Workspace Memory Benchmark Analysis
Use when the user wants to run workspace-memory benchmarks, interpret retrieval results, or map benchmark failures to likely ranking, lineage, or fallback defects before optimizing the system.
Openspec Superpower Orchestration
Use when a non-trivial change should follow an OpenSpec-plus-superpower workflow with formal specs, approval gates, implementation discipline, and no parallel planning system
Closure Retrospective
Use when a non-trivial task is substantively complete and end-of-task evidence may justify durable guidance in a skill or applicable AGENTS.md / CLAUDE.md, especially after repeated corrections, tool friction, sequencing loops, or stable scope boundaries surface near closure.
Idea Credibility Analyst
Use when a user wants to evaluate a product, startup, feature, or workflow idea by clarifying the idea through dialogue, researching similar products and discussions, comparing alternatives, assessing market crowdedness, deep-diving leading competitors and persistent user complaints in crowded spaces, and deciding whether to continue, pivot, or stop.
Advanced Brainstorming
Use when a user wants idea generation to become broader, less conservative, more imaginative, or more frame-breaking, especially when expanding an existing proposal into multiple unconventional but still intelligible directions.
Dispatching Code Review Subagents
Use when preparing to delegate code review to subagents — after implementation milestones, before merging complex changes, or when the diff spans multiple domains.
Receiving Feedback
Use when receiving feedback, suggestions, criticism, or review on any work — before acting on it. Especially when feedback seems unclear, questionable, conflicts with prior decisions, or asks for "professional" expansion.
Workspace Memory Skill
Use when the task involves creating, maintaining, or querying repo-local workspace memory for a project. This skill organizes team-shared agent memory as Markdown files under the current workspace, captures session summaries, maintains layered memory indexes, crystallizes durable team conventions and design rationale, and retrieves memory progressively to reduce context and token cost.
Workspace Memory Benchmark Authoring
Use when the user wants to add or expand workspace-memory benchmark fixture coverage, especially for complex retrieval cases that can be drafted safely by subagents under the benchmark fixture directory.
Openspec Discovery
Use when scope is unstable or requirements are unclear, before creating OpenSpec artifacts. Covers codebase investigation, requirement clarification, option comparison, and decision convergence.