スキルを探す

Compose a categorical news-roundup newsletter from Ahmad's OpenMark saves. Use when Ahmad wants a scannable "what happened in AI / tools / research / discourse" recap rather than a single-thesis essay. Trigger phrases include "roundup", "news roundup", "this week in AI", "weekly news", "what dropped this week", "category recap", "/newsletter-roundup". Output is bucketed by topic with 3–5 items per bucket, short blurbs, source-tagged for at-a-glance scanning.

日本語の概要は準備中です。原文の説明を表示しています。

Compose a short LinkedIn-post-style thread from Ahmad's OpenMark saves. Use when Ahmad wants a tight 200–400 word post he can paste into LinkedIn, X, or a short newsletter slot — NOT a long essay or full digest. Trigger phrases include "thread", "LinkedIn post", "short post", "tweet thread", "quick newsletter", "social post", "/newsletter-thread". Output is one strong hook + 4–7 short paragraphs + ONE link. Optimized for skim-reading on a phone.

日本語の概要は準備中です。原文の説明を表示しています。

Compose a newsletter draft from Ahmad's OpenMark bookmarks. Use whenever Ahmad asks to draft, compose, write, or assemble a newsletter — phrases like "write me a newsletter on X", "make a newsletter about Y", "newsletter draft on Z", "put together a newsletter about W", "compose a newsletter", "draft my newsletter". Also use when Ahmad asks for a weekly write-up, roundup, or curated post. Pulls from OpenMark first, then WebFetches the chosen sources for quote-grade detail. Triggers on "newsletter", "draft a newsletter", "compose", "roundup", "weekly post", "curated post".

日本語の概要は準備中です。原文の説明を表示しています。

Manus-style file-based planning for multi-step work. Keep task_plan.md, findings.md, progress.md in your run workspace so the filesystem is your working memory. Use for any research/build with 5+ tool calls. Adapted for OpenMark sub-agents from Ahmad's planning-with-files v3.0.0.

日本語の概要は準備中です。原文の説明を表示しています。

Scrub English drafts for AI tells before publishing. Use for any English LinkedIn post or newsletter draft right after composition and BEFORE export. Removes em-dash-as-pause, weak hedges, rule-of-three patterns, AI vocabulary, negative parallelisms, and inflated symbolism. Triggers on "polish", "humanize", "make this sound human", "/polisher", or after any English composer output. Leaves Arabic and Hebrew drafts untouched — humanizer-* skills handle those.

日本語の概要は準備中です。原文の説明を表示しています。

Audit a composer output against four hard checks before delivery — cite integrity, voice rules, word count, schema validity. Always invoked after the polisher (English) or humanizer-* (Arabic / Hebrew). Emits a VerificationReport Pydantic object; orchestrator branches on `overall_passed`. Target ≥0.9 score per run. Triggers automatically as the final composer sub-agent; not user-facing.

日本語の概要は準備中です。原文の説明を表示しています。

Produce a weekly digest of what Ahmad saved in OpenMark over a given time window, clustered by topic. Use whenever Ahmad asks "what did I save this week", "what's new in OpenMark", "last week's saves", "this week's bookmarks", "what happened in my feed", "weekly recap", or any temporal summary of saved content. Faster than full newsletter — output is a scannable digest, not a published post. Triggers on "this week", "last week", "what's new", "weekly digest", "recent saves", "recap".

日本語の概要は準備中です。原文の説明を表示しています。

HTML-first persistent planning skill. Generates a single self-contained plan.html with interactive phases, drag-and-drop tickets, sliders, mockups, and embedded JSON state. Survives /clear via session catchup, tamper-protected by SHA-256, mirrors across 17 IDEs, ships 10 templates across Thariq's 9 categories, exports back to Markdown on demand. Use when asked to "plan it", "make me an html plan", "show me the plan", "render the plan", or when starting any multi-step task that needs a navigable artifact instead of a markdown wall.

日本語の概要は準備中です。原文の説明を表示しています。

Remove AI-generated writing patterns from Modern Hebrew (עברית מודרנית) text. Use when editing or reviewing Hebrew text to make it sound naturally human-written.

日本語の概要は準備中です。原文の説明を表示しています。

Remove AI-generated writing patterns from Levantine Arabic (الشامي — Syrian, Lebanese, Palestinian) text. Use when editing or reviewing Levantine dialect text to make it sound authentically human-written.

日本語の概要は準備中です。原文の説明を表示しています。

Remove AI-generated writing patterns from Modern Standard Arabic (MSA/الفصحى) text. Use when editing or reviewing Arabic formal text to make it sound naturally human-written.

