3,508 件 ・ 関連度順
概要と使いどころ
Agent Tool Builder workflow skill. Use this skill when the user needs Tools are how AI agents interact with the world. A well-designed and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
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。
Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe (evaluator-as-selector, stop on regression). Routes on measured cost-per-completed-task rather than per-token price, because a tier's token count varies more by task shape than price varies across tiers. Covers per-model effort semantics, the concision lever, cascade preconditions, context handoff, and watching a subagent fan-out live. Use when choosing a subagent's model or effort, when choosing how to escalate a failed attempt, or when asked which model or effort a task should get. Grounded in a 2026-07 calibration, a 2026-08 coding-cost study, a 2026-09 seeded-bug repair battery, a 2026-10 Haiku 5.5 ladder priced per spawn, and a 2026-10 retry-versus-escalation ladder on 295 SWE-bench Verified tasks; Managed Agents API specifics are operational, not calibrated.
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。
Use when reading or writing persistent game variables in a @drincs/pixi-vn game — simple flags/counters via `storage`, custom persisted classes via `StoredClassModel`, temporary (label-scoped) variables, and how any of this survives save/load and history go-back. Load this before writing any `storage.set`/`storage.get`/`storage.flags.set` code or a class that extends `StoredClassModel`.
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。
Show whether each skill is earning its context-window cost — combined tokens-used view sorted by waste. Use when the user asks 'are my skills worth it', 'what's my context budget', 'which skills are dead weight', or wants to audit skill value, token cost, or usage. Trigger with '/janitor-value'.
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。
Use when the user wants to save knowledge as a file so others don't have to rediscover it — "turn this into a doc", "write this up", "document how X works", "we figured this out and want to capture it", "nobody should have to figure this out again". Covers any request to create or update durable written artifacts: onboarding guides, runbooks, ADRs, API docs, architecture notes, postmortems, changelogs, setup guides. The trigger: user wants knowledge captured in a file for future reference, not just a conversation. Do NOT use when still making decisions (→ give-plan), just asking for explanation without a file (→ ask), or writing code (→ cook).
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。
Author or improve a Skill (an executable, reusable capability with a ``SKILL.md`` plus optional ``scripts/``, ``references/``, and assets). Trigger this skill whenever the user wants to: - Capture a workflow they keep repeating into a fresh Skill - Polish an existing Skill's prompt, description, or examples - Tighten when-to-trigger wording so the model invokes the Skill more reliably - Discuss the Skill format, frontmatter, or how progressive disclosure works Do not wait for the user to say "skill-creator" verbatim — phrases like "turn this into a skill", "let's make a reusable thing for this", "improve my skill", or "tweak the description for this skill" should all reach this skill.
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。
Customer segmentation model builder — tiers customers by ARR, health, and expansion potential; defines CS motion per tier; maps resource allocation. Use when asked to "segment our customers", "define our CS tiers", "how should we allocate CS resources", "build a customer segmentation model", or "who gets high-touch vs. digital".
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。
Sort, hide, show, reorder, resize, pin, format, and color-code columns in a Datagrok TableView grid via the datagrok_exec tool. Use whenever the user asks to sort by a column (any direction), multi-sort, hide / show / reorder / pin / resize columns, freeze the first N columns, change number-format display, color-code cells (defaults and grid-only tint here; full per-type reference in datagrok-df-and-columns), set row height, or reset the grid back to defaults. Distinct from datagrok-df-and-columns (which owns column-level data metadata like semType, units, friendlyName, and is also where canonical color-coding lives) and from datagrok-viewers (which owns scatter plot / histogram / etc.). Does NOT cover filtering (`datagrok-filtering`), selection (`datagrok-selection`), custom cell renderer authoring (`create-cell-renderer`), saving / restoring layouts, or grid event handlers.
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。
Schools of historical thought, methodology debates, and the philosophy of history. Covers the major historiographical traditions (Annales, Marxist, feminist, postcolonial, subaltern, world-systems), their methodological commitments, their contributions and limitations, and the enduring debates about objectivity, narrative, and the nature of historical knowledge. Use when evaluating how different historians approach the same subject, understanding why historical interpretations change over time, or assessing the theoretical framework underlying a historical argument.
