skills-workflows

Orchestrate external agent CLI harnesses (pi, hermes) in turn-by-turn sessions from within Claude Code. Use when the user wants to delegate tasks to pi or hermes, chain multiple agent turns, compare outputs across harnesses, or build multi-agent workflows where Claude acts as the coordinator.

End-to-end publishing pipeline for a new article on shane.logsdon.io. Runs text quality passes (humanize → ms-style-pass), generates brand-system design artifacts (blog hero OG + in-page hero, LinkedIn post image), screenshots them at 1x, wires images into the article frontmatter and site, saves LinkedIn companion text to Obsidian, builds the site, bumps the service worker cache version, and commits + pushes. Unattended — no human checkpoints. Working directory must be the site repo root. Triggers: "publish <slug>", "publish the post", "run the publish pipeline", "/publish-post".

Run the monthly Claude Code skill hygiene pipeline — skill-audit (rank skills by usage + quality) → consolidate-memory (prune stale memories) → vault-lint (catch orphans created by deprecated workflows). Use when the 1st of the month rolls around, when the user says "monthly skill audit", "is my context layer healthy", "skill hygiene check", or after deprecating a workflow / removing a skill. Do NOT use for single-skill review (read the SKILL.md directly) or in the same week as the last audit. Output goes to ~/Downloads + Inbox/.

Run the full weekly vault-health pipeline — vault-lint (consistency check) → backlinks (graph repair) → vault-index (rebuild overview) → weekly-signals (deferral / pattern surface) → weekly-learnings (publishable thread surface). Use when /weekly-review is invoked, on Friday afternoons, when the user says "weekly vault review", "audit my vault", "what should I publish this week", or after a week of heavy capture activity. Skips stages whose preconditions aren't met (e.g. weekly-learnings needs ≥3 daily notes from the week).

Draft a blog post or article and prepare it for publishing — idea → first draft → humanize (remove AI-typical patterns) → ms-style-pass (term + bias + heading conventions). Use when the user says "draft a post about X", "write up this idea as a blog", "prepare a draft on Y", "stage a draft for publishing", or after /learned surfaces a publishable thread. Hands off to publish-post for the heavyweight pipeline (artifact generation + publishing); does NOT publish itself.

Run the full feature-spec pipeline for a new product / feature with commercial stakes — biz-brief (business context) → superpowers:brainstorming (technical spec) → superpowers:writing-plans (implementation plan). Use when the user says "let's build X", "I want to ship Y", "spec out this feature", "go from idea to plan for Z", or when starting any new feature with a user / market / business model. Do NOT use for purely internal tooling (skip biz-brief; go straight to brainstorming) or for bug fixes (use debugging-and-error-recovery instead).

Run the full design pipeline for a brand or one-off artifact — design-plan (strategy) → design-system (tokens + showcase) → an artifact skill (linkedin / blog-hero / etc.) → screenshot-html (PNG export). Use when the user says "design a brand", "I need the full design system + assets", "set up a new brand from scratch", "design pipeline for X", or when starting visual work on a brand that has no DESIGN.md yet. Do NOT use when the brand already exists and you just need one artifact — call the artifact skill directly.

Generate or update an AGENTS.md / CLAUDE.md / context file for a repo. Use when the user says "set up CLAUDE.md", "generate AGENTS.md", "write a context file for this repo", "document this codebase for AI agents", or when a fresh repo has none. Also use when an existing context file has gone stale and needs a rewrite from current source. Do NOT use for editing project-specific README or contributor docs.

Markdown-based task tracking for AI-human collaboration on a project — creates and maintains TASKS.md with status, owner, and decision log. Use when the user says "set up TASKS.md", "track these tasks", "make a checklist for this project", "coordinate work across sessions", "I need a project tracker", or at the start of any multi-task or multi-session project. Replaces the old /work skill (consolidated 2026-05-08).