「memory」の検索結果

Build and adopt production AI agent infrastructure in 2026. Covers framework selection (LangGraph, CrewAI, AutoGen, MCP), orchestration patterns, evaluation, observability, memory systems, and tool use. Also covers the SOCIAL dimension: how to sell agent infrastructure internally, change management, measuring ROI, building trust in autonomous systems, and scaling adoption across teams. Activate on: "agent infrastructure", "agent framework comparison", "which agent framework", "sell AI tools internally", "agent adoption", "agent observability", "agent evaluation", "MCP architecture", "agentic mesh", "enterprise AI agents", "AI change management", "agent ROI". NOT for: building specific agents (use ai-engineer), designing agent behavior patterns (use agentic-patterns), prompt tuning (use prompt-engineer).

日本語の概要は準備中です。原文の説明を表示しています。

Safety, privacy, cost management, and frank advice for building always-on AI agents with episodic memory. Covers data hygiene, privacy risk surfaces, runaway cost prevention, scope creep, psychological effects of persistent AI companions, and responsible deployment patterns. This is the skill that tells you what can go wrong and how to prevent it. Activate on: "agent safety", "always-on agent privacy", "agent cost control", "persistent agent risks", "AI companion safety", "agent data hygiene", "runaway agent costs", "parasocial AI risk", "/always-on-agent-safety". NOT for: architecture design (use always-on-agent-architecture), input design (use always-on-agent-inputs), application brainstorming (use always-on-agent-applications), healthcare compliance specifically (use hipaa-compliance).

日本語の概要は準備中です。原文の説明を表示しています。

Align preprocessed CLIP-seq reads (eCLIP, iCLIP, iCLIP2, PAR-CLIP) to genome with STAR or bowtie2 using crosslink-preserving parameters, choosing between unique-mapper-only and multi-mapper-aware alignment for repeat-binding RBPs, deciding STAR vs HISAT2 memory trade-offs, and applying ENCODE-compatible filters. Use when turning preprocessed CLIP FASTQ into a deduplicated, MAPQ-filtered BAM ready for peak calling or crosslink-site detection.

日本語の概要は準備中です。原文の説明を表示しています。

Process many sequence files in batch (count, merge, split, convert, summarize) with memory-safe streaming and on-disk indexing using Biopython, pysam, or pyfastx. Use when iterating over a directory of FASTA/FASTQ files, merging or splitting datasets, building random access across many or huge files, or automating per-file operations without exhausting RAM.

日本語の概要は準備中です。原文の説明を表示しています。

Report the health of the central system spec at `docs/system/` across seven checks — coverage gaps, stale elements, dangling anchors, duplicate anchors, orphan shards, unillustrated elements, and shards missing their kind annotation. Report-first and read-only: it repairs nothing until a human confirms a specific item. Use when the corpus has drifted, after a merge that touched `docs/system/`, or from `/archive` Step 5.5 in report-only mode. Requires `memory.architecture_map.enabled`.

日本語の概要は準備中です。原文の説明を表示しています。

Dev-only review of user-facing CLI interface copy in `src/cli/tui/*.js`, `src/cli/*.js` error paths, and `bin/cli.js` help/usage text. Surfaces three failure modes — copy/behavior mismatch, jargon, missing next-action — as a punch list the maintainer addresses before `/grant-commit`. Read-only; no writes to source. Conditionally seeded by `/triage` between `/memory-sync` and `/grant-commit` when the request will touch CLI surfaces.

日本語の概要は準備中です。原文の説明を表示しています。

Phase 10.6 — sync the project's execution roadmap (project.json → roadmap.path, default docs/roadmap-execution-plan.md) to the just-landed work. Flips the tasks named in workflow.json → roadmap_tasks[] from ⬜ to ✅ and promotes their epic headings ⬜→🟡→✅, preserving the standup parser format contract. On the epic track it appends instead — the epic's heading plus one row per slice — and stamps roadmap_epic back into the epic state. Also hosts the ad-hoc backfill that puts every epic already on disk onto the roadmap. Fail-open: never throws, no-ops when roadmap.path is unset/absent or no task matches, and never blocks a commit. Runs after /archive and before /memory-sync on every committing track.

