The library

gsd:complete-milestone · Closing out a versioned release when you want to archive scope, lock requirements, and create a git-tagged historical record.

feature-prioritizer · Deciding which features to build next when you have a backlog and want a repeatable scoring framework that works across teams.

gsd:debug · Investigating bugs that require multiple test cycles and evidence accumulation, when you want the investigation context isolated from main work.

competitive-analysis · Deciding what to build next when you want to understand competitor advantage and vulnerability with evidence, not opinions.

gsd:discuss-phase · Starting a phase when you want the system to ask smart questions that avoid re-asking decisions already locked by prior phases.

gsd:do · When you know what you want to accomplish but aren't sure which /gsd-* command to invoke.

gsd:eval-review · Finishing a phase when you want to verify evaluation coverage aligned with the plan, or identifying what post-launch monitoring is needed.

microsoft-style · Aligning technical documentation with Microsoft style when you publish alongside Microsoft product docs and need reader consistency.

anti-ai-writing · Sharpening polished human drafts to strip ChatGPT-isms (banned words, phrases, structures) without altering substance or voice.

gsd:explore · Thinking through ideas before committing to plans, routing outputs into structured project artifacts.

gsd:extract-learnings · Capturing decisions and patterns discovered during a phase before moving to the next one, enabling continuous learning cycles.

gsd:fast · Quick fixes (typos, config tweaks, small refactors, forgotten commits) that don't justify planning overhead.

gsd:from-gsd2 · Reverse-migrating legacy GSD-2 projects back to v1 format while preserving completion state and phase hierarchy.

sc-estimate · Planning timelines and resource allocation with transparent confidence levels rather than false precision.

gsd:health · Validating .planning/ integrity before running major workflow operations, catching configuration drift early.

cognitive-load · Reducing extraneous cognitive load in interfaces and onboarding via chunking, progressive disclosure, and defaults rather than generic UX advice.

gsd:import · Ingesting external planning artifacts without overwriting existing project decisions, using conflict detection as a safety gate.

dice-roller · Resolving skill checks, attack rolls, damage, initiative, and saving throws in tabletop RPG adventures with deterministic outcomes.

gsd:insert-phase · Handling urgent work discovered mid-milestone without renumbering the entire roadmap.

gsd:intel · Maintaining searchable codebase intelligence index across multiple project subsystems.

eisenhower-triage · Fast triage of mixed-urgency task lists without deep prioritization frameworks.

gsd:list-phase-assumptions · Exposing hidden assumptions in phase planning so users can correct course before work starts.

gsd:milestone-summary · Onboarding new team members or reviewers with a single structured summary from milestone artifacts.

higgsfield-cinematic-prompt · Generating cinematic video scripts with second-by-second camera/music/text direction for product ads.

gsd:new-milestone · Bootstrapping milestone planning with standard artifact templates and folder structure.

summarize · Condensing large documents into cited key points for team alignment or decision-making.

market-scout · Preventing wasteful engineering by validating demand before any code when competitors are unclear.

mvp-scoper · Ruthlessly cutting scope bloat to 5-7 core features when launch speed beats feature completeness.

system-architect · Eliminating spaghetti architecture when deliberate choices before coding prevent costly refactors.

gsd:remove-phase · Cleanly deleting unstarted work from roadmap without orphaned markers cluttering context.

os-environment-probe · Configuring delegation backends once instead of asking about available tools each workflow.

gsd:research-phase · Delegating technical research to a fresh-context subagent before planning expensive work.

gsd:resume-at · Scheduling future Claude sessions around usage caps or scheduled overnight batch work.

gsd:resume-work · Seamlessly restoring GSD session state from checkpoints across multiple Claude conversations.

gsd:review-backlog · Systematically triaging project tasks and surfacing critical path blockers.

gsd:scan · Quick status checkup showing active phase, pending tasks, and system health.

os-guide · Onboarding users to Agentic OS workflows without requiring manual documentation reading.

gsd:session-report · Generating shareable post-session summaries with estimated token costs

gsd:set-profile · Switching GSD agent quality/cost tradeoffs without restarting work

os-init · Bootstrapping Agentic OS structure for new multi-agent projects

gsd:settings · Interactive configuration of GSD workflow toggles and model profiles

os-memory-manager · Closing sessions with proper three-tier memory promotion and deduplication

gsd:ship · Creating PRs and tracking merges after verify-work passes

gsd:sketch-wrap-up · Distilling throwaway sketches into persistent design skills

todo-check · Pre-flight auditing a file for technical debt before committing

gsd:sketch · Exploring design directions with fast HTML mockup variants

gsd:spec-phase · Clarifying phase requirements with Socratic interview before discuss-phase

gsd:spike-wrap-up · Converting research findings into reusable project-local skills

learning-loop · Continuous improvement of agent skills through feedback loops

gsd:spike · Fast exploratory research on technical unknowns before planning