ComputerConnection
53 verified skills
plan-ceo-review
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when asked to "think bigger", "expand scope", "strategy review", "rethink this", or "is this ambitious enough". Proactively suggest when the user is questioning scope or ambition of a plan, or when the plan feels like it could be thinking bigger.
development
setup-browser-cookies
Import cookies from your real browser (Comet, Chrome, Arc, Brave, Edge) into the headless browse session. Opens an interactive picker UI where you select which cookie domains to import. Use before QA testing authenticated pages. Use when asked to "import cookies", "login to the site", or "authenticate the browser".
testing
design-consultation
Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview pages. Creates DESIGN.md as your project's design source of truth. For existing sites, use /plan-design-review to infer the system instead. Use when asked to "design system", "brand guidelines", or "create DESIGN.md". Proactively suggest when starting a new project's UI with no existing design system or DESIGN.md.
testing
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use /plan-design-review. Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish". Proactively suggest when the user mentions visual inconsistencies or wants to polish the look of a live site.
development
retro
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively suggest at the end of a work week or sprint.
development
code-forge-cycle
Post-POC build loop with 5 specialized builder agents and dual independent audit gates. Turns scaffolded code into production-quality software through iterative build-then-verify cycles.
development
office-hours
YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to "brainstorm this", "I have an idea", "help me think through this", "office hours", or "is this worth building". Proactively suggest when the user describes a new product idea or is exploring whether something is worth building — before any code is written. Use before /plan-ceo-review or /plan-eng-review.
development
plan-eng-review
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when the user has a plan or design doc and is about to start coding — to catch architecture issues before implementation.
testing
logic
Develop and refine advanced business logic. Use when modeling domains, designing state machines, defining validation rules, mapping business processes, or untangling complex conditional flows.
development
architect
Design system architecture for new features or major refactors. Use when planning complex implementations, evaluating trade-offs, or designing new systems.
development
gstack
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. gstack also includes development workflow skills. When you notice the user is at these stages, suggest the appropriate skill: - Brainstorming a new idea → suggest /office-hours - Reviewing a plan (strategy) → suggest /plan-ceo-review - Reviewing a plan (architecture) → suggest /plan-eng-review - Reviewing a plan (design) → suggest /plan-design-review - Creating a design system → suggest /design-consultation - Debugging errors → suggest /investigate - Testing the app → suggest /qa - Code review before merge → suggest /review - Visual design audit → suggest /design-review - Ready to deploy / create PR → suggest /ship - Post-ship doc updates → suggest /document-release - Weekly retrospective → suggest /retro - Wanting a second opinion or adversarial code review → suggest /codex - Working with production or live systems → suggest /careful - Want to scope edits to one module/directory → suggest /freeze - Maximum safety mode (destructive warnings + edit restrictions) → suggest /guard - Removing edit restrictions → suggest /unfreeze - Upgrading gstack to latest version → suggest /gstack-upgrade If the user pushes back on skill suggestions ("stop suggesting things", "I don't need suggestions", "too aggressive"): 1. Stop suggesting for the rest of this session 2. Run: gstack-config set proactive false 3. Say: "Got it — I'll stop suggesting skills. Just tell me to be proactive again if you change your mind." If the user says "be proactive again" or "turn on suggestions": 1. Run: gstack-config set proactive true 2. Say: "Proactive suggestions are back on."
development
tauri
Tauri-specific development patterns for NEXUS. Use when building desktop app features, handling IPC, or working with Rust backend.
development
sprint-planner
Orchestrates the full product strategy pipeline: product audit → roadmap → sprint plan with PM decision gates. This skill reads ACTUAL source code, cross-references git history, and produces three deliverables — a brutally honest product audit, a thesis-driven roadmap, and a sprint plan with PM decision gates between every phase. Use this skill whenever someone mentions: "sprint plan", "product roadmap", "plan the sprints", "PM questions", "product strategy", "audit this app", "roadmap this feature", "plan development", "break this into sprints", "phase this work", "create a development plan", "quarter planning", "what should we build next", "evaluate this app", "feature audit", "product review", "development roadmap", or any request for deliberate, methodical planning of software work. Also trigger when users want to evaluate whether features earn their place, when they reference PM decision gates or go/no-go checkpoints, or when they want to understand what's worth keeping in a codebase before planning new work. Even if the user only asks for one stage (just an audit, just a sprint plan), use this skill — it will guide them through the appropriate subset.
