Productivity plugins

CC-PO: a Product Owner workflow plugin for Claude Code. One PO session per product line triages a GitHub Project, starts sub-sessions and accepts their work.

1 skill

Universal AI context transpiler. Define once. Spec everywhere.

Strips wasteful patterns from Bash tool output (git boilerplate, long lines, repeated diagnostics) to save tokens.

Spawns steerable child Claude Code sessions in terminal windows with automatic result forwarding via hooks. Requires the spawn-claude CLI to be on PATH.

Injects the current local system time into Claude's context as <time>HH:MM</time> on every user prompt.

A local-first coding agent(Codex, Claude code, Cursor) plugin that turns everyday prompts into private, reusable language lessons with MCP tools, SQLite storage, and an interactive progress dashboard.

A memory companion that lives in your AI workflow

Le flash info du dev au-dessus du prompt : les actus fraîches de Human Coders News, du Journal du hacker, de la veille de Camille Roux, de LinuxFr et des blogs IA (Anthropic, claude.dev, Claude Code…), une à la fois.

Public Plugin. Browse a repository's ubiquitous language (GLOSSARY-MAP.md, each context's GLOSSARY.md, the ADRs) in a band above the prompt and a pane, and steer you and the model away from its Avoid words: a note to the model on prompts, a refusal on Markdown edits

Public Plugin, macOS. See the images you paste into Claude Code: a thumbnail above the prompt for each [Image #N], drawn in any truecolor terminal (Warp included) and with real pixels in kitty and Ghostty, and a button that opens it full size in Quick Look

See the pictures in your prompt: thumbnails above the prompt for pastes, @-mentioned files and the clipboard, with the real picture laid over them on Windows. Windows, macOS, Linux and WSL.

No description.

Routes each Claude Code turn to Haiku, Sonnet, or Opus based on task complexity, with cache-aware switching.

One install for everything Tommy curates: memory plus all skill bundles. tommy-pentest is separate and not included.

Pin one goal for the session: it sits above the prompt with a timer, and Claude is told to stay on it and flag unrelated work instead of drifting.

Reusable prompts one command away: /snip review drops your saved review prompt into the prompt box, with {{selection}}, {{branch}}, {{date}} and {{args}} filled in.

Your standup, written for you: journals every Claude turn (prompt, files, commits) and turns yesterday and today into Yesterday / Today / Blockers with /standup.

Audited scientific skills, public-source tools, reproducible artifacts, and evidence review for Codex.

200 skills · 1 MCP server · hooks

Expose the plugin-safe Claude Code subset of AI-Agents-Safe-Coding-Skills through a single marketplace entry.

200 skills

Expose the plugin-safe Claude Code subset of Agentic Awesome Skills through a single marketplace entry.

200 skills

Structured, repeatable workflows for digital production domains: 338 skills across 21 domains, run as gated workflows

200 skills

Product builders and configurers with guided feature increments for Documentation, Account, Access, Console, Environment, Build, Deploy, Model, Marketplace, Transform, Persist, Rule, Connect, System, Report, Schedule, Inference and Enact.

112 skills · 74 agents

Governed legal workflows, mostly Australian: research, contracts, drafting, employment, work health and safety, privacy, consumer and competition, corporations, AI governance, AML/CTF, estates, litigation deadlines, evidence, matter triage and jurisdiction-neutral reasoning practice, with official-source verification and qualified-lawyer review gates.

109 skills

Think more clearly about your work. 40+ skills and 20+ agents for technical leaders building and leading in the age of AI. Covers AI product craft, people leadership, stakeholder reflection, program coordination, and longitudinal self-reflection.

54 skills · 22 agents

Daily workflow, code quality, dev tools, and specialist agents.

60 skills · 13 agents

Educated, enforced project management for AI development - make any model ship like a senior team. An opinionated Claude Code plugin: a PM layer that challenges scope and sequences risk, parallel implementation waves, and a git-hook commit gate that blocks merges until a multi-agent review issues MERGE READY (enforced, not advisory). Context-clean by design - single-use agents with a learnings-driven retry loop, off-context ADR deliberation, and a depth gate that resets before the window compacts. Three integration tiers (full / balanced / light) and three voice profiles (dev / mid / eli5). 19 agents, 38 skills, 48 stack profiles, 7 combo profiles, 1 supplementary profile (frontend-data-flow).

38 skills · 1 command · 19 agents

Explicit skills for local engineering workflows, evidence-based reviews, and upstream tracking in Codex.

54 skills

Task-sized orchestration with durable lifecycle recovery and compact delegation visibility.

1 skill · 13 commands · 34 agents · hooks

Portable engineering workflows and standards for Codex and Claude Code.

47 skills · 1 agent

Business advisor AI agent skills for founders and small companies

29 skills · 11 commands · hooks