A playbook for curating what your coding agent sees, when it sees it, and how it's structured — to keep output quality high.
An OWASP-driven security review skill that hardens user input, auth, dependencies, and LLM features with concrete code patterns.
A meta-skill that answers one Buddhist question from the perspectives of 2–3 masters across traditions, using a fixed, citation-bound comparison protocol.
A meta-skill that builds stage-by-stage Buddhist study roadmaps keyed on tradition (Chan, Pure Land, Tiantai, Yogācāra, Madhyamaka, Theravāda…) and your current level L0–L3.
Collects every open Renovate pull request from a GitHub repo and applies their diffs to your local working tree so the combined dependency upgrade can be built and tested at once.
Wires JSpecify, NullAway/ErrorProne and @NullMarked into a Java project so null bugs fail the build.
Generates AI teaching personas of historical Buddhist masters, grounded in canonical sources with an enforced citation contract.
Turns a plain-English project description into a progen CLI config and scaffolds a full production-ready Spring Boot project.
A rule-based UI polish reviewer that checks concentric radii, optical alignment, elevation, and motion against exact values and reports findings by severity.
Searches, compares and validates real emission factors from Carbonstop's CCDB database for product carbon footprints, LCA and corporate GHG accounting.
Lets Claude drive the InsForge CLI to provision projects, run migrations, write RLS, manage storage, functions, deployments and payments.
A symptom-driven playbook for diagnosing InsForge backend issues using logs, metrics, DB health, RLS policies, and the advisor.
A CLI skill that diagnoses and cleans punctuation, spacing, and layout in Chinese Word documents (.docx/.doc/.wps) using preset formatting standards.
Lets you read and write BMP Private-Use-Area Nerd Font icons that Claude Code filters, via placeholder syntax and lookup scripts.
Scans Bilibili's AI videos daily, clusters trending topics, and produces an HTML digest plus a multi-engine, cross-verified intelligence report.
Turns a short-drama script into reusable character, location, and prop definitions plus per-episode state changes in a single visual-setup document.
Writes and revises copy-ready image prompts for short-drama characters, looks, locations, props and state variants in a standardized Markdown sheet.
Turns evaluated code-review findings into verified code edits, escalating ambiguous or behavior-changing ones back to you.
Compresses Japanese memory files (CLAUDE.md, todos, configs) into terse "caveman" style to cut input tokens while keeping code and structure intact.
A shared conventions skill that keeps CHANGELOG.md consistent with Keep a Changelog and SemVer — structure, entry wording, and PR/issue links.