recall

1

Search past Claude Code, Codex, and Grok sessions. Triggers: /recall, "search old conversations", "find a past session", "recall a previous conversation", "search session history", "what did we discuss", "remember when we"

scrape-sdk

3

Return the real page as markdown (not a summary). Use scrape() / scrape_url when you need the full body, failover, crawl, map, or extract. Host WebFetch often summarizes. Prefer host WebSearch for ordinary lookup.

watercolor-design

1

Create or revise websites, interfaces, illustrations, and scroll-driven art in a tactile watercolor and pencil style. Use when a request mentions watercolor, hand-painted UI, paper texture, pigment bleed, botanical illustration, sketch lines, pencil lettering, poetic portfolios, organic growth animation, or asks to soften digital-looking solid fills and rigid geometry.

flutter-control-and-screenshot

59

Guide on how to control a Flutter app using flutter_driver via MCP and capture screenshots.

ljg-plain

7160

Cognitive atom: Plain (白). Rewrites any content so a smart 12-year-old groks it. Structure-free — form follows content. Use when user says '白话说', '说人话', '解释一下', 'plain', 'grok'.

fpl-companion

Read-only Fantasy Premier League companion. Binds a public FPL entry ID, tracks live Gameweek deadlines, monitors player availability and fixture news, and delivers graded, low-noise reminders and lineup/captaincy/transfer recommendations. Never asks for FPL passwords, cookies, or session tokens. Use when the user mentions FPL, Fantasy Premier League, gameweek deadlines, captain picks, transfers, chips, price changes, or mini-leagues.

animate-expo

32457

Build animations in React Native and Expo, making the decisions in the order that determines whether they feel right — should it animate, which thread it runs on, which properties, spring or timing, how the gesture hands off, how it degrades. Writes the implementation with Reanimated, Gesture Handler, Expo Router and expo-haptics. Use when animating anything in an Expo app, adding gestures, sheets, screen transitions, press feedback or haptics, or fixing motion that stutters on device. For web animation use `animate`.

japanese-corporate-pptx

13

Create or edit information-dense, componentized, and fully editable Japanese corporate PowerPoint decks (.pptx) and one-page ポンチ絵 in the style of Japanese manufacturers, industry associations, ministries, technical committees, and large-enterprise internal briefings. Use for JEITA風, 経産省風, 霞ヶ関ポンチ, 曼荼羅資料, 事業スキーム, 技術ロードマップ, 全体像, レイヤー図, 関係者図, 業務フロー, 稟議資料, 講演資料, コンポーネント化, or when the user asks for “日本のトラディショナルなPPT”, “さっきみたいなポンチ”, “大企業っぽい資料”, “情報量のある一枚図”, “画像ではなく編集できる部品”, or a slide that combines diagrams, photos, charts, annotations, assumptions, and sources.

landing-page-design

1373

Complete system for building high converting landing pages: intake questions, page structure, layout selection, conversion copywriting, SEO, plus strict visual rules for typography, spacing, corner radius, backgrounds, hero layout, icons, and motion. Use this skill whenever building, editing, styling, reviewing, or writing copy for ANY landing page, marketing site, web UI, page section, component, or prototype, even when the user does not mention design, conversion, tokens, or a design system. Always consult it before choosing page sections, headlines, CTAs, fonts, font sizes, spacing values, border radii, background colors, icons, or transitions.

agent-orchestration

Delegates non-trivial engineering work to Pi `explorer` (investigation, research) and Pi `fixer` (implementation) in a Herdr session, while the current top-level agent keeps strategy and review. Use when a root cause is unclear, code or architecture is unfamiliar, an external API, SDK, or specification needs research, or an implementation spans several files — even when the user never mentions agents, delegation, or orchestration. Do not use when the current agent was itself delegated work as an `explorer` or `fixer`. Requires HERDR_ENV=1. Handle trivial, local, low-risk work directly.

calibrate-how-we-work

7

Run an explicit, evidence-seeking calibration interview to learn the user's durable collaboration, communication, learning, decision-making, and problem-solving preferences, then propose an "About me / How I think" section for AGENTS.md. Use only when the user explicitly invokes /calibrate-how-we-work or directly asks to run this calibration interview, build their collaboration profile, or update how the agent should work with them. Never auto-invoke from ordinary conversation, onboarding, project planning, isolated preference statements, or a request to personalize one response.

orchestrate

Coordinate parallel agents for substantial work with separable ownership; skip trivial or tightly coupled tasks.

triage

1387

Triage an incoming GitHub, Jira, Linear, or other issue-tracker issue against the current codebase and related issues, then return a structured decision with exactly one triage state. Use whenever the user asks to triage, classify, assess, prioritize, or label an issue for implementation readiness, especially when an issue URL, key, or number is supplied in the prompt.

i-have-adhd

24220

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

clean-room

44

Get an independent decision from a fresh agent that receives a neutral brief and none of the current conversation.

grill-me

A relentless interview to sharpen a plan, run through a Markdown file the user edits.

hitl

2

Use when resuming agent work after the user has hand-edited the codebase (human-in-the-loop commits) and the rest of the branch needs to be stitched around those frozen edits

list-open-work

173

List my open MRs/PRs in the current repo/worktree, each with its tracker ticket. Use when I invoke /list-open-work, or ask what I have open, what's in review, or for a standup list of my open MRs or PRs.

dsh-code-review

173579

Use when reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality gates) and the review-specific checks that code alone can't show

free-disk-space

163

Reclaim disk space on macOS by auditing and clearing build artifacts, package-manager caches, stale git worktrees, and offloading large media to an external drive. Use whenever the user complains about low storage, a full disk, "out of space" errors, or asks to clean up, offload, or free up their machine — even if they don't name specific folders.