101 skills · sorted by relevance
Review SaaS and purchasing spend to find growing cost categories, slow approval processes, and overlapping suppliers. Produce categorized reports and consolidation options that account for migration costs, clustered renewals, and the risks of relying on one critical supplier.
Find business logic repeated across software components, such as notifications, auditing, and validation. Compare responsibilities and dependencies, then recommend a shared service, shared library, or component merger with a prioritized consolidation plan.
Merges ephemeral report and analysis artifacts into permanent documentation. Use when LLM-generated markdown files have accumulated and need consolidation.
The English summary is being prepared. Showing the original description.
Memory systems specialist for hierarchical memory, consolidation, and outcome-based learningUse when "memory system, memory hierarchy, memory consolidation, forgetting strategy, salience learning, outcome feedback, temporal memory levels, entity resolution, memory, zep, graphiti, mem0, letta, hierarchical, consolidation, salience, forgetting, ml-memory" mentioned.
The English summary is being prepared. Showing the original description.
Restructure code through extraction, consolidation, or responsibility moves while preserving its behavior. Establish checks before editing, repeat them afterward, and keep intermediate versions buildable and testable without mixing in feature changes.
Compare changes across Git worktrees, branches, and pull requests through a facilitated discussion between agents. Produce one consolidation plan covering the target worktree, merge order, conflicts, and decisions that need human input.
Manage multiple apps and shared packages in one repository. Analyze dependencies and change impacts, limit builds and tests to affected packages, configure caching, and plan repository consolidation while preserving Git history.
Design persistent agent memory that retains knowledge across sessions and retrieves relevant facts when needed. Compare storage approaches, track people and changing information, and plan memory consolidation and evaluation based on the kinds of questions the agent must answer.
Find classes left in parent folders or namespaces and identify nested component structures. Compare consolidation, splitting, and shared code extraction, then plan and carry out refactoring with updated references and tests.
Create an evidence-based plan for modernizing an existing system. Analyze code and dependencies, research technology choices, and produce domain-specific migration plans with testing, rollback steps, and a consolidated roadmap for developers to execute.
Review Google and Meta campaign structures against goals, budgets, and conversion data. Identify excessive segmentation, overlapping targeting, and fragmented budgets, then get consolidation recommendations, an explained account structure, and a migration plan.
Stage exploration before instruction on complex problems. The learner produces two attempted approaches before consolidation — which builds on those attempts, not from scratch. Use for genuinely hard problems where struggle produces deeper learning.
The English summary is being prepared. Showing the original description.
Stage exploration before instruction on complex problems. The learner produces two attempted approaches before consolidation — which builds on those attempts, not from scratch. Use for genuinely hard problems where struggle produces deeper learning.
The English summary is being prepared. Showing the original description.
Debt payoff strategy generator. Compares avalanche (highest interest first) vs snowball (smallest balance first) methods, calculates payoff timelines and total interest saved, and recommends optimal payment allocation across multiple debts. Includes credit card consolidation and refinancing analysis. Use when the user says "/finance debt", "pay off my debt", "snowball or avalanche", "consolidation", or asks for any debt strategy.
The English summary is being prepared. Showing the original description.
Drive the ENTIRE tdmcp roadmap-to-1.0 to completion as a resumable, wave-by-wave campaign — Milestone 4 (generative-AI bridge wave), Milestone 5 (mixer scene arming), and the v1.0 consolidation gates G1–G6 — routing each class of work to the right existing sub-harness. Use whenever the user wants to "implement everything / all the milestones / the whole roadmap / finish the road to 1.0", run the next milestone, close the consolidation gates, or build a long autonomous campaign across M4/M5/G1–G6. ALSO use for every follow-up: continue/resume the roadmap campaign, run the next wave, re-run a failed wave, fold in QA results, check campaign status, re-prioritize, or scope to one milestone/gate. This is the CAMPAIGN layer ABOVE tdmcp-pipeline / tdmcp-feature-lead / tdmcp-backlog-campaign — it sequences across MULTIPLE sub-harnesses (tools, mixer, coverage, docs, bridge, recipes, submission), which the generic backlog-campaign does not. For a SINGLE feature use tdmcp-pipeline; for one tool-shaped backlog file use tdmcp-backlog-campaign. Simple questions can be answered directly.
