4.5万 件 ・ 関連度順
概要と使いどころ
Guides work on the Grida file format (.grida) from the TS side: the I/O packages that read/write it (loading, archive packing, clipboard) and the frozen schema bindings. Use when working with .grida files in the editor or packages, or debugging format round-trip issues. (The schema and the Rust decoder live in the engine repo.)
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。
Establish what is actually true and current for the surface you are about to change — not just search. Grounding = locate the authoritative source and reconcile sources that disagree (code vs doc, migration vs schema, memory vs current code, live vs archived), not take the first hit. Use before any grep/find/explore of the codebase or docs, when deciding which of several definitions is the real one, or when a doc or memory conflicts with the code. Covers the source-of-truth hierarchy, reconciliation discipline, scoped ripgrep, and the docs/tags.yml + docsearch.py index.
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。
Guided journey from a business with lucky months to a repeatable growth engine that produces a forecast. Orchestrates nine skills phase by phase - one-page-marketing, hundred-million-offers, predictable-revenue, contagious, influence-psychology, crossing-the-chasm, cold-start-problem, lean-analytics, negotiation - asking the user questions at every decision point and recording results in the project docs/ folder (MARKETING.md, OFFER.md, METRICS.md, GROW-BUSINESS-PLAN.md) so the journey resumes across sessions. Use when the user wants to build a marketing and sales system, manufacture predictable pipeline, engineer word-of-mouth and referrals, or says 'revenue is real but lumpy and I need growth that repeats'. If the offer, retention, or operations underneath are broken, run improve-business first; with no paying customers yet, start with create-business; when the product itself must carry the growth loops, use grow-app. For one framework in isolation, invoke that skill directly.
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。
Guided journey from a stalled, plateaued business to one with an honest diagnosis, a working operating rhythm, and offers repriced to real value. Orchestrates eight skills phase by phase - good-strategy-bad-strategy, traction-eos, high-output-management, team-topologies, drive-motivation, lean-analytics, negotiation, monetizing-innovation - asking the user questions at every decision point and recording results in the project docs/ folder (STRATEGY.md, OPERATIONS.md, METRICS.md, IMPROVE-BUSINESS-PLAN.md) so the journey resumes across sessions. Use when the user wants to fix a business that has plateaued, diagnose why growth stalled, tighten strategy and execution, re-motivate a team, or says 'revenue is flat and I do not know why'. Starting from scratch with no customers: use create-business. Once the fundamentals work and the goal is expansion: use grow-business. When the product itself drags the business down: use improve-app. For one framework in isolation, invoke that skill directly.
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。
Guided journey from an app people sign up for and then quietly abandon to a sealed retention engine with a habit loop, an activated first run, and one metric the whole team trusts. Orchestrates eight skills phase by phase - hooked-ux, improve-retention, continuous-discovery, lean-ux, inspired-product, lean-analytics, microinteractions, drive-motivation - asking the user questions at every decision point and recording results in the project docs/ folder (PRODUCT.md, METRICS.md, GROW-APP-PLAN.md) so the journey resumes across sessions. Use when the user wants to lift activation and retention, design a habit loop, fix a leaky onboarding funnel, or says 'users sign up then disappear'. Do not use to fix broken UX or performance that no engagement mechanic can paper over - run improve-app first; if there is no app yet, use create-app. For one framework in isolation, invoke that skill directly.
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。
Train and run models on Tinker (Thinking Machines) — LoRA and full fine-tuning, SFT with correct loss masking, RL/RFT with group-relative advantages and importance sampling, agentic RL over multi-turn tool-using agents, inference via the SamplingClient or the OpenAI-compatible endpoint, checkpoint management and export, every hyperparameter, and cost estimation from the live price table. Use this skill whenever the user mentions Tinker, tinker://, TINKER_API_KEY, console.tinker.ai, or the tinker CLI; wants to fine-tune, SFT, RFT, or RL a model on Tinker; asks about Tinker models, context windows, LoRA rank, sampling params, loss functions (cross_entropy, importance_sampling, ppo, cispo, dro), Datum construction, forward_backward or optim_step; wants to sample from, download, resume, merge, or export a Tinker checkpoint; or asks what a Tinker run will cost. Whenever Tinker work is initialized in a project, this skill also creates a TINKER_PRICING.md there so prices sit next to the training code. Reach for it even on vague asks like "train a model on this data" or "get inference working" when Tinker is the platform in play.