日本語の概要は準備中です。原文の説明を表示しています。

Remove AI-generated writing patterns from Egyptian Arabic (عامية مصرية / Masri) text. Use when editing or reviewing Egyptian dialect text to make it sound authentically human-written.

日本語の概要は準備中です。原文の説明を表示しています。

Set up automatic keepalive for Appwrite free-tier projects to prevent them from being paused after 7 days of inactivity. Use when working in a codebase that uses Appwrite, when the developer mentions Appwrite free tier, project pausing, or keeping an Appwrite project alive, or when you detect Appwrite configuration (node-appwrite dependency, APPWRITE_ env vars, Appwrite SDK imports).

日本語の概要は準備中です。原文の説明を表示しています。

Routes memory and retrieval tasks between MemPalace and QMD. Use this skill whenever the user asks WHERE something is in the codebase (route to QMD), WHY something was built a certain way or what was decided (route to MemPalace), or needs BOTH code and historical context (combined). Trigger on phrases like: 'where is X', 'find X in the code', 'search the codebase for X', 'what did we decide about X', 'why does X work this way', 'show me X and why we built it', 'look up X', 'what's in the handoffs about X', 'pull the relevant files for X'. Use proactively whenever a question could benefit from codebase search OR project memory — don't wait for the user to explicitly ask for a search.

日本語の概要は準備中です。原文の説明を表示しています。

Gives coding agents temporal awareness by reading the session transcript the host already writes, so the agent stops guessing about time and stops repeating commands that just failed. Activates whenever an agent reasons about recency, elapsed time, retry windows, deploy cooldowns, memory or file staleness, idle detection, or any "when / how long ago / how long did that take" question. Required for autonomous, parallel, or long-running agents.

日本語の概要は準備中です。原文の説明を表示しています。

Build production-grade AI agents from scratch using patterns inspired by production-grade agentic systems like Claude Code. Covers two audiences — (1) workflow builders who need planner+executor pipelines, human-in-the-loop checkpoints, and multi-agent orchestration, and (2) application embedders who need HTTP/SSE APIs, multi-user session management, and React frontend integration. Use when asked to build an AI agent, create a coding assistant, embed an agent in an app, build an API agent, clone Claude Code, build a CLI agent, design an agent architecture, scaffold an agentic system, or automate a multi-step workflow. Triggers on keywords like agent builder, agent blueprint, coding assistant, CLI agent, agentic tool, claude code clone, agent scaffold, agent architecture, workflow automation, multi-agent, planner executor, SSE streaming, agent API.

日本語の概要は準備中です。原文の説明を表示しています。

Create a GitHub PR with an engineered description that matches the team's established format — numbered problem-fix sections, technical tables, file-by-file breakdowns, commit lists, and verification checklists. Use this skill whenever the user asks to create a PR, ship code, prepare a merge request, write a PR description, or says anything like "ship to boss", "pr perfect", "make a PR", "prepare PR for merge", "create pull request", "engineer the PR", "PR description", or "ready to push". Also trigger when the user has finished a batch of work and says things like "let's wrap this up", "time to merge", "push this to main", or "get this ready for review". The skill handles everything: commit analysis, description generation, branch creation, and PR submission via gh CLI.

日本語の概要は準備中です。原文の説明を表示しています。

The barber for your coding agents' config. Weighs everything every agent on this machine loads (instruction files, memory, MCP servers, hooks, skills, commands, subagents, plugins, leftovers), prices each item in tokens from your own transcripts, and parks the dead weight with a receipt and an undo. Use this skill whenever the user mentions config bloat, a heavy or slow session start, tokens burned before the first word, too many MCP servers, hooks that are slow or fire on every prompt, skills or commands or plugins nobody invokes, cleaning up or auditing CLAUDE.md or AGENTS.md, Codex config, or asks what does my agent actually load, why is my context full before I type, which of these servers can I turn off, or what is this plugin costing me. Use it even when they only say the session feels bloated or startup got slow, and even when they mention /context, /doctor or /skill-doctor.

日本語の概要は準備中です。原文の説明を表示しています。

Undo a haircut trim. Puts back the skills, commands, subagents, MCP servers, hooks, plugins and files that haircut parked into a dated bag, using the receipt it wrote at the time. Use this skill whenever the user says undo the cleanup, undo the haircut, put my config back, restore what was trimmed, I need that MCP server again, that skill is gone and I want it back, roll the trim back, what is in the bag, or which files were moved. Use it also when something stopped working right after a config cleanup and they suspect the cleanup caused it, and whenever they ask how to reverse a config cleanup they regret.

日本語の概要は準備中です。原文の説明を表示しています。