Skill Claude CodeCodex
An implementation-plan guide for turning a written requirement into small, testable coding tasks. It records the files, changes, tests, and documentation an engineer needs.
Skill Claude CodeCodex
An implementation-plan guide for turning a written requirement into small, testable coding tasks. It records the files, changes, tests, and documentation an engineer needs.
Skill Claude CodeCodex
A guide for creating and testing reusable instructions for AI agents, called skills. It applies test-driven development, or TDD—the practice of writing tests before implementation—to instruction documents.
jnMetaCode/agency-orchestrator
Instructions file
Instructions for jnMetaCode/agency-orchestrator, covering agency orchestrator — project context, key commands, community templates (remote manifest), release pipeline (all automatic) and skills (methodology playbooks).
jnMetaCode/agency-orchestrator
Skill Claude CodeCodex
A five-part method for writing prompts for AI-generated videos, such as Sora or Seedance. It organizes each prompt into the subject, setting, visual style, camera movement, and timed shots with sound.
jnMetaCode/agency-orchestrator
Cursor rule
Triggered when user asks to run a YAML workflow or multi-role collaboration.
jnMetaCode/agency-orchestrator
Skill Claude CodeCodex
A workflow engine that reads YAML files and runs tasks assigned to different named roles. YAML is a text format for describing structured settings and steps.
Skill Claude CodeCodex
Draft user-facing release notes from a git log range. Trigger when the user asks for "release notes", "changelog entry", or "what shipped this week" with a git ref range. Output is markdown sections grouped by Features / Fixes / Breaking with PR links.
jnMetaCode/ai-shortfilm-prompts
Plugin Claude Code
A plugin containing a method for writing prompts for AI-generated short films, including a five-part structure and subject-specific templates.
jnMetaCode/ai-shortfilm-prompts
Plugin Claude Code
A collection of five-part methods and reusable templates for writing cinematic prompts for AI video generation. It covers 21 subject areas and lists compatibility with tools such as Seedance, Kling, Sora, Veo, Jimeng, and Runway.
jnMetaCode/ai-shortfilm-prompts
Instructions file
Instructions for jnMetaCode/ai-shortfilm-prompts, covering claude.md, what this repo is, hard conventions, licensing boundary (don't blur it) and do not commit.
jnMetaCode/ai-shortfilm-prompts
Skill Claude CodeCodex
Generate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using the 5-stage structure from Mx-Shell's Zombie Scavenger. Trigger when the user wants transformation sequences, multi-shot narrative shorts, weapon-charge/combat segments, emotional family/pet/farewell…
Skill Claude CodeCodex
OpenClaw 安全部署指南 / Security deployment guide — help users secure their OpenClaw installation.
MCP server Claude CodeCodexCursor +2
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP. Runs locally from the shellward npm package. Needs 3 environment variables to run.
jnMetaCode/local-agent-toolkit
Plugin Claude Code
Plugin marketplace listing 1 plugin: local-agent-toolkit.
jnMetaCode/local-agent-toolkit
Plugin Claude Code
Local-first memory, skills and tracing for your agent: engram (recall/remember your notes via MCP), skillet (search/install agent skills via MCP), plus skills that teach the agent to use them — nothing leaves your machine.
jnMetaCode/local-agent-toolkit
Skill Claude CodeCodex
Capture decisions and facts as durable notes; use when the user makes a decision worth remembering.
jnMetaCode/local-agent-toolkit
Skill Claude CodeCodex
Give the agent durable, local memory with engram — recall past decisions before answering, and persist new decisions, preferences and facts as they happen. Use when work spans sessions or the user says "remember".
jnMetaCode/local-agent-toolkit
Skill Claude CodeCodex
Instrument an AI agent or LLM app with OpenTelemetry and watch its runs live in tracelet (local DevTools). Use when asked to add tracing/observability to an agent, or to debug what an agent actually did.
MCP server Claude CodeCodexCursor
Your local, private memory layer. Index your notes and files, then recall anything with citations and temporal reasoning — 100% on your machine. Runs locally from the @jnmetacode/engram npm package.
Skill Claude CodeCodex
A tiny example skill that greets the user — use it to verify skillet installs work.
Skill Claude CodeCodex
Generate or update a CHANGELOG.md in Keep a Changelog format from real git history. Use when cutting a release, tagging a version, or asked "what changed since…".
Skill Claude CodeCodex
Write precise Conventional Commits messages from the actual staged diff. Use whenever committing code or asked to write/fix a commit message.
Skill Claude CodeCodex
Give the agent durable, local memory with engram — recall past decisions before answering, and persist new decisions, preferences and facts as they happen. Use when work spans sessions or the user says "remember".
Skill Claude CodeCodex
Write a blameless, actionable incident postmortem from the raw facts. Use after an outage/incident, or when asked to write up "what happened" for the team.