eagle-skills

Write code the way an experienced human engineer writes it — minimal, direct, first-principles, no AI slop, no over-engineering. Use this skill for EVERY code generation, refactoring, or code review task, in any language. Trigger especially when the user says "maintainable", "clean", "simple", "no slop", "don't over-engineer", "production code", "like a human wrote it", or complains that generated code is bloated, over-abstracted, over-commented, or defensive. Also use when writing new modules, functions, scripts, API endpoints, or components from scratch.

Install hook-based engineering governance for agent-led projects. Use when the user says: 'govern this project', 'install governance hooks', 'agent governance', 'context bloat guard', 'hook-based engineering governance', 'stop agents ignoring instructions', or asks to make AGENTS.md / CLAUDE.md enforceable through hooks.

Full project onboarding: generates a lean CLAUDE.md, bootstraps LLM Wiki, links Obsidian vault, and installs eagle-skills (15 skills + 13 agents). Use when starting a new project, onboarding to a codebase, or when the user says: 'init claude', 'setup claude md', 'create claude.md', 'project init', 'eagle init', 'bootstrap this project', 'set up this repo for claude', 'add claude.md', 'onboard this project', 'install eagle skills'. Also trigger when you detect a project has no CLAUDE.md and the user is about to do significant work in it.

Use this skill to create project trackers, task lists, roadmaps, and Gantt charts as .xlsx files that open in Excel AND import cleanly into Google Sheets. Triggers on: 'project tracker', 'task tracker', 'create a Gantt chart', 'project plan', 'roadmap', 'timeline', 'sprint board', 'RAID log', 'who's doing what by when', 'track tasks with owners and dates', 'turn this into a tracker', or when the user lists tasks/owners/dates and wants them organized into a trackable, shareable sheet. Produces status dropdowns, status-colored Gantt bars, computed duration/%-complete, a today marker, and a small dashboard. Composes with eagle-clean-sheet styling. Do NOT use for ad-hoc data tables with no time/ownership dimension (use eagle-clean-sheet directly), or for live Google Sheets API integration.

Write like a human, not like an AI. Use this skill whenever the user asks for writing that sounds natural, authentic, specific, or not AI. Trigger on: human writing, make it sound human, less AI, no AI voice, ghost mode, no corporate tone, no AI slop, write like a journalist, write like a real person, degpt, README polish, article rewrite, email rewrite, report rewrite, or social post rewrite.

Route Spectral review requests to the correct Eagle specialist. Use when the user says spectral agents, spectral review, full spectrum review, run review specialists, review this PR with agents, choose the right review agents, or asks for code review without naming a specialist. Do not default to plan, investigate, or ship unless the user is planning, debugging, or shipping.

One-time global environment setup for Claude Code. Use when the user says: 'eagle bootstrap', 'setup my environment', 'eagle setup', 'first time setup', 'configure claude globally', 'install eagle environment', 'set up my machine for claude'. This skill enriches the global ~/.claude/CLAUDE.md with behavioral rules, installs the compact.sh token-saving hook, configures the Obsidian vault path, and confirms eagle-skills agents are installed. Run once per machine — safe to re-run (idempotent, skips what's already done).

Review and add new rules to compact-rules.json for the token-saving hook. Use when the user says: 'add compact rules', 'compact-add', 'add a compact rule', 'this command is too verbose', 'compact this command', 'grow compact database'.

Structured development workflow that sequences planning, building, testing, and shipping. Use when the user says: 'feature flow', 'build this feature', 'implement this', 'dev workflow', 'eagle flow', 'start feature', 'build and ship', 'full dev cycle', 'plan and build', 'implement and review'. Also trigger when the user describes a feature to build and expects the full cycle: planning, implementation, testing, review, and commit.

Research-driven project scaffolding for multiple technology stacks. This skill MUST be used when the user asks to: create a new app, scaffold a project, set up a new project, initialize a codebase, start a new application, bootstrap a project, set up a monorepo, or needs help with project structure, dependencies, database setup, or deployment. Covers mobile development (SwiftUI for iOS/macOS, Jetpack Compose for Android, Kotlin XML Views for traditional Android, Flutter for cross-platform, Expo React Native for cross-platform), backend APIs (Node.js/Express, Python/FastAPI, Python/Flask, Python/Django, Rust/Axum), web frontends (Next.js for React, Nuxt.js for Vue), and monorepo architecture (Turborepo). All mobile stacks include comprehensive design system patterns with tokens, components, and Material 3/Cupertino styling. All backend stacks include database setup (PostgreSQL, MongoDB, SQLite), ORM configuration (Prisma, Drizzle, SQLAlchemy, SQLModel, SQLx), object storage (MinIO/S3), and Railway deployment.

