「the」の検索結果

Run Claude Code INSIDE a ca-sandbox box (`--with-claude`). Routed to when the user wants an agent loop running against an isolated, ephemeral sandbox rather than the host. Authenticates via an env-injected CLAUDE_CODE_OAUTH_TOKEN with no host bind of ~/.claude; the image pins the CLI and disables the autoupdater; HOME is backed by a named volume so the .claude state persists across restart. Five gated phases — posture, image, token, run, teardown. The hard default is offline or Anthropic-domains-only egress, and the token volume is NEVER co-mounted with an untrusted-code run; both are enforced, not advised.

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。

Draws an activity flow / system architecture diagram as ONE self-contained, INTERACTIVE HTML+SVG page (2-pane app layout — left: diagram, default fit-to-view with zoom/pan; right: sidebar with explainer cards), styled like a real hand-drawn enterprise doc (Stripe/AWS-docs style — real brand logos for MongoDB/Odoo/n8n/etc. from a bundled Simple Icons library, neutral white boxes, sans-serif, no "AI neon" look), scroll-to-zoom, auto light/dark with a toggle button — clicking a flow (a legend chip, a line, or a step badge) highlights that flow with traveling dots along the arrows in their direction, a ping at the destination box, and a sidebar panel that slides out, while everything else dims; two-way arrows (OUT = solid blue / RETURN = dashed green) carry numbered step badges, colored by semantic meaning (red = auth checkpoint, purple = scheduled flow, amber = data pipeline), a small "hop" arc where two lines are forced to cross, dashed group regions, one explainer card per flow in the right sidebar. Use this skill ANY TIME the user wants to "draw a diagram", "draw a flow", "draw a system diagram", "redraw this so it's easier to follow", "interactive diagram", "two-way diagram", "request/response flow", "make a free-form HTML diagram" — even if they never say the word HTML. Especially good when both the request direction AND the response direction need to be shown, or when a templated tool (archify, mermaid) is too rigid. Do NOT use for data charts (bar/line/pie), and do not use when the user asks specifically for archify or mermaid.

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 open-ended requests into things to think WITH instead of answers to accept. Audits the hidden assumptions inside a topic, inverts them into sharp "what if" provocations, branches each one outward, and delivers a fully-expanded mind map image plus the written wonderings. Fire this when the person signals they want to open up a space and think alongside you — "wonder about X", "what are the weird angles on X", "help me think about what this could be", "I want to explore, not decide yet" — or when they invoke /wonder or /wonderpill. Do NOT fire when the same topic is attached to a request for concrete, usable, or decided output: a named deliverable, a count ("give me 5 names"), a deadline ("ideas I can ship this week"), or a "which / what should I pick" question — those want straight answers, not a wonder pill. When it is genuinely unclear which they want, this skill opens by asking one line rather than branching. Not for factual lookups or executing a plan already chosen.

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。

Find the papers that answer a research query in Firecrawl's research paper index — a corpus of paper abstracts whose largest share is biomedical and life-science literature (PubMed, bioRxiv, medRxiv), alongside arXiv preprints in CS, physics, and math — using semantic search, semantic and structural expansion, and in-body verification. Use this skill for literature-finding and paper-retrieval tasks of any kind, including clinical, biomedical, drug, gene, disease, and other life-science questions, whether the answer is a single paper or a full multi-paper set. The index is reached only through the `firecrawl_research_*` MCP tools or the `firecrawl research` CLI subcommands. Calling `firecrawl_search` with its `categories` option set to `["research"]` is a different feature — it filters ordinary web search to research-affiliated websites (the list includes PubMed, bioRxiv, medRxiv, arXiv, and publisher sites) and returns page results from them, without querying the paper records in this 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。

Allows you to view the user's screen as well as several hours of history. Use when the user makes a reference to their recent work, for which it'd be helpful to see the screen. This skill MUST be used whenever you need to resolve ambiguity in a user request, where the user hasn't specified enough context to do the task. Examples include disambiguating the specific user/app/document/error the user is referring to. You must also use this skill if the user asks about any question regarding Chronicle or asks what you can see from the screen.

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。

Find the papers that answer a research query in Firecrawl's research paper index — a corpus of paper abstracts whose largest share is biomedical and life-science literature (PubMed, bioRxiv, medRxiv), alongside arXiv preprints in CS, physics, and math — using semantic search, semantic and structural expansion, and in-body verification. Use this skill for literature-finding and paper-retrieval tasks of any kind, including clinical, biomedical, drug, gene, disease, and other life-science questions, whether the answer is a single paper or a full multi-paper set. The index is reached only through the `firecrawl_research_*` MCP tools or the `firecrawl research` CLI subcommands. Calling `firecrawl_search` with its `categories` option set to `["research"]` is a different feature — it filters ordinary web search to research-affiliated websites (the list includes PubMed, bioRxiv, medRxiv, arXiv, and publisher sites) and returns page results from them, without querying the paper records in this 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。

Learns how the user writes from their own sent messages and docs, and builds a voice profile so future drafts sound like them instead of generic AI. The profile is saved as the my-writing-style skill. Use when the user asks to set up, learn, or capture their writing voice, or complains that drafts sound generic or unlike them and no my-writing-style profile exists. Only for drafting text the user will send as themselves, not for Claude's own replies.

