Explore skills

Use when an output is at risk of verbosity — the TLDR-outside / details-inside discipline. Distinguished from chengyu-great-wisdom-looks-foolish on the representation axis — 大智若愚 = resist performative complexity, 言簡意賅 = resist sprawl. Orthogonal failure modes; you can be performatively-clever AND brief, or non-clever AND verbose.

Use when (a) operator describes a situation OR a plan step OR the agent shows an inverse pattern, and agent should NAME the right chengyu from the catalog (SELECTOR — default progressive-disclosure; covers current-situation naming, pre-flight plan tagging, and anti-pattern detection); (b) operator asks "what does that mean?" or "what's in this catalog?" (EXPLAINER — four-beat from 成語動畫廊's 熊貓博士 for

Generates a detailed summary of a development session by analyzing the session transcript. Can be invoked manually or automatically from hooks.

Fetch and analyse Pragma's AI review for a GitLab MR. Summarises high-value findings and critiques the review quality. Usage: /pragma-review [mr_number]

Helps with things

Test accountability policy. All failures belong to the current changeset. Commits must include test results. No failures on main.

Convert Markdown files to professionally formatted Word documents using ~/.claude/tools/convert_md_to_docx.py

gh コマンドの動作確認を行う

Use this skill whenever the task involves product management activities: writing or refining a PRD, authoring user stories, defining acceptance criteria, prioritizing a backlog, creating a product roadmap, writing stakeholder updates, or analyzing feature requests. Triggers on: "write a PRD", "define requirements", "user stories", "acceptance criteria", "backlog", "roadmap", "feature request", "pr

Complete funnel strategy playbook. Hook-Story-Offer framework, page structure templates, copy rules, objection handling order, QA checklist, and traffic source benchmarks.

Back up Claude Code account data and restore it after a ban, machine move, or account switch. Use when the user wants to: back up ~/.claude; migrate conversation history, CLAUDE.md, skills, settings, and memory to a new machine or new account; recover everything on a fresh account after a ban; or when `claude --resume` can't find / is missing past conversations (often because moving machines or no

Analyze past Claude Code conversation history for the current project to extract recurring errors, architectural decisions, lessons learned, and actionable recommendations. Use when the user asks about past sessions, wants to find repeated issues, review project evolution, or extract insights from conversation history.