All skills

A team-shared, AI-ready markdown knowledge base of people, companies, meetings, SOPs and decisions that Claude can answer from on your team's behalf.

A six-step framework for mapping supply-chain choke points and screening small-cap names across A-share, Hong Kong and US markets.

Lets Claude drive the ktui terminal kanban tool to manage boards, tasks, and dependencies from the CLI.

A meta-skill that walks through a 6-step process and checklists for designing, writing, and validating Claude Code plugin skills.

A strategy guide for managing Claude Code context and token budgets through four operations: Write, Select, Compress, Isolate.

Read and write GitHub repositories through the REST API and raw URLs when git clone is blocked in sandboxed containers.

Generates a pre-change blast-radius report showing what breaks if you rename, refactor, or delete a symbol or file.

Takes an existing image ad and rebuilds it at every ratio you need — recomposed, not cropped.

Teaches Claude to drive Oxylabs' remote anti-detect Chrome over CDP with Playwright or Puppeteer for scraping bot-protected sites.

Composites your source video with shot-analysis data into a watchable video where the current shot's metadata panel switches in sync with every cut.

Practical rules and ready-made code patterns for algorithmic art on Canvas 2D — particles, flow fields, noise, fractals, L-systems.

Converges a chosen game concept into a single GAME_DESIGN.md covering player promise, core loop, level pacing, feedback, and a playable prototype slice.

Internal skill that keeps Codex session titles updated every turn in the format 'status｜original request｜current progress'.

A reader-first editing ruleset for explanations, status reports, comparisons and docs that preserves facts, conditions and hedges.

Works through the task list of an OpenSpec change one task at a time, updating progress as it goes.

A meta-skill that turns a finished task, log trail, or refined workflow into a validated, reusable skill package.

Turns real run evidence, recurring failures and user feedback into a concrete upgrade plan for an existing skill, applying changes only after explicit approval.

Pre-publish gatekeeper for WeChat公众号 drafts: scans sensitive words, typos and platform rules, then emits an actionable fix list.

Turns Markdown drafts into paste-ready WeChat Official Account HTML with multiple themes, color schemes and side-by-side previews.

An editorial leader's playbook for splitting work between humans and AI: participation boundaries, hybrid workflow patterns, voice preservation, slop prevention, and disclosure policy.