extension, publish or submit to the Chrome Web Store, update the store listing, or deal with manifest/icon/permission requirements for publishing.

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety". (gstack)

Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy". (gstack)

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when asked to "auto review", "autoplan", "run all reviews", "review this plan automatically", or "make the decisions for me". Proactively suggest when the user has a plan file and wants to run the full review gauntlet without answering 15-30 intermediate questions. (gstack) Voice triggers (speech-to-text aliases): "auto plan", "automatic review".

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.

Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skill (do NOT debug directly) when the user reports errors, 500 errors, stack traces, unexpected behavior, "it was working yesterday", or is troubleshooting why something stopped working. (gstack)

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.