development
ollama
Local AI integration patterns using Ollama. Use when building features that need local LLM inference for the store AI server or other on-prem solutions.
development
cso
Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification. Two modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep scan, 2/10 bar). Trend tracking across audit runs. Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review".
testing
explain
Explain code or concepts in a clear, beginner-friendly way
development
benchmark
Performance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals", "bundle size", "load time".
development
closing-statements
End-of-session wrap-up that updates TELEMETRY.yaml, captures what happened, and writes a handoff for the next agent. Use this skill whenever the user says "close out", "wrap up", "end of session", "closing statements", "session done", "hand off", "update telemetry", or anything that signals they're done working and want to preserve context for the next session on any workspace. Also trigger when the user says "I'm done for now" or "save where we are." This should be the LAST thing that runs before a session ends.
documentation
document-release
Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when asked to "update the docs", "sync documentation", or "post-ship docs". Proactively suggest after a PR is merged or code is shipped.
development
store-sop
Document Computer Connection store processes in AI-queryable format. Use to capture SOPs for the store AI server POC.
development
gstack-upgrade
Upgrade gstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new. Use when asked to "upgrade gstack", "update gstack", or "get latest version".
testing
guard
Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety".
development
investigate
Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively suggest when the user reports errors, unexpected behavior, or is troubleshooting why something stopped working.
development
review
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff". Proactively suggest when the user is about to merge or land code changes.
development
unfreeze
Clear the freeze boundary set by /freeze, allowing edits to all directories again. Use when you want to widen edit scope without ending the session. Use when asked to "unfreeze", "unlock edits", "remove freeze", or "allow all edits".
data-ai
cc-platform-context
Loads the full Computer Connection AI platform repo map, architecture, and file layout. Use this skill at the START of any conversation that involves working on CC infrastructure, agents, MCP servers, dashboards, apps, Docker, the knowledge base, or anything in the ComputerConnection GitHub org. Also trigger when the user mentions repo names like cc-agents, cc-infrastructure, cc-platform, etc., or refers to 'the server', 'the stack', 'the agents', 'the dashboard', or any CC project work. If in doubt about whether to load this, load it — it's lightweight context and prevents the agent from fumbling around looking for files.
tools
debug
Systematic debugging workflow for vibe coders. Use when something isn't working and you're not sure why. Structured approach to find and fix issues.
development
decision
Log a decision with rationale. Captures the "why" so future-you doesn't wonder "why did we do it this way?" Use whenever making a non-obvious choice.
testing
skills/brainmap
--- name: brainmap description: Deep technical brain mapping of a project's logic web. Maps architecture, data flow, dependencies, component relationships, and generates POC recommendations. Use for understanding complex codebases, planning refactors, or brainstorming technical approaches. context: fork agent: Explore allowed-tools: Read, Grep, Glob, Bash(find *), Bash(wc *), Bash(git log *), Bash(tree *), Bash(head *), Bash(ls *) argument-hint: [project-path-or-focus-area] [--depth=deep|medium|
tools
codex
OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex".
tools
design
Product design deep-dive. Use when specifying features, mapping user journeys, defining UX, scoping MVPs, or thinking through product decisions. Translates ideas into buildable specs.
development
skills/docs
--- name: docs description: Produce missing documentation for projects. Analyzes codebase, identifies documentation gaps, and generates READMEs, API docs, architecture docs, setup guides, and inline documentation. context: fork agent: Explore allowed-tools: Read, Write, Edit, Grep, Glob, Bash(find *), Bash(tree *), Bash(wc *), Bash(git log *), Bash(head *) argument-hint: [project-path] [--type=readme|api|architecture|setup|all] --- ## Documentation Generator: $ARGUMENTS Find what's missing. Wr
tools
autoplan
Auto-review pipeline — reads the full CEO, design, and eng review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when asked to "auto review", "autoplan", "run all reviews", "review this plan automatically", or "make the decisions for me". Proactively suggest when the user has a plan file and wants to run the full review gauntlet without answering 15-30 intermediate questions.
development
browse
Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this".
testing
canary
Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy".
testing
careful
Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode".
