Utilities

Searches Claude Code (and Codex) session history across every config home and registered archive, and recovers deleted files byte-for-byte from file-history snapshots.

An output-style skill that compresses answers into short numbered steps with visible progress and one clear next action.

A meta-skill that scores SKILL.md files on a 9-dimension rubric and improves them through an edit → test → human-approval → keep-or-revert loop backed by git.

Inventories recent local Claude Code and Codex conversations for a workspace with a single read-only command.

Installs, switches, and debugs the Claude Code statusline with one script, two layouts, and a four-layer self-verification health check.

Safely analyzes macOS disk usage and produces a cleanup report that explains the real cost of deleting each item.

Extracts every Mermaid diagram from a markdown file and renders them as high-resolution PNG images.

Turns vague requests into precise, testable prompt specifications using EARS syntax and domain theory grounding.

Exports the complete transcript of any claude.ai chat or share link — tool calls, attachments and all — into local Markdown with a lossless-render guarantee.

A conversation-style skill that forces Claude into terse, zero-warmth answers with the conclusion on line one.

Runs a new business, product, or side-project idea through a 9-dimension serial-founder filter and outputs a Build / Sleep on it / Pass viability brief.

Triages the 37signals decision questions down to the 6–8 that matter, forces a clear call, and archives the rationale with a revisit date.

A multi-pass research workflow that plans sources, cross-checks them, and outputs a cited brief with contradictions and gaps — then archives every run for later grepping.

A safety net that preserves your task state and key files across Claude Code context compaction cycles.

Teaches Claude when to stop guessing and ask a well-structured clarifying question instead.

Recommends which AI agent skill to install using nine daily-refreshed Top-100 ranking CSVs.

Stops in-progress work at a safe boundary, emits a precise continuation checkpoint, and picks it back up exactly when you say "continue".

Turns a trade plan (entry, stop, target) into an exact whole-share bracket order that fits your budget and your max loss per trade.

Watches your tickers and rings once when a target, stop, percent move, or the NYSE opening bell hits.

Prepares an Indian resident individual's ITR for FY 2025-26 (or advance-tax plan for FY 2026-27) with every rupee computed by a tested Python engine, leaving pay/submit/e-verify to you.