my-ai-workspace

Review all pending changes against repo conventions before committing

Mark files as human-reviewed with specific validation types

Harvest and locally merge changes from a paude container session. Use when pulling agent work from paude, running paude harvest, merging session commits, importing submodule changes from a container, or fixing failed harvest/submodule fetch.

Start a paude container session for fire-and-forget agent work. Use when creating a paude session, delegating a task to paude, running work in an isolated container, setting up a paude worktree, or launching pi/claude/gemini in podman.

Write a task spec file for a paude container agent. Use when delegating work to paude, preparing a paude prompt-file, writing fire-and-forget agent tasks, or scoping submodule work for harvest.

Diagnose a running or stalled paude container session. Use when paude seems stuck, harvest returned empty, checking paude status, debugging 403 proxy blocks, or deciding wait vs harvest vs reset.

Create or update a project BRIEF.md — scaffolds planning structure for work that crosses the 5-file / multi-session threshold

Apply engineering principles to code or design — DRY, KISS, SRP, YAGNI, phased delivery

Surface assumptions collaboratively before proceeding — beginner's mind, invoked depth

Tag and analyze day-based releases in a workspace — create release tags for recent sessions, generate RELEASES.md, and diff between releases to understand what changed

Quick session orientation — state, handoff, focus

YouTube transcript ingestion via fetch-transcript.py (captions to markdown under research/), plus systematic research, citation verification, and evidence-based analysis of articles, docs, and talks. Use when the user pastes youtube.com or youtu.be URLs, asks to save or pull a video transcript, verify claims against sources, evaluate a talk or video, run gather/manifest/analyze pipelines, or build assessments from source material. For transcript-only + library stub routing, youtube-transcript-library is the narrow entry skill; this skill holds the full workflows and scripts.

Linked-Intent Development — scale change discipline to scope (touch/change/restructure)

Comprehensive content audit — link integrity, registry alignment, cross-references, and freshness

Audit repository structure and flag misplaced files or convention violations

Narrow entry skill for YouTube transcript ingestion and library stub creation. Use when the user pastes a youtube.com or youtu.be URL and wants a transcript saved to disk and/or a library entry created. Fetches captions via fetch-transcript.py and walks the 4-step library ingest checklist. For full pipeline work (citation verification, multi-source analysis, batch gathering), hand off to the research-and-analyze skill after the transcript is on disk.

Audit a skill's SKILL.md for AgentSkills compliance — YAML frontmatter, XML structure, progressive disclosure, routing, and content quality. Provides a scored report with specific fixes.

View, add, pick, complete, or review items in the project backlog

Find and fix missing cross-links for a file or all new files from this session

Add, search, or enrich entries in the personal reference library

Execute a PLAN.md file directly without loading planning skill context

Delegate one or more prompts to fresh sub-task contexts with parallel or sequential execution