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。
The machine has to stay one machine while the camera does all the work. Lock the vehicle part by part, then fill the runtime with a numbered cut list that moves the camera every second. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Cars and vehicles at speed; 中文触发词: 汽车与载具速度片, 汽车, 赛车, 摩托, 载具), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
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。
Finds out whether a problem is real and a solution would work, before building it — recruiting the right people, interviewing without leading them, separating what users say from what they do, naming the riskiest assumption and testing that one first, and reaching a decision rather than a summary. Use this to validate a problem, test an idea cheaply, decide whether to build something, or fix a discovery process that keeps confirming what the team already believed.
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。
Concentrates marketing and sales effort on a named set of accounts rather than on volume — qualifying whether the model fits your economics at all, building the account list and the buying group inside each, tiering effort against account value, coordinating so the account experiences one campaign rather than several, and measuring account progression instead of leads. Use this to decide whether to run an account-based program, build one, or work out why an existing one produces activity and no pipeline.
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。
Design or build a page, screen, landing page, website, app or UI from a request - the whole job, end to end. Use this for "design a landing page", "build a settings screen", "make me a website", "design the onboarding", "ออกแบบหน้าเว็บ", "ทำหน้า landing", "ออกแบบ UI", "ทำแอป". It runs the pipeline no single skill covers: the house doctrine, a written Brief Inference so the result is not the statistical mean, a committed visual direction, tokens, build, the objective gates, then an adversarial critic. Hands off to data-dashboard for dense data screens, redesign for existing UI, and image-to-code when a reference image is given.
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。
The house rules for ANY design or UI work - the verification protocol (run the gate, never claim a number), the absolute no-emoji rule, token by intent, one shared theme, the eight states, one thing leads, and output completeness. Load this FIRST whenever building, reviewing, or theming a screen, component, or token set. Installed as a plugin, this skill carries what CLAUDE.md carries in the repo.
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。
Review a change to the ffmpeg-skill repository for the failures its own contract makes possible — a claim in a result document that is true at one layer and false at the layer a caller reads, a new flag that reaches the code but not the contract/docs/demo surfaces, a "bug" that docs/design-decisions.md already decided with a pinning test, a fix with no regression test, a new runtime dependency or a raw ffmpeg shell call that breaks the scope boundary, a SKILL.md line added without one trimmed, a review that re-derives findings from a summary instead of the tree at the reviewed commit. Use when asked to review a PR or diff in this repository, when authoring code here and needing a pre-commit check, or when triaging an external review or audit report about this codebase.
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。
Make the build step a real gate on what you actually distribute — build scripts that warn and exit 0 on a missing input, size checks with only an upper bound, hand-maintained file lists that drift from the entrypoints they must cover, committed bundles that go stale when only the source changes, GNU-only shell in release scripts that aborts on the other OS, and verification that runs against the source tree instead of the artifact. Use when writing or reviewing a build/package script, a `dist/` copy step, a release workflow that uploads a zip or installer, or a committed compiled asset.
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。
Writing plays and screenplays in the Chekhovian mode (契诃夫戏剧法) — distilled from the complete plays (没有父亲的人/普拉东诺夫, 伊凡诺夫, 林妖→万尼亚舅舅, 海鸥, 三姊妹, 樱桃园, nine one-acts) plus Chekhov's own letters, Stanislavsky's and Nemirovich-Danchenko's rehearsal notes and 焦菊隐/童道明 criticism. Covers the four-act mood-based structure without central climax, off-stage events, "correct answer stated in Act 1 and refused", the announced event that never happens, three-layer endings (hope monologue + nihilist line + household action), no-villain conflict with environment, every character's object and catchphrase, one-way love chains, half-step-off dialogue, philosophy cut by thirst, the shortest words for the deepest pain, stage-direction and sound discipline, and how Chekhov revised The Wood Demon into Uncle Vanya. Use when the user wants an ensemble drama, a "nothing happens" play, subtext-heavy dialogue, a family estate / provincial story, an anti-climactic structure, or asks how to "Chekhov-ize" a script.
