oxbshw/LLM-Agents-Ecosystem-Handbook
Skill Claude CodeCodex
Use when capturing an architecture decision so it survives turnover — produces an ADR-NNNN.md from context, options considered, and the chosen path.
oxbshw/LLM-Agents-Ecosystem-Handbook
Skill Claude CodeCodex
Use when reviewing a proposed REST or GraphQL API change before merge — checks contract clarity, backwards compatibility, errors, pagination, auth, and naming.
oxbshw/LLM-Agents-Ecosystem-Handbook
Skill Claude CodeCodex
Use when first encountering a new dataset — produces a structured profile (schema, missingness, distributions, outliers, gotchas) before any analysis.
oxbshw/LLM-Agents-Ecosystem-Handbook
Skill Claude CodeCodex
Use after an incident is resolved — drafts a blameless postmortem from timeline notes, alerts, and chat threads.
oxbshw/LLM-Agents-Ecosystem-Handbook
Skill Claude CodeCodex
Use when opening a PR — produces a clean PR description (what / why / how to verify / risks) from a branch diff against base.
oxbshw/LLM-Agents-Ecosystem-Handbook
Skill Claude CodeCodex
Use when planning the next sprint — turns ticket intake + team capacity into a planned sprint with explicit non-goals.
oxbshw/LLM-Agents-Ecosystem-Handbook
Skill Claude CodeCodex
Use after a session to promote useful episodic notes from logs/episodic/ into distilled, dated entries in MEMORY.md and memory/semantic/.
oxbshw/LLM-Agents-Ecosystem-Handbook
Skill Claude CodeCodex
Use before connecting a new MCP server to your agent — produces a structured security review covering source, permissions, tools, network, and approvals.
oxbshw/LLM-Agents-Ecosystem-Handbook
Skill Claude CodeCodex
Use before opening a PR to audit the changes for stale comments, unused imports, missing tests, and inconsistencies with neighboring code.
oxbshw/LLM-Agents-Ecosystem-Handbook
Skill Claude CodeCodex
Use when the user asks for a sourced briefing on a topic that spans multiple web sources and requires citations.
Plugin Claude Code
Plugin marketplace listing 1 plugin: watch-skill.
Plugin Claude Code
Give the agent a video input via Watch Skill: watch, index, ask, and iterate (THE LOOP).
MCP server Claude CodeCodexCursor +2
MCP server "watch-skill" as configured in oxbshw/watch-skill. Launched with watch-skill serve.
Instructions file CodexOpenCode
Instructions for oxbshw/watch-skill, covering working on watch skill, what this project is, layout, commands and rules that are not negotiable.
Command
One-shot setup for Watch Skill — installs the engine, bootstraps ffmpeg/yt-dlp, registers the MCP server in every detected AI agent (with backups), and configures the user's preferred vision provider. Run once after installing the plugin.
Agent
Agent "agent-zero" from oxbshw/watch-skill, covering watch skill in agent zero, install, configure, smoke test (3 steps) and notes.
Agent
Agent "aider" from oxbshw/watch-skill, covering watch skill in aider, install, use it, a recording of a bug and notes.
Agent
Agent "amp" from oxbshw/watch-skill, covering watch skill in amp, install, configure, smoke test (3 steps) and notes.
Agent
Agent "claude-code" from oxbshw/watch-skill, covering watch skill in claude code, install, register the mcp server, smoke test (3 steps) and notes.
Agent
Agent "claude-desktop" from oxbshw/watch-skill, covering watch skill in claude desktop, install, configure and smoke test (3 steps).
Agent
Agent "cline" from oxbshw/watch-skill, covering watch skill in cline (vs code extension), install, configure and smoke test (3 steps).
Agent
Agent "codex-cli" from oxbshw/watch-skill, covering watch skill in codex cli (openai), install, configure, smoke test (3 steps) and notes.
Agent
Agent "continue" from oxbshw/watch-skill, covering watch skill in continue, install, configure, smoke test (3 steps) and notes.
Agent
Agent "cursor" from oxbshw/watch-skill, covering watch skill in cursor, install, configure, smoke test (3 steps) and notes.