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 this skill before the first step that uses Claude in Chrome, the browser extension whose tools are named mcp__claude-in-chrome__* (also called Chrome, the browser extension, or the external browser) and which acts in the person's real Chrome with their own sign-ins; before those tools are turned on there may be a single enable__mcp__claude-in-chrome tool instead. It covers loading the tools in one ToolSearch call, checking the person's open tabs and working in a new tab, site permissions, GIF recordings, console logs, dialogs to avoid, and when to stop and ask. It is not for the built-in browser (mcp__Claude_Browser__* or mcp__remote-devices__Claude_Browser__* tools), which has its own skill, and it does not decide which browser to use.

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。

Authoritative reference and rules for developing for Obsidian — building TypeScript plugins (Plugin lifecycle, manifest.json, commands, settings, modals, views, ribbon/status bar), the Vault and Editor APIs, the event system, Markdown post-processing & code-block processors, CodeMirror 6 editor extensions, building CSS themes (CSS variables, theme.css/manifest), and submitting plugins/themes to the community directory. Use whenever the user asks to build, debug, or review an Obsidian plugin or theme, work with the Obsidian API (Vault/Editor/Workspace/Plugin), register commands/views/events, process Markdown, or release/submit to the Obsidian community.

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 the moment a request is underspecified and you are about to act on an ASSUMED goal. Enumerate the candidate goals the request could mean, project the action or artifact each one implies, and check whether they diverge: if two or more plausible goals lead to materially different actions or artifacts, ask exactly ONE targeted clarifying question; otherwise proceed on the most-likely goal and state the assumption in one line. Clarification is an evidence-producing action, not a delay — but one question, never an interrogation. Distinct from gsd-spec-phase (GSD-phase-bound, emits a heavy SPEC.md) and intent-router (fetch strategy, not goal disambiguation). Backed by agent goal-state inference (arxiv 2606.16813v1). Triggers on acting under an assumed goal when the request admits more than one materially different reading.

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 changed Anabasis v2 code for reuse, simplification, efficiency and altitude, then apply the fixes. Quality only: it hunts no bugs, which /code-review does. Starts from what the repository already finds (the lint plugins, the whole-tree census, the not-slop ledger), measures before and after with reduce-complexity's scripts, and holds a pass to its budgets and to the rules no pass trades. Use as /simplify on your own diff before a commit, or when the operator asks whether code is simple enough, why something exists, to go one layer higher, or to remove something and find another way.

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。

Activate Specification Know-How: load the SpecBook format contract, the SpecBook schema configuration of the project, and the list of specification (SPEC) artifacts into the context, so the specification can be read, queried, explained, and edited ad-hoc in plain conversation. Use *automatically* whenever the user wants to work with the specification files -- asks what the "spec" or "specification" says, wants to "look up", "query", "check", or "explain" specification content, or wants a small ad-hoc change to it -- and no dedicated specification skill (`ase-spec-edit`, `ase-sync-import`, `ase-sync-reconcile`, `ase-sync-export`) is invoked, as those activate the know-how implicitly.

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 writing, expanding, rewriting, or drafting any chapter (.mdx) or Go exercise for this book. Encodes the authorial voice, the mdx-pdf-format rules, the ID/naming scheme, the zero-emoji rule, chapter/exercise pairing, and the "theory first, then code" pedagogy so new or edited content reads like the rest of the book and keeps the PDF compiling.

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 more than one agent may need the same single-instance resource at the same time — most of all the local server loop, which holds the one URL (https://local.voxt.ai, port 7080) the app can run on. Also when you are about to dispatch several agents that will test the UI, when you find another agent already using the loop, or when the user says "coordinate", "shared resource", "queue for the server".

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。

Orchestrates the tdmcp Anthropic Connectors Directory (Desktop Extension / MCPB) submission prep — designs the package, writes the privacy page, migrates .dxt→.mcpb, drafts all form answers, and QAs the result. Use for ANY work on the tdmcp directory/marketplace submission, including re-runs after a rejection ("update the submission", "redo the form answers", "re-migrate the bundle", "fix the privacy page", "the directory rejected us"). Drives a 4-agent pipeline (architect → docs-author ∥ bundle-engineer → QA).