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。
Continue a multi-phase engineering spec from its progress table. Use when the user says /continue-spec, "continue the spec", "continue the operations feature", or asks what the next phase is. Runs the next step (plan, implement, review) in this session on the model the spec names, stopping at the spec's gates. Never uses subagents.
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。
Assemble a submission-ready replication package to the AEA Data and Code Availability Standard (DCAS) / openICPSR / Social Science Reproduction Platform expectations — standard replication README, dataset manifest, computational-requirements capture, a Table/Figure → script:line map, and a confidential-data deposit plan. Use when user says "build the replication package", "prepare the openICPSR deposit", "make the AEA data and code package", "DCAS compliance", "assemble the deposit for the journal", or after a paper is accepted and the journal's data editor needs the package. NOT a numeric verifier — it calls /audit-reproducibility to confirm claims reproduce before packaging.
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 the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user asks structural questions about the codebase — "what calls X?", "what does Y import?", "where is Z defined?", "what's the architecture / which subsystems exist?", "what's the impact of changing this?". The graph is an AST-derived map of the repo, queried as files (no build needed — it rebuilds automatically).
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。
Answer a construction request for information so the site can act on it — a direct answer, the drawing or specification reference that supports it, and an explicit statement of whether it changes cost or programme. Use when asked to respond to an RFI, answer a contractor query, or handle a request for information on site, or when RFIs keep coming back for clarification. Produces the answer with its reference, the cost and time implication stated, the instruction status, the distribution list, and the register entry.
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。
Write a product listing for an overseas marketplace or store, localised for the buyer rather than translated from Chinese: title, bullet points, description, search terms and the compliance claims that must or must not appear. Use when asked 帮我写亚马逊 listing, 跨境电商标题, write a product listing for Amazon, TikTok Shop, Shopee, Lazada, Etsy or Shopify, or localise my listing for the US, UK, Germany or Japan. Produces the listing in the target language within the platform's field limits, a keyword map, a compliance check of every claim, and a list of images the listing needs.
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 everything an outgoing club secretary, chair, or organizer carries in their head before they disappear — accounts and logins with owners, the annual rhythm calendar, key relationships and their quirks, the unwritten rules, and the first-90-days guide for the successor. Use when a committee member is stepping down, when someone says 'it all lives in Linda's head', or right after elections. Produces a complete handover pack plus the one-hour handover meeting agenda.
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。
Prepare a promotion defence (晋升答辩) for a level-based promotion process common at Chinese technology companies: the materials, the presentation structure, the evidence for the next level, and a rehearsal of the committee's questions. Use when asked 帮我准备晋升答辩, 晋升述职, 晋升 PPT, how do I prepare for my promotion committee, or 答辩问题. Produces a level-gap analysis against the target level's criteria, the defence presentation outline in Chinese, a timed talk track, and a question bank with answer points, then a mock committee round.
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。
Set up a repo or project so an AI coding agent works well in it — the CLAUDE.md, the context, the guardrails, and the conventions the agent needs to be useful instead of lost. Use when asked how do I set up CLAUDE.md, configure my repo for Claude Code, my AI agent keeps getting my project wrong, or onboard an AI agent to my codebase. Produces a structured CLAUDE.md/project-context file (architecture, conventions, commands, do-nots), the right level of detail (enough to orient, not a novel), the guardrails that keep the agent safe (what not to touch, how to test), and a maintenance habit so it stays current — turning a repo an agent flails in into one it navigates like a teammate.
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。
Decode an insurance claim denial letter — what the cited reason actually means, whether it's commonly overturnable, and the appeal letter that answers it point by point. Use when someone asks 'my insurance claim was denied what do I do', 'decode this denial letter', 'can I appeal this denial', or 'write my insurance appeal'. Produces the denial decode with overturn-likelihood framing, the evidence checklist, the point-by-point appeal letter, and the escalation ladder past the insurer.
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。
Write a human changelog from the REAL commit history — read the actual commit range via the GitHub connector, not a template. Use when asked to write the changelog for this release, what changed since the last tag, draft release notes from my commits, or summarise this range for users in Cowork. Reads commits/PRs between two refs via the GitHub connector, groups them into user-facing changes (features / fixes / breaking), translates commit-speak into human benefit, and produces a changelog artifact ready for the release.
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。