日本語の概要は準備中です。原文の説明を表示しています。

Cycle-end retrospective converting recurring judgment failures into durable enforcement. Reviews the cycle's friction — repeated user corrections, guard trips, RCA themes, integrate failures — and turns each recurring one into a landmines.md entry, then proposes graduation candidates up the enforcement funnel (landmine → advisory hook → hard gate). Pairs with standup: standup says what shipped and what's next; retrospective says what kept going wrong and how to stop it structurally. Writes only memory entries and a report — graduation proposals are advisory and require the normal seed.md amendment path to become enforcement. Invoke at the end of a release cycle, an epic, or any stretch of work with repeated friction.

日本語の概要は準備中です。原文の説明を表示しています。

Capture what someone actually said without contaminating it with your own inference. Invoke when eliciting intent in conversation (design discussion, requirement interview, decision surfacing) and when turning a conversation into a durable record (ADR, decision node, memory entry, spec `## Decisions` row). Enforces quote-before-critique, keeps illustration separate from commitment, and holds interpretation subordinate to verbatim. Prevents the failure where unspecified space is filled by the recorder and then evaluated as if the speaker had specified it.

日本語の概要は準備中です。原文の説明を表示しています。

Bootstrap the central system spec at `docs/system/` for a repository that has never had one. Scans the governed surface, proposes a concept map clustered by directory, and materializes elements + shards ONLY after a human confirms that map. Use when adopting the baseline on an existing project, or when the corpus needs re-deriving from scratch. Re-runnable. Requires `memory.architecture_map.enabled` and a declared `governed_surface`.

日本語の概要は準備中です。原文の説明を表示しています。

Workflow track for tasks that need no TDD — documentation edits, governance count bumps, vendored-skill content updates, configuration tweaks, formatting, typo fixes, dependency bumps where no project code changes. Skips `/scenario` and `/implement` (no failing test to drive) and runs the work directly. `archive`, `memory-sync`, `/grant-commit`, and `/commit` remain mandatory. `verify`, `simplify`, `integrate`, and `document` are conditional — required when the diff hits one of the listed triggers, optional otherwise. `verify` is skipped only when the diff is pure-docs/prose AND `project.json → test.kind` is `behavior` (absent/invalid `test.kind` → `structural` → verify runs). Chore is a stripped-down pipeline, not a bypass; never silently skip a conditional phase whose triggers apply.

日本語の概要は準備中です。原文の説明を表示しています。

Propose the next dependency-ready sprint from the ALREADY-DECOMPOSED roadmap — standup's active sibling. Reads docs/roadmap-execution-plan.md + the memory backlog, computes per-task readiness from the roadmap's machine-readable status, orders with roadmap-planner's graph engine, and emits a proposed task-set (sprint-plan manifest shape) with per-feature done-criteria, excluding unready tasks and naming their unmet prerequisite. PROPOSES ONLY — the human confirms/edits before /triage routes it (typically to the `power` track). Distinct from `sprint-plan`, which decomposes a fresh vision.

日本語の概要は準備中です。原文の説明を表示しています。

A workflow skill that lets Codex keep coding for 60 hours on medium and large projects: Claude Code CLI plans through an interactive requirements questionnaire, PRD, specs, and roadmap; Codex implements verified vertical slices, with resumable Long-Run Execution for lengthy work; Trellis maintains project memory. Use when the user mentions 大项目工作流, Codex 连续开发 60 小时, Codex 长任务, long-running or resumable Codex implementation, large/medium project, new SaaS, multi-module system, requirements questionnaire, Claude Code CLI planning, Codex implementation handoff, Trellis bootstrap, non-system-drive project, or vertical slice. Skip for: single-file edits, casual Q&A, copy polish, throwaway prototypes, or tasks the user explicitly wants done fast without process.

日本語の概要は準備中です。原文の説明を表示しています。

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.

日本語の概要は準備中です。原文の説明を表示しています。

Turns a plan phase into a PhaseSpec v1 and dispatches it to a specialist subagent via the Agent tool. Subagent reads files itself, returns a structured result, the result is logged into progress.md. Markdown is the shared state; no in-memory shared store across agents.

日本語の概要は準備中です。原文の説明を表示しています。

Makes sessions durable across `/clear`, machine reboots, and IDE switches. SessionStart catchup pulls scratch + last MemPalace recall + planning files into context. Stop promotion writes a handoff note and runs memory-keeper. Manual `/mddesign:handoff` re-runs either at any time.

