espresso
01Plugin Claude Code
Concentrated Claude. Zero fluff, max power per token.
Plugin Claude Code
Concentrated Claude. Zero fluff, max power per token.
Plugin Claude Code
Concentrated Claude. Zero fluff, max power per token.
Instructions file CodexOpenCode
Instructions for mirkobozzetto/espresso, covering output rules, forbidden patterns and style.
Plugin Claude Code
Mirko Bozzetto's curated skills for AI coding agents (Claude Code, Codex, Cursor, ...).
Plugin Claude Code
Socratic roadmap interviewer. Clarifies what you actually want to build through a one-question-at-a-time conversation, researches how others solved it, then delivers a phased roadmap as a styled HTML page with a wireframe mockup and copy-paste command blocks. Re-discussable at any time; hands off to /brief or /ship.
Skill Claude CodeCodex
Clarify a fuzzy project idea into a phased roadmap through a Socratic interview. Asks what the objective really is, one question at a time, researches how others solved it (Exa), then writes docs/roadmap/ /roadmap.md and opens it as a styled HTML page with a wireframe mockup and copy-paste command blocks.…
Plugin Claude Code
Author a product brief by interview (the PRD tradition, under a plainer name), then emit user stories, scope, success metrics, and a derived nested task list. Stops at the task list and hands off.
Skill Claude CodeCodex
Author a product brief by interviewing the user, then emit user stories, scope, success metrics, and a derived task list. Triggers on "write a brief", "create a brief", "spec this feature", "brief". A brief is a product spec (what/why), NOT a technical design (use propose) and NOT open research (use brainstorm). The…
Plugin Claude Code
Orientation map at the start of a coding task: matches your intent against the skills available in this session and prints a recommended chain + execution mode + reflection level. Advisory only.
Skill Claude CodeCodex
Orientation map for the start of a coding task. Reads your intent, matches it against the skills currently available in this session, and prints a recommended chain of skills plus a suggested execution mode and reflection level, as options with a WHY, never a forced path. Advisory only: it never launches a skill and…
Plugin Claude Code
Use GitHub issues as cross-session resolution memory. Create, update, and resume self-contained, cold-readable issues via the gh CLI, recording the hypothesis and the resolution.
Skill Claude CodeCodex
Use GitHub issues as persistent cross-session resolution memory. Create, update, and re-read issues that are self-contained and re-readable cold, recording the hypothesis and the resolution. Triggers on "track this in an issue", "create an issue I can resume", "resume issue", "issue memory", "log this problem as an…
Plugin Claude Code
Query unfinished brief/propose/ship work and the exact command to resume it. Derives an open-work board from artifact frontmatter (no separate ledger to drift), and auto-surfaces it at session start so context survives /clear.
Hook
Runs when a session starts, executing scan.cjs via node with --banner. From mirkobozzetto/arsenal.
Skill Claude CodeCodex
Report unfinished brief/propose/ship work in this repo and the exact command to resume each, ranked by what to do now. Use when the user asks "what's next", "what's left", "where do I resume", "/next", "la suite", or to re-orient after a context reset. Reads artifact frontmatter as the source of truth; never…
Plugin Claude Code
Design workflow in the RFC tradition: problem -> alternatives -> tradeoffs -> design -> risks -> recommendation -> impl plan. Two sizes with hard ceilings. Forces reasoning before action. Optional GitNexus + Exa integration.
Skill Claude CodeCodex
Design workflow in the RFC tradition. Forces reasoning before action: problem → alternatives → tradeoffs → design → risks → recommendation → impl plan. Two sizes with hard ceilings: one page for a bounded choice, a few pages for a real design question. Use when user says "propose", "write a proposal", "design doc"…
Plugin Claude Code
Spec executor. Implements a finalized brief or an Accepted propose (or a bare prompt via an inline contract) on agent-teams / subagents / solo, then emits a user-run verification bundle + a trace ledger.
Skill Claude CodeCodex
Execute a predetermined spec. Ingests a finalized brief (docs/brief/ / with brief.md status ready + tasks.md) or an Accepted propose (PROPOSAL.md), locks a definition-of-done contract, implements it on the strongest available engine (agent-teams / subagents / solo, with ultracode awareness), keeps a tight leash with…
Plugin Claude Code
A project-level progress ledger written automatically. A Stop hook logs the working-tree delta at the end of every turn that touched files, so what you did - in ship, propose, or plain conversation - is recorded without you remembering to log it. next reads the ledger to show what moved.
Skill Claude CodeCodex
Read or hand-write the project progress ledger (.claude/trace.md). Use when the user says "/trace", "what did I do", "log this", "trace done", or wants to record or review what moved this session. The automatic Stop hook already logs file changes; this skill is the reader and the manual writer for the intent the hook…
Plugin Claude Code
Intent-routed web search via Exa MCP. 8 modes (quick/deep/code/docs/debug/news/compare/research).
Skill Claude CodeCodex
Power search via Exa MCP. Modes: quick, deep research, code, docs, debug, news, compare. Use when searching the web, finding docs, debugging errors, or researching any topic.