development
connect-chrome
Launch real Chrome controlled by gstack with the Side Panel extension auto-loaded. One command: connects Claude to a visible Chrome window where you can watch every action in real time. The extension shows a live activity feed in the Side Panel. Use when asked to "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser".
tools
freeze
Restrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Use when debugging to prevent accidentally "fixing" unrelated code, or when you want to scope changes to one module. Use when asked to "freeze", "restrict edits", "only edit this folder", or "lock down edits".
development
land-and-deploy
Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies production health via canary checks. Takes over after /ship creates the PR. Use when: "merge", "land", "deploy", "merge and verify", "land it", "ship it to production".
testing
plan-design-review
Designer's eye plan review — interactive, like CEO and Eng review. Rates each design dimension 0-10, explains what would make it a 10, then fixes the plan to get there. Works in plan mode. For live site visual audits, use /design-review. Use when asked to "review the design plan" or "design critique". Proactively suggest when the user has a plan with UI/UX components that should be reviewed before implementation.
testing
qa
Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only.
development
qa-only
Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively suggest when the user wants a bug report without any code changes.
development
setup-deploy
Configure deployment settings for /land-and-deploy. Detects your deploy platform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom), production URL, health check endpoints, and deploy status commands. Writes the configuration to CLAUDE.md so all future deploys are automatic. Use when: "setup deploy", "configure deployment", "set up land-and-deploy", "how do I deploy with gstack", "add deploy config".
testing
ship
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", or "merge and push". Proactively suggest when the user says code is ready or asks about deploying.
development
skills/handoff
--- name: handoff description: Generate NEXUS-compliant handoff blocks when completing work. Use at the end of any significant task to create structured context for the next agent or session. disable-model-invocation: true allowed-tools: Read, Grep, Glob, Bash(git diff *), Bash(git log *), Bash(git status *) argument-hint: [agent-role] [task-id] --- ## NEXUS Handoff Generator Generate a handoff block for: **$ARGUMENTS** Reference the protocol: [HANDOFF_PROTOCOL.md](~/nexus/HANDOFF_PROTOCOL.md
tools
skills/onboard
--- name: onboard description: Generate onboarding documentation for new team members. Analyzes project and creates a "new developer guide" covering setup, architecture, key concepts, and gotchas. context: fork agent: Explore allowed-tools: Read, Grep, Glob, Bash(find *), Bash(tree *), Bash(git log *), Bash(head *), Bash(ls *), Bash(wc *) argument-hint: [project-path] [--role=frontend|backend|fullstack] --- ## Onboarding Guide Generator: $ARGUMENTS Create the guide you wish you had on day one.
tools
pitch
Generate sales and pitch materials for Computer Connection's AI services. Use when preparing to sell on-prem AI solutions to local SMBs.
data-ai
poc
Rapidly scaffold a proof of concept. Use when testing an idea quickly before committing to full implementation. Optimized for Zach's rapid prototyping style.
development
resume
Pick up exactly where we left off on a project. Reconstructs context from handoffs, git history, and project state. Use when starting a session on existing work.
tools
skills/review
--- name: review description: Thorough code review workflow. Use when reviewing PRs, auditing code quality, or doing self-review before submitting. Catches bugs, security issues, and design problems. context: fork agent: Explore allowed-tools: Read, Grep, Glob, Bash(git diff *), Bash(git log *), Bash(git show *), Bash(wc *), Bash(gh pr *), Bash(gh api *) argument-hint: [pr-number|branch|file-path] [--focus=security|performance|logic|style|all] --- ## Code Review: $ARGUMENTS Systematic review t
tools
scope-check
Anti-drift guard. Validates current work against original intent. Use when you feel things expanding or want to verify you're on track.
testing
skills/vision
--- name: vision description: "Zach's personal AI — his Jarvis. NOT a store agent. This is the owner's private command center that sits above everything else. Handles anything Zach needs — business, personal, technical, strategic, creative. High-systems AI: precise, anticipatory, authoritative. Invoke for ANY task." context: fork allowed-tools: Read, Grep, Glob, Bash, Edit, Write, Task, TodoWrite argument-hint: [what-do-you-need] — freeform. Vision figures out the rest. --- # VISION — Zach's Ja
tools
zach
Inject Zach's full identity, business context, and working preferences. Use at session start to eliminate cold starts. Lightweight context load — not a full agent like Vision, just who Zach is and how to work with him.
data-ai