loganmancuso-scout
@loganmancuso-scout
Public Skills
schema
by loganmancuso-scout
Knowledge base schema reference. Quick-lookup guide for KB file paths, naming conventions, and update triggers. Shows WHERE things live and WHEN to update them. For full file schemas and detailed structure, load /skill:scribe or read the templates in ~/Documents/Notes/templates/. This skill is a path reference, not a workflow executor.
scribe
by loganmancuso-scout
Records architectural decisions, plans, and session findings into the project knowledge base and README files. Load this skill when KB writes are needed — after significant decisions, completed work summaries, discovered gotchas, or when the user says "remember this", "save this", or "update the knowledge base". Does not write to source code.
debug
by loganmancuso-scout
Generic debugging and investigation methodology for any system or codebase — Java apps, K8s clusters, Docker Compose, scripts, APIs, or anything else. Use when something is broken, when investigating why something happened, tracking down a root cause, or figuring out the cause of an alert, error, or unexpected behavior — even if nothing is confirmed "broken" yet. Focuses on evidence gathering, hypothesis testing, fix validation, and knowledge base updates. Load ops skill to execute infrastructure commands. Load knowledge-base for project context.
youtube-transcript
by loganmancuso-scout
Fetch the transcript and title of a YouTube video as JSON. Use when the user provides a YouTube URL and you need the spoken content (captions) for analysis, summarization, quoting, or search.
analyze-sessions
by loganmancuso-scout
Analyze past pi agent sessions stored under ~/.pi/agent/sessions. Use when the user asks about cost (totals, per project, per model, per day), wants to mine prompting patterns from past prompts, view a specific past session, or search across session transcripts.
pdf-reader
by loganmancuso-scout
Read and comprehend PDF files, especially math lecture notes and academic papers. Use when the user asks to read, parse, analyze, or extract content from a PDF file.
caveman
by loganmancuso-scout
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
docs
by loganmancuso-scout
Documentation writing standards and conventions. Covers inline code comments, JSDoc/docstrings, API docs, READMEs, changelogs, and markdown files. Load this skill when writing or updating any documentation — in code or in markdown.