frizynn

Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. The PRD should be detailed enough for execution by AI agents across tools (Amp, Cursor, Codex, etc.). Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Ralph may run via Amp, Cursor, Codex, or similar tools, so keep output tool-agnostic unless required. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.

Build and validate task DAGs for Ralph parallel execution. Use when planning execution order, detecting cycles, or explaining why tasks are blocked. Triggers on: plan dag, check dependencies, why is task blocked, execution order.

Merge task branches and resolve conflicts for Ralph parallel execution. Use when merging completed task branches or resolving git conflicts. Triggers on: merge branches, resolve conflict, integration merge.

Guidelines for implementing tasks safely in parallel execution. Use when working on a task in Ralph parallel mode to avoid conflicts. Triggers on: implement task safely, parallel mode, avoid conflicts.

Review integrated code for semantic and design issues. Use after merging task branches to detect inconsistencies. Triggers on: review integration, semantic review, check design consistency.

Generate and validate task metadata for Ralph parallel execution. Use when creating tasks.yaml v1 files, validating task dependencies, or checking mutex usage. Triggers on: create task metadata, validate tasks yaml, check task dependencies.

Diagnose and repair `linkedin-cli` authentication and runtime setup. Trigger on requests about `auth-status`, cookies, `LINKEDIN_COOKIE_HEADER`, `LINKEDIN_LI_AT`, `LINKEDIN_JSESSIONID`, browser extraction, `LINKEDIN_BROWSER`, `LINKEDIN_HEADLESS`, `LINKEDIN_PROXY`, `LINKEDIN_CONFIG`, `config.yaml`, redirect loops, authwall, checkpoint, session rejection, or any failure to authenticate LinkedIn requests in this repo.

Use the `linkedin-cli` repository to operate LinkedIn from the terminal. Trigger on requests to inspect the LinkedIn feed, search people or posts, fetch a profile, fetch profile posts, inspect an activity, export LinkedIn data as JSON, run `linkedin` commands, or decide which `linkedin-cli` command to use. Also use when the user mentions this repo or the `linkedin` CLI directly.

Use `linkedin-cli` for authenticated LinkedIn write actions. Trigger on requests to publish a LinkedIn post, react, unreact, save, unsave, or comment through the terminal, or when a user needs guidance on write-side browser fallback, visibility options, reaction types, or safe mutation workflows in this repo.

Archive a WhatsApp chat/group/channel history (text + images + transcribed voice notes) into an Obsidian vault, READ-ONLY, using the `wa2vault` CLI. Activate when the user says "archive/get me/pull/scrape/export the chat/group/channel with X", "the last N days of my chat with X", "X's WhatsApp", "the conversation with X", "transcribe the chat's voice notes", "update/refresh the history with X", or asks to pull fresh whatever was discussed with someone so it can be worked on. Engine: `wa2vault` (read-only, never sends). Requires wacli paired once via QR.

Append-only, attributed project memory for a code repository, stored as Markdown in `.trail/` and written only through the `trail` CLI (atomic, provenance-stamped, append-only). Tracks tasks with a timeline, lightweight ADR-style decisions, research notes, and a daily log, plus a regenerated `_hot.md` cache. Use when the repo has a `.trail/` directory, or when the user wants to start project memory in a code repo. Triggers include the word "trail"; starting or resuming a task, feature, or refactor; recording progress; making a technical decision or ADR (stack, schema, infra, library, API contract); doing non-trivial research; and questions like "what did we do with X", "where did X land", or "what did we decide about X". Activate proactively, without asking, when a non-trivial task, decision, or research begins. For notes with no associated repo (personal/global scratch), use the obsidian-memory skill instead.

Deep code optimization audit AND automatic fix execution using parallel specialist agents. Each agent hunts for performance anti-patterns, inefficiencies, duplication, and suboptimal code using pattern-based detection (Grep/Glob) WITHOUT reading the full source code first. Covers ALL domains: database queries, memory leaks, algorithmic complexity, concurrency, bundle size, dead code, I/O & network, rendering/UI, data structures, error handling, caching, build config, security-performance, logging, infrastructure, AND code simplification (duplication elimination, logic reduction, data compression, boilerplate extraction). With --fix flag, automatically implements fixes as parallel PRs in isolated git worktrees. Use when asked to: "optimize my code", "find performance issues", "audit code quality", "speed up my app", "find bottlenecks", "code review for performance", "find anti-patterns", "improve code efficiency", "reduce latency", "optimize performance", "code smell detection", "find slow code", "optimize thi