decafclaw
decafclaw contient 21 skills collectées depuis lmorchard, avec une couverture métier par dépôt et des pages de détail sur le site.
Skills dans ce dépôt
Unified knowledge base — shared Obsidian-compatible vault for curated pages, journal entries, and user notes
Daily scheduled brainstorm (also runnable on demand via /blog-ideas) that reviews the week-so-far across ingested activity, the daily journal, and the blog archive, and maintains a living weekly page of blog-post ideas.
Fetch recent Linkding bookmarks, analyze their content in child agents, and record insights to the vault
Fetch recent Mastodon posts and record interesting content to the vault
Fetch recent activity across all me-to-markdown sources (Mastodon, Linkding, GitHub, Spotify, YouTube, Pocket Casts), analyze each source in a child agent, and record insights to the vault
Fetch new items from subscribed RSS/Atom feeds and record interesting content to the vault
Review recent journal entries and conversations, distill insights into vault pages
Vault gardening sweep — merge, link, split, and tidy agent pages
Structured project workflow: brainstorm, spec, plan, execute multi-step tasks
Start, monitor, and stop long-running background processes (servers, watchers, builds). Returns immediately with a job ID you can poll for output.
Delegate any programming or code-related tasks to Claude Code as a specialized subagent. This skill provides a dedicated context for all things code, making it ideal for generating new code, debugging, refactoring, writing tests, or analyzing programming problems. Prefer activating this skill for programming tasks to leverage its specialized context and structured approach, even if the task seems straightforward.
Admin tools for inspecting and restarting connected MCP servers — status, resources, prompts. Does NOT expose tools provided by MCP servers; those appear as mcp__server__tool and are fetched via tool_search.
Compose and deliver a narrative newsletter summarizing autonomous agent activity in the window.
Your primary tool for any web, PDF, or research task. More powerful than web_fetch — prefer this for all research, web reading, and data extraction. Triggers on: 'tell me about,' 'what is,' 'look up,' 'find out,' 'research,' 'summarize this article,' 'read this PDF,' 'check this site,' 'what does this page say,' 'extract data from,' 'find the price on,' 'compare X vs Y,' 'is it true that,' or any URL/link. Handles JavaScript-heavy websites, PDFs, structured data extraction, content transformation, multi-source research with citations, and multi-step browser automation.
How to author a decafclaw skill — where the files go, SKILL.md frontmatter, the tools.py contract, the get_tools(ctx) signature, and validating before load. Activate BEFORE creating or editing a skill under skills/, or when a skill you wrote isn't loading.
On-demand workflow (/blog-develop <idea>) that develops any blog-post idea into a take-or-leave first draft — scout → interview → deep research → draft, with research and drafting run as child agents.
Sync highlights & notes from your Kindle library (read.amazon.com/notebook) into per-book vault pages.
Edit prose for clarity and concision using Strunk's *The Elements of Style* (1918). Use whenever you have a draft — documentation, commit messages, blog posts, replies — that should be tightened before it goes out.
Fetch a URL, workspace file, or attachment and integrate its content into the vault — one primary page plus cross-linked updates to related pages
Structured blameless analysis of what went wrong in this conversation — identifies root causes and proposes minimal, specific fixes
Show agent diagnostic status — process, MCP, heartbeat, tools, embeddings