romiluz13

THE ONLY ENTRY POINT FOR CC10X. Activate this skill for build, debug, review, and plan requests. Use when the user asks to implement, fix, review, plan, test, refactor, or continue code work. Trigger keywords: build, implement, create, write, add, review, audit, debug, fix, error, bug, broken, plan, design, architect, spec, brainstorm, test, refactor, optimize, update, change, research, cc10x, c10x. CRITICAL: Route and execute immediately. Do not stop at describing capabilities.

Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.

Resolve an in-progress git merge or rebase conflict hunk by hunk — see the state, find the primary sources for each side's intent, resolve by intent (never --abort), run the project's checks, and finish the operation. Model- invoked: agents reach for it when a git operation reports conflicts.

Canonical deep-module vocabulary (module, interface, depth, seam, adapter, leverage, locality) for designing a module's shape — a lot of behaviour behind a small interface at a clean seam, testable through that interface. The single source of truth for these terms; other skills (architecture, codebase-hygiene, building, planning) point here instead of restating them. Use when designing or improving a module's interface, finding deepening opportunities, deciding where a seam goes, or making code more testable.

Two-mode skill: (1) find semantic duplicates — functions doing the same thing under different names, invisible to copy-paste detectors; (2) deepen shallow modules — thin wrappers and pass-through layers that spread complexity. Advisory and read-only; changes route through BUILD with full gates.

Use when a BUILD phase completes, a commit is staged, or a PR is about to be created, and the diff has not yet been reflected in documentation. Also use when the user says "update docs", "sync docs", "document this", or asks whether documentation is up to date.

Shared preamble loaded by all cc10x agents — memory protocol, contract format, output rules.

Greenfield architecture design: map functionality flows, draw components, design APIs, classify dependencies, plan observability. For multi-component, API, schema, auth, or integration-heavy work. For retrofitting existing code, use codebase-hygiene instead.

Post-call debrief. Captures notes, maps to qualification framework, flags gaps, drafts follow-up email. Use when: just got off a call, have call notes to process, need to capture discovery output, want to update qualification status, need a follow-up email, or want to update CRM notes. Triggers: debrief, call notes, just got off, post call, call recap, capture notes, what happened, update MEDDPICC, follow up email after call, notes from meeting, call summary, discovery notes, I just spoke with.

Diagnoses stuck deals and builds a 3-move recovery strategy using MEDDPICC scoring and targeted frameworks. Use when: deal is stalled, competitive threat identified, single-threaded, or process has stopped. Triggers: deal strategy, deal review, stuck deal, advance this deal, competitive play, challenger approach, deal health, how do I win this, competitive strategy, how to advance, deal blocked, reframe strategy.

Builds a complete meeting brief before any discovery, intro, or follow-up call. Never walk in blind. Use when: preparing for a discovery call, intro meeting, follow-up, or AE-led meeting. Includes: exec summary, agenda, qualification gap analysis, key questions, objections, proof points. Triggers: prep, meeting prep, discovery prep, prepare for, call prep, before meeting, discovery call, intro meeting, meeting brief, what should I know, going into a call, prep me.

Reviews full pipeline, assigns forecast categories by MEDDPICC score, calculates coverage and velocity. Use when: doing a pipeline review, preparing a forecast, checking territory health, or finding at-risk deals. Triggers: pipeline review, forecast review, pipeline health, deal health check, commit list, best case list, forecast, coverage analysis, what's my number, pipeline at risk, inspect pipeline, weekly forecast.

Builds a three-act proposal narrative with win themes and executive summary from discovery notes. Use when: deal is qualified (MEDDPICC 20+) and seller needs to write a formal proposal or business case. Triggers: proposal, write proposal, build proposal, proposal narrative, executive summary, business case, win themes, three-act proposal, proposal strategy, proposal draft, write the business case.

Drafts hyper-personalized outreach across all 4 channels. Always reads research file first. Never generic. Use when: writing LinkedIn connection requests, InMail, cold emails, cold call scripts, follow-up messages, or any outreach for a specific contact at an account. Triggers: write outreach, draft message, cold call, cold email, LinkedIn message, InMail, email sequence, follow up, outreach for, message to, reach out to, contact script, call script, sequence.

Post-call debrief. Captures notes, maps to qualification framework, drafts follow-up email. Trigger with "just got off a call with [company]", "debrief [company]", "call notes for [company]", "I just spoke with [name]", "post call [company]", or "update qualification for [company]".

Builds a complete meeting brief before any sales call. Never walk in blind. Trigger with "prep me for [company]", "meeting prep for [company]", "call prep [company]", "prepare for my call with [company]", "going into a call with [company]", or "what should I know before [company]".

Pi terminal agent workspace — install, /commands, sessions, compaction, settings.json, AGENTS.md, skill discovery, precedence, session JSONL, /tree, providers/auth, models.json, credential resolution, platform setup, editor (@file, Tab, images, !bash), message queue (steering, follow-up), built-in tools (read/bash/edit/write/grep/find/ls, --tools, --no-tools), print mode (-p, piped stdin), SYSTEM.md/APPEND_SYSTEM.md, CLI flags (-c, -r, --session, --fork, --no-session), @files args, resource flags (--no-extensions, --no-skills), model shorthand (provider/id, name:thinking), all slash commands, env vars, philosophy (no MCP/sub-agents/plan-mode by design). Use for pi config, skills, sessions, compaction, providers, models, tmux, Termux, Windows, tools, modes, system prompt, message queue, or "does pi support X".

