The library

sprint-status · Quick snapshot of progress across parallel Claude Code sessions before switching contexts.

analyze-test · Validating A/B test results with statistical rigor before deciding to ship a variant.

brand-setup · When you are an agency managing multiple client brands and need one canonical profile that auto-loads into every marketing skill without manual context-switching.

competitor-analysis · Benchmarking your marketing strategy and messaging against 2-5 direct competitors when you need a 360-degree view of their content, SEO, ads, social, and positioning strategies.

finance · Building a complete financial picture with variance analysis and runway projection for founders

write-query · Quickly drafting SQL exploratory queries without manual syntax lookup.

dashboard · DevOps teams and engineering leads setting up project health dashboards for visibility on CI/CD, code quality, and infrastructure.

analyze-cohorts · Measuring product retention and engagement trends by user cohort to guide onboarding improvements and feature prioritization.

annotate · Teams reviewing specifications, documentation, or design rationales where structured feedback (comments, deletions, image callouts) beats inline email.

seo-auditor · Content teams and developers launching sites who want a quick checklist for on-page SEO (meta tags, headings, images, structured data).

team-delegate · Quick team task delegation with workload balancing, member messaging, and unassigned task triage.

transform-roadmap · Product teams transitioning from output-focused to outcome-focused planning, especially before executive presentations or quarterly planning.

plan-review · Multi-turn agent workflows where a human must review a plan before expensive implementation decisions are locked in.

plan-ceo-review · Founders and product managers blocking time BEFORE spec writing to validate that the requested feature is actually the right product.

report · Tech leads and engineering managers running quarterly health reviews who want a one-page snapshot of code quality, velocity, and dependency health.

financial-health · Quick SaaS financial diagnosis when you need investor-ready health snapshot.

okr · Engineering and product teams running quarterly planning cycles who want consistent OKR structure with clear scoring rubrics.

meeting-notes · Converting raw meeting notes into structured summaries with clear action items for tracking.

design-sales-stages · Establishing a forecast-aligned stage ladder for a new business motion or validating an existing Salesforce Opportunity structure against best practices.

sprint · Teams running 1-2 week sprints who need capacity estimation, story selection, and structured retrospectives in one workflow.

execute · Multi-channel campaign asset production where you need blog, social, email, and video scripts all generated from a single brief using specialized channel writers.

campaign-plan · Creating a comprehensive, ready-to-execute campaign plan when you have a clear goal, audience, and timeline but need guidance on messaging, channels, and content calendar.

retro · Engineering teams running retrospectives who want data-driven insights from git history supplemented by team feedback.

sprint-health · Scrum masters and engineering leads running daily standups who need a quick health check with clear red/yellow/green signals.

sprint-plan · Scrum masters facilitating sprint planning who need a structured template to fill capacity, identify risks, and align the team on goals.

recruiting-prep-interview · Recruiting coordinators onboarding new candidates into an existing hiring pipeline who need consistent folder structure and template for resume and interview notes.

recruiting-process-interview · Systematically evaluating multiple PM candidates against the same opening using a consistent 4-dimension scoring model that produces comparable rankings.

legal · Best for interactive legal command execution with user gating.

retro · Teams running Claude Code with persistent learning hooks who want to systematically harvest and embed hard-won insights into their agent skills.

brand-config · Real estate fund managers or CRE groups producing repeated investor-facing documents who want consistent visual identity across pitch decks, memos, and LP updates.

pr · One-command workflow to atomically format, stage, and push a PR without manual git steps.

km · Switching cognitive modes (e.g., from coding to research) without losing session continuity.

Q · MCP-first code intelligence queries when you need call/def/ref across the whole codebase without manual grep.

qa · Verifying semantic and regex search implementations work correctly across all file types and languages without blocking or pagination bugs.

cr · Catching language-specific bugs and design issues before commit by applying both project-local and generic review profiles to changed code.

ci · Testing a Haskell-to-Rocq compiler change locally before pushing by running the exact GitHub Actions workflow steps without Docker.

do · Managing multi-wave work streams where wave-dependent model routing and context-aware task selection accelerate delivery over manual task picking.

av · Programmatically launching and controlling multiple AI agent sessions without TUI overhead when orchestrating batch work or CI/CD-driven agent tasks.

pr · Separating code review (clean diff) from planning artifact archiving, allowing reviewers to focus on implementation while preserving design rationale as write-once history.

rlm · Deep codebase analysis on large repositories requiring multi-level reasoning without manual context pruning, routing models and tool access by depth/effort.

db · Quick ad-hoc database queries during development when Docker Compose is the deployment model and CLI access is faster than GUI tools.

ox · Maintaining team coding standards and recording agent execution traces when working in a SageOx-enabled team project.

qf · Gate code commits and PRs by enforcing type safety, linting, and RDO-specific conventions (database, auth, MUI Grid v2) before review.

fi · Marking a sprint or phase complete by bundling build verification, documentation updates, dialog export, and git history into a single protocol.

ui · Browsing and managing Claude Code dialogs in a browser interface when command-line export is insufficient or team collaboration is needed.

es · Grounding agent fact-checking in explicit evidence standards when making claims, combining project-agnostic and project-specific validation rules.

up · Synchronizing new project or environment preferences across all AI tools (Claude, Codex, Gemini, Cursor) in a single command.

dev · Routing developer tasks to the right specialist agent (debug, review, refactor, commit, PR) without manual agent selection overhead.

wt · Isolating work on individual GitHub issues using git worktrees, avoiding context switching between branches in a single checkout.

bg · Autonomous grinding through a priority-sorted issue queue without pausing between tasks, ideal for high-volume bug triage or feature checklists.