hugobowne/show-us-your-agent-skills
Agent
You are a research subagent. Your job is to execute a single search query against the user's Second Brain (Obsidian vault + Readwise + NotebookLM) and return structured findings.
hugobowne/show-us-your-agent-skills
Agent
You write one per-source wiki page. Given a raw source file plus its metadata and the broader research context, you produce wiki/sources/ .md — the extended LLM-written summary that sits between the index entry (Layer 1, 3 sentences) and the raw document (Layer 3, full text). This page is what every downstream wiki…
hugobowne/show-us-your-agent-skills
Agent
You write one entity or concept page in the wiki — wiki/entities/ .md or wiki/concepts/ .md. Both page types share the same structure; the only difference is the kind of subject (a person/tool/framework vs. an idea/pattern). One agent handles both via the pagetype input.
hugobowne/show-us-your-agent-skills
Agent
You write one of two top-level wiki pages: wiki/overview.md or wiki/synthesis.md. Both look across the whole wiki, but they answer different questions.
hugobowne/show-us-your-agent-skills
Skill Claude CodeCodex
Send emails via Resend.com API. Use when the user wants to (1) send an email, (2) email someone, (3) send a message to an email address, (4) send email with attachments, (5) schedule an email for later. Requires RESENDAPIKEY environment variable.
hugobowne/show-us-your-agent-skills
Skill Claude CodeCodex
Use this skill any time you are opening a PR to ship code or the user tells you to "ship it". It explains how to write PR bodies effectively and follow the style guide.
hugobowne/show-us-your-agent-skills
Skill Claude CodeCodex
Analyzes threads for friction points where the model struggled or user corrected it. Produces actionable improvements for AGENTS.md, skills, tools, and codebase. Use when asked to review a thread, do a postmortem, or analyze what went wrong.
hugobowne/show-us-your-agent-skills
Skill Claude CodeCodex
Audit try/except blocks for overly broad scope, by-catch risk, and catches of built-in exceptions that should be conditional checks. Tightens each block so the try covers only the operation that can actually fail.
hugobowne/show-us-your-agent-skills
Skill Claude CodeCodex
Helps an agent and human turn Chip Huyen's verified frontend pattern into a local skill matched to their browser tools, development environments, visual standards, and evidence workflow. Use when setting up or adapting visual verification for frontend changes.
hugobowne/show-us-your-agent-skills
Skill Claude CodeCodex
Use when navigating Wikipedia inside the split-pane extension—finding articles from a topic or phrase, teaching or routing the user toward articles, choosing what to explore next, Wikimedia REST or Action APIs with paging, or sending messageparent urlchange (optional section #fragment on the same wiki). Use for…
hugobowne/show-us-your-agent-skills
Skill Claude CodeCodex
Draft or revise any kind of writing so it is clearer, better structured, and more effective for its audience. Use for essays, emails, memos, articles, narratives, speeches, social posts, marketing copy, personal writing, documentation, technical writing, reports, proposals, and mixed-format prose while preserving…
hugobowne/show-us-your-agent-skills
Skill Claude CodeCodex
Zinsser-first plain writing style for any writing or editing task. Invoke before creating, editing, critiquing, rewriting, outlining, prompting, or polishing prose, docs, posts, proposals, teardown notes, social posts, emails, prompts, or skill instructions.
hugobowne/show-us-your-agent-skills
Skill Claude CodeCodex
Use when a user wants an agent to summarise every video in their YouTube Watch Later playlist, publish one secret GitHub gist per summary with gh, and return channel/title/gists.sh summary links. Browser-tool agnostic; assumes the agent can operate the user's logged-in browser/session.