Pi coding agent customization — Themes, Keybindings, Prompt Templates, System Prompt overrides, and Settings. Use when configuring or modifying the visual appearance, UI colors, keyboard shortcuts, prompt templates, or the default system prompt behavior of the pi terminal agent. Use for "custom theme pi", "change keybindings", "modify system prompt", "SYSTEM.md", "APPEND_SYSTEM.md", "settings.json", "keybindings.json", "prompt template", even if pi-cli-workspace is already active.

Authoring Pi TypeScript extensions — ExtensionAPI, custom tools, commands, UI hooks, resources_discover, `registerProvider()`, and how extendResources merges skill paths after base reload. Use when the user builds or debugs pi extensions, registers tools, adds /commands, hooks events, integrates TUI components, or ships extension examples. Use for "how do I extend pi", "extension API", "registerTool", "registerProvider", even if pi-mono is not mentioned.

@mariozechner/pi-mom — Slack bot Master Of Mischief (Mom), self-managing agent, Docker sandbox, and events system. Use when setting up Mom in Slack, debugging data/ workspace issues, managing context.jsonl/log.jsonl memory, or creating periodic/immediate events. Use for "mom slack bot", "docker sandbox", "mom events", "artifacts server", "cloudflare tunnel", "custom tools", "MomCustomTool", "multi-platform", "v86 sandbox", even if pi-coding-agent is not mentioned.

Pi headless RPC JSONL over stdin/stdout, strict LF framing, --mode json event streaming, and Node SDK alternatives (AgentSession). Use when integrating pi --mode rpc, pi --mode json, writing a client that speaks the protocol, reading JSON event streams, or choosing RPC vs in-process SDK. Use for "pi rpc client", "JSONL framing", "readline rpc", "--mode json", "json events", "embed pi without subprocess", "createAgentSession", "AgentSessionRuntime", "ModelRegistry", "embed pi", "SDK factory", even if the user only pasted JSON lines.

@mariozechner/pi-agent-core Agent runtime — message flow, tool execution modes, event sequence for prompt() and continue(), embedding in apps. Use when building on Agent class, wiring subscribers, or debugging tool loops beside pi-ai. Use for "pi agent events", "beforeToolCall", "agent.subscribe", even if coding-agent CLI is not involved.

@mariozechner/pi-ai — unified LLM streaming API, tools, providers, thinking events, and cross-provider handoffs as implemented in pi-mono. Use when integrating or debugging pi-ai, adding providers, using stream/complete, TypeBox tools, or token usage. Use for "pi-ai stream", "getModel", "new provider in pi", even if the user only says OpenRouter or Anthropic APIs.

Pi packages — npm/git distribution of extensions, skills, prompts, themes via keywords pi-package and package.json pi manifest; pi install paths and security expectations. Use when shipping or consuming pi-package, adding pi.skills entries, or explaining install vs project-local -l. Use for "publish pi skills on npm", "pi install", "pi-package.json", even without naming this skill.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Maintain and improve a Pi coding agent setup over time — prevent drift AND find new leverage. Use when auditing setup health, before adding a package/extension, before publishing, or when asked "is my setup healthy" / "audit my setup" / "how do I keep this sharp".

Find semantic duplicates (same intent, different implementation) and shallow modules (thin wrappers spreading complexity). Read-only advisory — changes route through BUILD with full gates. Use when auditing code quality, before refactoring, or when a codebase feels bloated.

Treat documentation as a first-class deliverable of every BUILD phase. Classify the diff's doc impact across 3 layers (business/technical/audit) and write only the updates genuinely needed. Use after BUILD completes, before a commit/PR, or when asked "are docs up to date".

Review and sharpen persistent memory so it compounds instead of accumulating. Use when pruning pi-hermes-memory entries, doing monthly memory hygiene, or when the same lesson has been recorded multiple times.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

THE ONLY ENTRY POINT FOR CC-P4P. This skill MUST be activated for ANY product management task - never skip. Use this skill when: writing specs, synthesizing research, planning roadmaps, drafting stakeholder updates, defining metrics, or ANY PM request. Triggers: spec, prd, feature, requirement, user story, acceptance criteria, research, interview, feedback, survey, competitive, persona, insight, roadmap, priority, plan, timeline, rice, moscow, okr, quarter, update, status, stakeholder, announcement, launch, report, metric, kpi, dashboard, retention, conversion, north star, product, pm, brainstorm. CRITICAL: Execute workflow immediately. Never just describe capabilities.

Internal skill. Use cc-p4p-router for all PM tasks.

Internal skill. Use cc-p4p-router for all PM tasks.

Internal skill. Use cc-p4p-router for all PM tasks.

Internal skill. Use cc-p4p-router for all PM tasks.

Internal skill. Use cc-p4p-router for all PM tasks.

Internal skill. Use cc-p4p-router for all PM tasks.

Internal skill. Use cc-p4p-router for all PM tasks.

Audits Claude Code project setup and provides score with recommendations. Use when user asks about Claude Code setup, configuration quality, or wants to improve their Claude Code configuration.

Helps with common project tasks like setup, configuration, and troubleshooting. Use when user asks about project structure, dependencies, common issues, or says "help me understand this project".