prateek
@prateek
Public Skills
agent-skill-management
by prateek
Manage agent-marketplace packages, reviewed APM caches and patches, plugin materialization, and Claude, Codex, Cursor, or pi activation in this dotfiles repo. Use for skill imports or edits, package policy, the console's guarded edits, apply hooks, and related architecture docs.
fork-lifecycle
by prateek
"Sync the forks package group in prateek/dotfiles packages.toml with the live state of the prateek/forks fleet: adopt a fork once it ships a release, or retire one whose upstream PRs have all landed. Reads fleet state via gh api (no clone), edits packages.toml through scripts/packages/fork-lifecycle-entry, validates the reconciler, and opens an ordinary PR. Use when a fork ships its first release, when a fork files a retire self-issue, or when asked to reconcile fork packages. Trigger on 'adopt the X fork', 'retire the X fork in dotfiles', 'sync fork packages', 'a fork filed a retire issue'."
land-changes
by prateek
Land a finished dotfiles branch onto master the way Prateek does it — no PRs, linear history, one commit per change. Use when the user says "land", "ship it", "land this branch", "merge into master", "ff-only merge", or "push to master". Rebases the branch onto the latest master, squashes to one commit, runs the checks for that diff, fast-forward-only merges into the ~/dotfiles checkout, and pushes. Then confirms chezmoi's source is ~/dotfiles and summarizes what a chezmoi apply would change — it does not apply chezmoi unless asked. Not for GitHub PRs (this repo lands locally), creating worktrees (Orca owns those), or landing in other repos.
chezmoi-management
by prateek
Chezmoi workflow skill for Prateek's dotfiles repo. Use for chezmoi apply/diff/verify/merge/edit/re-add/forget/status/managed/unmanaged/data/execute-template/doctor; source-target drift; files under home/.chezmoitemplates/, .chezmoiassets/, .chezmoiscripts/, .chezmoidata/, or .chezmoiexternal.; package, secret, and license data; Brewfile rendering; app plist capture or modify stubs; chezmoi-owned DOTFILES_ gates; 1Password op:// refs; and mapping ~/.foo targets to home/dot_* sources. Do not use for unrelated dotfile edits, pure shell-startup debugging, or test/VM/harness env vars.
deep-research
by prateek
Use when the user needs multi-source research with citation tracking, evidence persistence, and structured report generation. Triggers on "deep research", "comprehensive analysis", "research report", "compare X vs Y", "analyze trends", or "state of the art". Not for simple lookups, debugging, or questions answerable with 1-2 searches.
trycycle
by prateek
Invoke trycycle only when the user requests it by name.
better-writing
by prateek
Rewrite, draft, and review prose so it is clear, specific, human, and fits its context. Use when improving emails, reports, documentation, marketing copy, UI text, or posts that sound generic, AI-written, verbose, salesy, or formulaic. Covers voice calibration, anti-slop audits, and pre-flight checks.
swiftui-expert-skill
by prateek
Use when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state management and @Observable data flow, view composition and invalidation/performance, lists and ForEach identity, environment usage, localization, animations, Liquid Glass adoption, migrating soft-deprecated APIs, or Instruments .trace capture/analysis for hangs, hitches, CPU hotspots, or
swift-patterns
by prateek
Review, refactor, or build SwiftUI features with correct state management, modern API usage, optimal view composition, navigation patterns, performance optimization, and testing best practices.
shortcut
by prateek
Manage Shortcut stories, epics, objectives, iterations, docs, labels, teams, and more using the short CLI — view, search, update, and create items for project management and issue tracking. Use when the user mentions Shortcut, references tickets or tasks in Shortcut, or when you see URLs matching app.shortcut.com/* (use this skill instead of WebFetch).
claude-history-ingest
by prateek
Ingest Claude Code conversation history into the Obsidian wiki. Use this skill when the user wants to mine their past Claude conversations for knowledge, import their ~/.claude folder, extract insights from previous coding sessions, or says things like "process my Claude history", "add my conversations to the wiki", "what have I discussed with Claude before". Also triggers when the user mentions their .claude folder, Claude projects, session data, past conversation logs, local-agent-mode sessions, or audit logs.
code-understand
by prateek
Build a ranked, citation-backed focus map of a codebase — the files and symbols an architecture actually hangs on — using CodeGraph when available and a dependency-free builtin (regex AST extraction + rg cross-file references) otherwise. Use this any time you (the coding agent) need to orient in an unfamiliar or large codebase before making a change: the user says "help me understand this codebase", "what's load-bearing here", "what would break if I change X", "who calls this", "map out this project's architecture", or you're about to touch code you haven't read yet and want to know what matters before scanning everything by hand. This is the same extractor wiki-update Step 3b uses internally — this skill exposes it directly so any agent session can call it on demand, not just during a wiki sync.
codex-history-ingest
by prateek
Ingest Codex CLI conversation history into the Obsidian wiki. Use this skill when the user wants to mine their past Codex sessions for knowledge, import their ~/.codex folder, extract insights from previous coding sessions, or says things like "process my Codex history", "add my Codex conversations to the wiki", or "what have I discussed in Codex before". Also triggers when the user mentions .codex sessions, rollout files, session_index.jsonl, or Codex transcript logs.