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。
Audit a MaaFramework/Maa-series project's Git history to learn how Pipeline JSON, interface options, Python AgentServer CustomAction code, and related data tables evolved. Use when asked to review a Maa project from initial commit through a target commit, map `action: Custom` pipeline nodes to `@AgentServer.custom_action(...)` implementations, find pipeline/custom/option patterns or breakages, and produce a report plus skill-improvement recommendations.
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。
Use whenever the user wants to find, shortlist, vet, or enrich US AI/ML/data consulting firms (consultancies) — AI/ML development, MLOps, generative AI / LLM apps (RAG, chatbots, agents), computer vision, NLP, recommendation systems, data engineering, BI/analytics. Triggers on "find an AI/ML consulting firm to build our recommendation engine", "shortlist three RAG/LLM consultancies for an enterprise chatbot", "compare three AI/ML consulting firms with strong ratings", or "pull contact info for these 8 AI consultancy domains", even when described indirectly (we want to use AI for X, deploy ML to production). Drives the ServiceGraph API (api.servicegraph.co) — a 100k+ US firm catalog filterable by industry, services, location, size, ratings. Defer to find-software-developer for general app/backend work where AI is just a feature. Skip in-house ML/data hires, LLM/AI-tool comparisons (ChatGPT vs Claude), "how do I fine-tune X" DIY questions, AI courses for individuals, non-US firms, individual freelancers.
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。
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for SSRF reachability, internal route probing, metadata-service access, credential pivoting, and token-to-accepted-privilege chains. Use when the user asks to trace SSRF sources, internal hosts, metadata endpoints, link-local tokens, service-account credentials, or explain how a server-side fetch edge turns into accepted access. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
日本語の概要は準備中です。原文の説明を表示しています。
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for browser cookies, localStorage, sessionStorage, IndexedDB, Cache Storage, service workers, offline caches, and client-side session persistence. Use when the user asks to inspect browser state, replay cached auth or session behavior, explain why a page behaves differently after load, or trace how stored client state changes requests, rendering, or access. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
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。
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for cloud metadata services, instance identity, workload identity, link-local credential paths, role assumption, and metadata-to-privilege trust edges. Use when the user asks to inspect metadata-service access, instance credentials, pod or workload identity, link-local token paths, SSRF-to-metadata escalation, or explain how metadata-derived credentials turn into accepted cloud or control-plane privilege. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
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。
Implement comprehensive model drift monitoring using Evidently AI, statistical tests (PSI, KS), and custom metrics to detect data drift and concept drift in production ML systems. Set up automated alerting and reporting workflows to catch degradation before it impacts business metrics. Use when production models show unexplained performance degradation, when new data distributions differ from training data, when seasonal shifts affect input features, or when regulatory requirements mandate model monitoring.
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。
Fix RFDB V2 graph data silently not persisting to disk after analysis. Use when: (1) rfdb-server reports "0 nodes, 0 edges" on restart despite successful analysis, (2) segment directories exist but are empty (no .bin files), (3) manifest_index.json shows total_nodes: 0 despite analysis logging 70k+ nodes, (4) Docker builds produce empty graph databases, (5) --clear flag used before analyze command. Root cause: GraphEngineV2::clear() replaces the store with MultiShardStore::ephemeral() which has path: None, causing all flush operations to write to in-memory buffers only.
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。
Define or extract a consistent brand voice that other skills can use. Three modes: Extract (analyze existing content), Build (interview-based), Auto-Scrape (from URL). Use when copy sounds generic, when starting any new project, when voice feels inconsistent across channels, when onboarding a new brand, or when any skill needs voice-profile.md but it doesn't exist yet. This is always the first skill to run for a new project. Make sure to use this skill whenever the user mentions tone of voice, brand personality, 'my copy all sounds the same', 'how should I sound', 'analyze my website voice', 'define my tone', or anything about making content sound more human or distinctive. Even if the user just says 'my marketing sounds generic' — that's a voice problem.
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。
"Calculate safety stock levels to buffer against demand and lead time uncertainty. Use this skill when the user needs to set inventory buffers, determine service level trade-offs, or optimize safety stock across SKUs — even if they say 'how much buffer inventory', 'stockout prevention', or 'service level calculation'.".