Detects and eliminates AI-generated slop in code, text, and design. Use this skill whenever the user asks to review code quality, clean up AI-generated content, remove LLM patterns, simplify over-engineered code, or make output feel human-written. Trigger on: 'review for slop', 'too much AI', 'over-engineered', 'simplify this', 'feels like AI wrote this', 'clean up this code', 'make it human', 'remove the slop', 'code quality review', 'LLM smell', 'vibe check', 'anti-slop'. Also trigger proactively when you notice AI-typical patterns in code or text you're writing or reviewing — don't wait for the user to ask.

This skill should be used when the user asks to review ad creatives, audit advertising campaigns, evaluate marketing collateral, critique ad designs, or assess creative performance across any medium. Trigger phrases include: 'review these ads', 'ad creative review', 'audit my ads', 'critique these creatives', 'what's wrong with my ads', 'ad review', 'creative review', 'evaluate these campaigns', 'review my marketing materials', 'ad teardown', 'creative audit', 'are these ads effective', 'review this radio ad', 'critique our billboard', 'evaluate our TV commercial', 'review this jingle', 'audit our print ads', 'review our podcast ad'. Also trigger when the user provides ad files (images, videos, audio, PDFs, scripts) and asks for feedback, or mentions ad platforms or channels (Meta, Google, TikTok, radio, OOH, print, TV, podcast, etc.) in the context of evaluating creative quality. This skill handles digital ads, audio ads (radio, podcast, jingles), out-of-home (billboards, transit), print (newspaper, magazine

ALWAYS use this skill instead of the default docx skill whenever creating, editing, or manipulating Word documents (.docx files). This skill applies a modern, clean, monochrome design system — Helvetica body, Courier New for code, tight margins, inline code spans, proper multi-line code blocks, clean tables, and zero visual clutter. Triggers on: 'Word doc', '.docx', reports, memos, letters, templates, or any Word deliverable. Also use when eagle-ux-review, eagle-product-diagnostics, or eagle-ad-review output format is set to Word or both. Do NOT use for PDFs, spreadsheets, or Google Docs.

ALWAYS use this skill instead of the default xlsx skill whenever creating, editing, or manipulating spreadsheet files (.xlsx, .xlsm, .csv, .tsv). This skill applies the Clean Doc design system to Excel outputs — Helvetica body, Courier New for code/formulas, monochrome palette, clean table styling. Triggers on: any spreadsheet task including creating, reading, editing, formatting, charting, cleaning data, or converting tabular formats. Also use when eagle-product-diagnostics or eagle-ad-review needs to export structured data (scorecards, funnels, findings) to Excel. Do NOT use for Word documents, PDFs, or Google Sheets API integrations.

This skill should be used when the user asks to validate UX findings against real data, triangulate product metrics, diagnose why a feature isn't hitting its goals, connect Firebase/Mixpanel/Amplitude events to UX problems, analyze event funnels against design intent, check if a product hypothesis passed or failed using data, or correlate drop-offs with UX issues. Trigger phrases include: 'validate these findings', 'why isn't this metric moving', 'triangulate UX and data', 'product diagnostics', 'check events against UX', 'is this feature working', 'funnel analysis', 'metric validation', 'connect analytics to UX', 'why are users dropping off', 'compare DB outcomes to UX', 'event-to-screen mapping'. Also trigger when the user provides analytics exports, event schemas, or database samples alongside UX review findings or product goals.

This skill should be used when the user asks to conduct a UX review, UX audit, usability review, heuristic evaluation, or design critique of any digital product. Trigger phrases include: 'review this app', 'UX audit', 'UX review', 'critique this design', 'what's wrong with this UI', 'analyze this screen', 'teardown this app', 'heuristic evaluation', 'usability review', 'evaluate the UX', 'design feedback', 'UX teardown'. Also trigger when the user uploads screenshots or video of an app and asks for feedback, or mentions UX laws (Hick's Law, Fitts's Law, Jakob's Law, etc.) in the context of evaluating a product. This skill handles video files (extracting frames via ffmpeg at 1-second intervals), screenshot sets, single screen images, or PRD-based flow validation. Always use this skill for any UX evaluation task even if the user doesn't explicitly say 'UX review'.