copilot-history-ingest
by prateek
Ingest GitHub Copilot CLI session history into an Obsidian wiki as distilled knowledge pages. Use this skill when the user wants to capture their Copilot CLI sessions into a personal wiki — extracting architecture decisions, debug notes, and patterns into searchable Obsidian pages. Triggers on phrases like "ingest my copilot sessions into obsidian", "add my copilot history to my wiki", "pull my copilot session history into the vault", "capture what I've learned from copilot into obsidian", "just the new sessions since last time", or "mine patterns across my copilot sessions". Also triggers when the user mentions session-store.db, ~/.copilot/session-state, or VS Code copilot-chat transcripts in the context of building a wiki or knowledge base. Does NOT trigger for general copilot usage questions, searching sessions, or backing up history.
cross-linker
by prateek
Scan the Obsidian wiki and automatically discover missing cross-references between pages. Use this skill when the user says "link my pages", "find missing links", "cross-reference", "connect my wiki", "add wikilinks", "what pages should be linked", or after any large ingestion to ensure new pages are woven into the existing knowledge graph. Also trigger when the user mentions "orphan pages" in the context of wanting to connect them, or says things like "my wiki feels disconnected" or "pages aren't linked well". This is a write-heavy skill — it actually modifies pages to add links, unlike wiki-lint which just reports issues.
daily-update
by prateek
Run the daily wiki maintenance cycle: check all source freshness, update the index, and regenerate hot.md. Use this skill when the user says "/daily-update", "run the daily update", "update everything", "morning sync", "refresh the wiki index", or when triggered by the launchd cron at 9 AM. Also use to set up or verify the cron + terminal notification infrastructure for the first time ("set up the daily cron", "install the terminal notification", "how do I get the morning reminder?").
graph-colorize
by prateek
Color-code the Obsidian graph view by rewriting .obsidian/graph.json colorGroups. Use this skill when the user says "color my graph", "color code obsidian", "colorize the graph", "color the graph by tag", "color by category", "highlight visibility in graph", "make the graph colorful", "distinguish tags in graph", or wants nodes in Obsidian's graph view tinted by tag, folder, or visibility. Generates a colorGroups array from the vault's actual tags/categories and merges it into the existing graph.json without clobbering other graph settings. Always backs up first.
hermes-history-ingest
by prateek
Ingest Hermes agent history into the Obsidian wiki. Use this skill when the user wants to mine their past Hermes sessions for knowledge, import their ~/.hermes folder, extract insights from previous Hermes conversations, or says things like "process my Hermes history", "add my Hermes memories to the wiki", "ingest ~/.hermes", or "what have I worked on in Hermes". Also triggers when the user mentions Hermes memories, Hermes sessions, ~/.hermes/memories, or Hermes skill logs.
impl-validator
by prateek
Validate whether an implementation matches its stated goal. Use this skill when a skill or agent wants a second opinion on its own output, when the user says "check this implementation", "validate what you did", "is this correct?", "review the output", or "did you do this right?". Also spawned automatically as a subagent by other skills (memory-bridge, daily-update) to self-check their outputs before presenting to the user. Returns a structured pass/warn/fail verdict with specific actionable issues.
llm-wiki
by prateek
The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources → wiki → schema). Also use when discussing knowledge management strategy, wiki structure decisions, or how to organize distilled knowledge. This is the "theory" skill — other skills handle specific operations (ingesting, querying, linting).
memory-bridge
by prateek
Browse and compare wiki knowledge by which AI tool originally produced it. Use this skill when the user says "/memory-bridge", "browse codex memory", "what did codex know about X", "show me claude knowledge", "cross-tool memory", "what does hermes know that claude doesn't", "show me knowledge from <tool>", "compare my AI tool memories", or wants to explore knowledge gaps between tools. Works from any project. Diff mode ("what's different", "unique to codex", "gaps between tools") is the killer feature — it surfaces blind spots between tools that the user may not know exist.
obsidian-layout-adjustment
by prateek
Workflow for working with the user on changing how Obsidian looks using CSS snippets. Use this whenever the user asks to restyle Obsidian, tune a vault's visual layout, adjust tabs, sidebars, note surfaces, properties, backlinks, graph panes, file explorer rows, icons, links, shadows, active states, or CSS snippets. Also use it when the user says a visual CSS change did nothing, still looks wrapped, is not lifted, is unreadable, or needs to be refactored without changing the current appearance.
yojam-config
by prateek
Maintain Prateek's chezmoi-managed Yojam browser-router config. Use for desired mutations, disappearing or disabled rules, schema bumps, new rule UUIDs, or Mac onboarding. Edit the desired fragment, never the live config; installation belongs to chezmoi-management.
benchmark-zsh-startup
by prateek
Benchmark and attribute zsh startup and prompt latency. Use when asked to profile a slow zsh prompt, explain where shell startup time is spent, compare zsh-bench with zprof or xtrace, or decide which zsh plugin, hook, or startup file to optimize first. Also use when the task is to track which zsh features, widgets, completions, or plugin-provided commands are actually being used.
peekaboo-vm-app-audit
by prateek
Drive an LLM-led audit of one or more macOS apps using Peekaboo as eyes-and-hands — verify install, inspect on-disk preferences, launch the app, navigate its UI (windows, menu bar, settings panes), compare what the app's own UI shows against the configured plist, and produce a markdown report with embedded screenshot proof for each step. Works locally on the current Mac, against a remote Mac via SSH, or inside a Tart VM via double-hop SSH. Use whenever the user asks to "verify the install", "prove the settings landed", "screenshot every app", "audit what's running", or after a fresh chezmoi/dotfiles apply on a new machine or VM. The skill installs Peekaboo if missing.