日本語の概要は準備中です。原文の説明を表示しています。

Generate production-ready manga pages, chapter pages, covers, and panel sequences with strict recurring-character consistency. Use this when the user asks for a manga page, manga scene, chapter page, comic page, storyboard page, or character-consistent page generation. Before generating any page, inspect `img-memory`, create missing character sprites/reference sheets, make those images visible to image generation, then generate the final manga page.

日本語の概要は準備中です。原文の説明を表示しています。

Claude Code workflow tips from Boris Cherny (creator of Claude Code) and the Claude Code team. Use when: setting up Claude Code, optimizing workflows, running parallel sessions, configuring CLAUDE.md, using skills/commands, subagents, hooks, MCP integrations, or learning best practices. Covers: git worktrees, plan mode, verification, permissions, Slack MCP, BigQuery, prompting tips, plugins, custom agents, sandboxing, keybindings, status lines, output styles, customization, /simplify for code quality, /batch for parallel code migrations, /loop for scheduled tasks, code review agents, /btw for mid-task questions, /effort max reasoning, remote control sessions, voice mode, setup scripts, session naming, /color, PostCompact hook, auto mode, /schedule cloud jobs, iMessage plugin, auto-memory, and auto-dream, mobile app, session teleporting, Cowork Dispatch, Chrome extension, Desktop app, /branch forking, --bare SDK startup, --add-dir multi-repo, --agent custom agents, /voice input.

日本語の概要は準備中です。原文の説明を表示しています。

Codex workflow tips from Boris Cherny (creator of Codex) and the Codex team. Use when: setting up Codex, optimizing workflows, running parallel sessions, configuring AGENTS.md, using skills/commands, subagents, hooks, MCP integrations, or learning best practices. Covers: git worktrees, plan mode, verification, permissions, Slack MCP, BigQuery, prompting tips, plugins, custom agents, sandboxing, keybindings, status lines, output styles, customization, /simplify for code quality, /batch for parallel code migrations, /loop for scheduled tasks, code review agents, /btw for mid-task questions, /effort max reasoning, remote control sessions, voice mode, setup scripts, session naming, /color, PostCompact hook, auto mode, /schedule cloud jobs, iMessage plugin, auto-memory, and auto-dream, mobile app, session teleporting, Cowork Dispatch, Chrome extension, Desktop app, /branch forking, --bare SDK startup, --add-dir multi-repo, --agent custom agents, /voice input.

日本語の概要は準備中です。原文の説明を表示しています。

Archive merged feature specs into project memory with provenance, sweep discovery, and gated cleanup

日本語の概要は準備中です。原文の説明を表示しています。

Read the project's knowledge record before answering from memory or from the files. Use before answering about the project's state, a number, a date, a decision, a source, a deadline or what was agreed - even a casual 'what's the situation with X' or 'is that quote still current'; before changing a recorded value; and whenever the opener or a grounding line names entries. After finding relevant IDs, prefer kpop context to read them with their declared dependencies and checks. Uses pull for concise readings or when the checked reader is unavailable, affects for changed inputs, and search when no ID is known. A missing id is not absence. Not for showing the record's page (the hub skill). Requests come in any language.

日本語の概要は準備中です。原文の説明を表示しています。

Build AI agents with Hugging Face's SmolAgents framework. Use when creating code-executing agents, tool-calling agents, multi-agent systems, agentic RAG, text-to-SQL pipelines, web browsing agents, or any multi-step AI workflows. Covers CodeAgent, ToolCallingAgent, custom tools, MCP integration, memory management, secure code execution (E2B, Docker, Blaxel), and model configuration (HF Inference, LiteLLM, Transformers, Ollama).

日本語の概要は準備中です。原文の説明を表示しています。

Build AI agents with LangChain framework. Use when building agents, tools, memory, MCP integrations, RAG pipelines, multi-agent systems, or any LLM-powered applications using LangChain or LangGraph in Python or TypeScript.

日本語の概要は準備中です。原文の説明を表示しています。

Measure real frontend performance — Core Web Vitals (LCP, CLS, INP), page-load traces, CPU and network throttling, Lighthouse accessibility/SEO scores, and heap growth — using chrome-devtools-mcp against a live browser. Trigger when asked "is the page fast enough", "measure Core Web Vitals", "why is this route slow", "run Lighthouse", "check for a memory leak", before any performance-gated certification (Built for Shopify, Core Web Vitals thresholds, store listing review), and before any launch or traffic-multiplier event. Measurement only — this skill never drives functional journeys.

日本語の概要は準備中です。原文の説明を表示しています。