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。

Post-implementation QA planning — independent of /review (the developer chooses whether to run them sequentially or in parallel), only when the change has a running surface worth driving. Interviews the developer to turn the specs and the diff into an executable QA specification (specs/qa/QA-<N>-<slug>.md) that /execute-qa runs. The agent drives browser and shell; the human steps in only at named handoff points. Use only when the user asks to plan manual QA — never trigger 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。

Apply the Minimum Sufficient Language (MSL) principle through the MSL Kernel to write anything a reader must act on. Bind the reader and what they already know, partition facts from the machinery that produced them, emit each admitted fact as an action, a verification, a judgment, or a state, and stop when every claim is checkable and the reader can act. Use for status updates, work-in-progress reports to your own user, closeout and convergence comments, tickets, pull request and review write-ups, incident and postmortem notes, emails, memos, and any draft for readers outside the work. Also use when the user says MSL, Minimum Sufficient Language, write this for stakeholders, drop the jargon, make this readable, or asks for a paste-ready draft.

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 you need to know where a piece of reporting actually came from — the user gives an article URL and asks "where does this come from?", "who is the original source?", "is this just a rewrite?", or another skill needs the provenance chain before grading or citing a report. Follows an article's links and named attributions back to the originating vendor, government, victim or actor document and returns the chain, the primary's stated access and confidence language, publication dates, and every hop it could not resolve. Deterministic — a script or the Liberty91 platform resolves the chain; the model does not reconstruct it from memory. Invoked by /quality-of-information-check, /threat-actor-profiling, /campaign-tracking and /intelligence-writing. Works on any URL with no API key.

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。

Create a compact handoff note so a new chat/session can first acknowledge the current state before work resumes. Use when the user asks to close the current session, make a message for the next session, create/export a handoff, resume later, セッションを閉じる, 引き継ぎを作る, or 伝言を作る. Do not use for pasted handoff notes that instruct the current agent to resume work; consume those as instructions instead.

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.

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。

Audits whether a machine-readable regelrecht law model is faithful to the LETTER of the wettekst — and strictly separates the wettekst (leading) from the toelichting (Nota/Memorie van Toelichting; explanatory, not a norm). Runs in critical passes per article/lid and detects four deviation classes: toelichting-bleed (a modeled criterion that the letter only states as an open norm, or not at all), missing verbatim elements (a word/condition such as a "tenzij" or a qualifier dropped from the model), wrong legal_basis anchoring (an endpoint hung on a "kapstok"-article while the operative norm lives elsewhere), and verbatim-drift in text: (an ingetrokken/older redaction). Also detects positief-lid vs uitsluitings-lid conflicts and checks the chapeau for an explicit derogation rule ("zo nodig in afwijking van het eerste lid") before judging precedence. Classifies every finding as modelfout (fix), wettekst-gevolg (report, do not fix), or letter-vs-toelichting-question (jurist decides what is leading + revision signal). Use when the user wants to know if a model is "dicht bij de letter", mentions letter vs toelichting/bedoeling, fidelity, "natuurgetrouw", or before trusting feature outcomes.

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 a new standalone skill repo under gaia-research/ from the canonical template set at gaia-research/gaia-research/templates/skill-repo/. Handles the full flow: interactive prompts for all placeholders, fetches templates via the GitHub API, substitutes values, creates the new repo (gaia-research/skill-<name>), writes README.md / SKILL.md / install.sh / .gitignore / LICENSE / powered-by-gaia.svg, makes the initial commit and pushes. Also supports update mode: re-applies the template structure to a pre-existing skill repo and opens a draft PR with the drift. Use when the user says "new skill repo", "bootstrap a skill repo", "/skill-template", "create skill-foo", "spin up a gaia-research skill repo", "template a new skill", "align skill-fuse to the template", or "/skill-template update <repo>". Requires: gh CLI (authenticated with gaia-research org access), python3, git.

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 3 of the feature-pipeline suite. Use this after /fp-plan has received explicit user approval and printed the M2-plan stop hook — when you need to translate an approved numbered plan into committed, pushed code. Triggers on: "implement the plan", "start coding", "commit the plan", "write the code", "fp-implement", "Phase 3", "plan is approved let's code", "next step after plan", "execute the plan", "apply the plan", "make the changes". Reads planApproved and branch from state; refuses to run if approval hasn't been recorded. Commits one atomic change per plan step, pushes after each commit, handles obstacles cleanly, and hands off to /fp-review when done. Never squashes or skips steps — the one-commit-per-step rule keeps the review history readable and rollback surgical.

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 1 of the feature-pipeline suite — stress-test a CLI command, feature, flag, or module as a developer seeing it for the first time, then file GitHub issues for every distinct finding. Use when someone says "explore X", "test X", "find issues with X", "what's wrong with X", or after /feature-pipeline init. Also triggers standalone as /fp-explore <feature> when you want just the exploration phase without the full pipeline. Reads the target feature from .fp-state.json (or the argument if provided). Completes in one bounded turn and prints the M1 stop hook so the user decides whether to continue to /fp-plan.

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。