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。
Audit and repair Gaia user-tree timelines so every skill's current rank is explained by a chain of Hero's Journey events. Trigger this skill when: a contributor's profile chart shows a stale rank (e.g. still shows 3★ after a demotion to 1★); someone asks to "trace what happened" to a skill's rank; `validate_timelines.py` is failing in CI; you need to backfill missing `demote` or `rank_up` events before cutting a release; a skill was reclassified or Star-Bar-reset and the user tree was never updated; or any time the registry node and user tree disagree on a skill's current level. Uses `scripts/trace_timeline.py` (dry-run + apply) and `scripts/validate_timelines.py` (CI gate). Do NOT hand-edit `timeline[]` arrays — the script synthesises properly labelled events with `previousValue`/`newValue` so the rank chart plots correctly.
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。
Downloads a competitor's live ad creatives — the actual MP4s and JPEGs — from the Meta Ad Library into a local swipe folder, through the Novoads API. One sweep per competitor, priced by a live estimate before anything is charged, media pulled the moment the response lands because the CDN links expire, and every ad carried with its permanent Ad Library URL, the page running it, and how many audiences the creative is running against, closing with the three most established and why. Use when asked to spy on competitors, find what ads a brand is running, pull a competitor's video or static creatives, build or refresh a swipe file, check who is outspending you on Meta, or source a reference ad to recreate. It finds, ranks and files ads; it does not rebuild them — a static becomes your own ads, or a reusable template, via clone-image-ad. It writes no craft analysis and no creative brief. A sweep that finds nothing is a result, never an apology.
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。
Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.
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。
Query and answer questions about Volcengine API specifications. Use when the user asks about API parameters, error codes, request methods, enum values, required fields, response structures, pagination, parameter dependencies, service capability lists, API availability, or API comparisons, even if they do not explicitly say "API". Typical intent includes checking what an action supports, which fields are required, what values a parameter accepts, why an API returns a specific error, how to pass nested or body parameters, how pagination works, what an API response contains, whether a batch operation exists, what services or versions expose an operation, or how two APIs differ. Use API Explorer data as the authoritative source and preserve constraints, examples, and caveats found in the spec. Answer in Chinese or English. When the user needs runnable SDK code, language-specific examples, or SDK configuration, hand off to volcengine-sdk-generator. When they need CLI operations, hand off to volcengine-cli.
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。
Use when admins are governing the Chatter group lifecycle — creation policy, public/private/unlisted visibility decisions, group ownership transfer when owners leave, archived vs inactive vs deleted state changes, auto-archive behavior, naming conventions, group templates (Information Templates), and orphan-group cleanup after user terminations. Triggers: 'we have 800 dead chatter groups', 'group owner left the company who owns it now', 'should this group be public private or unlisted', 'when does a chatter group auto-archive', 'how do I delete vs archive a chatter group', 'we need a chatter group naming convention'. NOT for Chatter notification / digest / feed-noise tuning (use admin/chatter-notification-tuning), NOT for Chatter REST API integration patterns (use apex/apex-connect-api-chatter), NOT for Custom Notifications API (use apex/apex-custom-notifications-from-apex), NOT for Experience Cloud / Customer Community group access (different sharing model).
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。
Understand what SKMTC is, how its engine works, and the architectural invariants — for agents building or extending infrastructure *around* SKMTC rather than authoring generators or running the CLI. Covers the three-phase pipeline, the host/Worker boundary, cross-generator coordination, the manifest, the attribution / gen-maps (provenance) subsystem, the package graph, the dependency substrate, and the design decisions that make SKMTC behave unlike a typical codegen tool. Use this skill when the user asks "what is SKMTC", "how does the SKMTC engine work", "explain the SKMTC architecture", or is building platform infrastructure around SKMTC — a hosted generate API, a schema or generator registry, tracing or provenance tooling, a web app or SaaS that wraps the engine, or platform-level CI integration. This skill is the system mental model. It does NOT cover authoring generators (→ skmtc-generator), running CLI commands (→ skmtc-cli), or diagnosing broken runs (→ skmtc-debug).
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。