The English summary is being prepared. Showing the original description.
Evolve SKILL.md files from agent execution traces using a three-stage pipeline: trajectory collection from observed runs, parallel multi-agent patch proposal for error and success analysis, and conflict-free consolidation of overlapping edits via prevalence-weighting. Based on the Trace2Skill methodology.
The English summary is being prepared. Showing the original description.
Use when designing or refactoring record types across objects with many profiles, business processes, or picklist variations. Covers layout assignment explosion, Dynamic Forms migration, and record type ID portability. NOT for basic record type setup or page layout assignment — use admin/record-types-and-page-layouts. NOT for converting one page layout to Dynamic Forms — use admin/dynamic-forms-migration. Trigger keywords: record type consolidation, layout assignment matrix, recordTypeVisibilities, layoutAssignments, Master record type default, bulk RecordTypeId migration, record type audit, RecordType wildcard package.xml.
The English summary is being prepared. Showing the original description.
Data structures and algorithms for AI agent episodic memory. Covers vector stores (HNSW, IVF, PQ), temporal indexing, knowledge graphs with triple stores, hierarchical summarization, forgetting curves, working/long-term/ procedural memory, and memory consolidation. Deep analysis of MemGPT/Letta, Zep/Graphiti, Mem0, and the Stanford generative agents memory architecture. Teaches the CS fundamentals behind how agents remember, retrieve, and forget. Activate on: "agent memory", "episodic memory", "vector search algorithm", "HNSW", "memory retrieval", "forgetting curve", "knowledge graph memory", "MemGPT", "Letta", "Zep", "Mem0", "memory consolidation", "temporal retrieval", "agent long-term memory", "memory layer". NOT for: conversation protocol design (use agent-conversation-protocols), agent infrastructure selection (use agentic-infrastructure-2026), building RAG pipelines (use ai-engineer).
The English summary is being prepared. Showing the original description.
Expert-level geotechnical engineering covering soil classification, shear strength, consolidation, foundation design, slope stability, and retaining structures.
The English summary is being prepared. Showing the original description.
We need to answer the question: "Explain how sleep consolidation improves memory in biological and a
The English summary is being prepared. Showing the original description.
USE FOR: MCQ, 整併疑問書, 規格整併, 疑點裁決, consolidation-manifest, scan-answers, rewrite-all, doc-id-registry, 討論來源整併。當任務涉及 docs/遊戲規格文件/討論來源/ 內容歸納、衝突轉 MCQ、人工填答後批次回寫相關規格文件時啟用。強制流程: generate -> 人工填答 -> scan-answers -> rewrite-all。DO NOT USE FOR: UI 視覺調整、一般程式除錯、非規格文件任務。
The English summary is being prepared. Showing the original description.
Data structures and algorithms for AI agent episodic memory. Covers vector stores (HNSW, IVF, PQ), temporal indexing, knowledge graphs with triple stores, hierarchical summarization, forgetting curves, working/long-term/ procedural memory, and memory consolidation. Deep analysis of MemGPT/Letta, Zep/Graphiti, Mem0, and the Stanford generative agents memory architecture. Teaches the CS fundamentals behind how agents remember, retrieve, and forget. Activate on: "agent memory", "episodic memory", "vector search algorithm", "HNSW", "memory retrieval", "forgetting curve", "knowledge graph memory", "MemGPT", "Letta", "Zep", "Mem0", "memory consolidation", "temporal retrieval", "agent long-term memory", "memory layer". NOT for: conversation protocol design (use agent-conversation-protocols), agent infrastructure selection (use agentic-infrastructure-2026), building RAG pipelines (use ai-engineer).
The English summary is being prepared. Showing the original description.
Review Claude skills and commands for usefulness, overlapping content, and outdated technical references. Choose a scan of changed skills or a full review, then receive reasoned recommendations to keep, improve, update, retire, or merge them.
Audit a codebase for unnecessary complexity, including dead code, duplicated state, redundant interfaces, and obsolete compatibility paths. Receive evidence-backed simplification candidates, or authorize changes that remove justified targets and validate the behavior that must remain.