「sam」の検索結果

How to reach a user's CONNECTED COMPUTER (their laptop, desktop, or server) from a Kortix session — read/write files, run shell commands, and drive the desktop (click/type/screenshot) on that machine. A connected computer is an ACCOUNT of the project's `computer` connector, called through the same `kortix connectors` path as every other connector, with `--account` picking the machine. Load this when the task is about acting ON a specific physical computer the user has connected ("on my laptop…", "read ~/Downloads on my machine", "run this on my desktop", "click the button on my screen"), or when the user asks how the agent reaches their computer. ALSO load it when the user mentions their own machine or its files and no computer may be connected yet ("my local files", "my Desktop", a path like `~/…`, `/Users/…`, "the repo on my laptop") — this sandbox cannot see their disk, and the skill says how to tell them to connect it. For files INSIDE this sandbox, use normal shell/fs — not this.

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。

Route code, repository, and data/SQL work to isolated Kortix sessions instead of burning your main context on it. Use when asked to implement a feature, fix a bug, make failing tests pass, work a ticket/issue, refactor, navigate or change a codebase, ship a PR, review a pull request, or run SQL/warehouse analysis against a dataset — and when the user wants two agents or parallel reviewers/investigators on the same work. Covers the explore-vs-session routing call, deciding where the code lives (this project's repo vs cloning an external GitHub repo) or where the data lives, finding the repo with gh, spawning sessions in parallel, dual PR reviews, and reporting results back. Triggers: 'implement', 'fix the bug', 'make the tests pass', 'work this ticket', 'refactor this', 'open a PR', 'review this PR', 'run two agents on it', 'query the warehouse', 'analyze this dataset'.

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。

Monthly close runbook: how to walk {{close_sheet}}'s checklist, reconcile Stripe revenue against the recorded ledger, judge a missing supporting document, and spot an anomaly against prior months. Load this before touching a single checklist line so every item is judged to the same standard and only genuine open items reach a human.

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。

Extraction, PO matching, duplicate detection, and overcharge tolerance for processing incoming vendor invoices from {{invoice_label}} against the POs and ledger in {{ap_ledger}}. Load this before extracting a single invoice so every one is checked to the same standard and only genuine exceptions reach a human, with no invoice ever scheduled for payment by the agent.

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。

PUA Shot — compact all-in-one PUA reference for explicit injection into sub-agents or short sessions. Strong flavor, same evidence-first behavior.

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。

Put your AI on a Performance Improvement Plan. Forces exhaustive problem-solving with Western big-tech performance culture rhetoric and structured debugging. Trigger when: (1) task failed 2+ times or stuck tweaking same approach; (2) about to say 'I cannot', suggest manual work, or blame environment without verifying; (3) being passive—not searching, not reading source, just waiting; (4) user frustration: 'try harder', 'stop giving up', 'figure it out', 'again???', or similar. Also for complex debugging, env issues, config/deployment failures. All task types: code, config, research, writing, deployment, infra, API. Do NOT trigger on first-attempt failures or when a known fix is executing.

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。

Evaluates an ML GPU cluster for a cloud trial or acceptance test: environment dump, isolated newest PyTorch, matmul FLOPS (MAMF/MSMF) on every GPU while the others compute, intra-node all-reduce bandwidth and per-call latency of every collective, the same inter-node on every node you were given (omit those sections if there is only one node), fio on local disk and shared FS, dated markdown report. Use when the user asks to evaluate a cluster, kick the tires on trial nodes, run cluster acceptance, or measure GPU/network/storage. Canonical copy: https://github.com/stas00/ml-engineering/blob/master/skills/evaluate-cluster/SKILL.md

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。

Divergent ideation and corpus expansion via Verbalized Sampling plus extended thinking — single-shot generates several internally diverse candidates and surfaces the strongest, or expands a seed corpus into a diverse dataset for evals and test sets. USE WHEN be creative, brainstorm, divergent ideas, creative solutions, maximum creativity, tree of thoughts, radically different, name this, creative angle, expand this corpus, synthetic data, generate diverse examples, create test set. NOT FOR multi-cycle evolutionary ideation with Lamarckian meta-learning (use Ideate).

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。

Structured multi-angle exploration running 2-8 sequential passes over the same problem, each through a different scientific lens, to surface hidden requirements and edge cases invisible from one angle; each pass yields new ISC criteria. USE WHEN iterative depth, explore deeper, multi-angle analysis, surface hidden requirements, blind spot check, what am I missing. NOT FOR scope/zoom analysis (use ApertureOscillation).

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。

Discover WHICH new skills you should create, from your own work history plus your satisfaction/frustration signals. Read-only and proposal-only: it surfaces recurring pain that no existing skill, loop, or workflow covers, then hands you a ranked shortlist to build with CreateSkill. It never creates or edits a skill itself. Frustration is a first-class signal (a topic can look 'covered' while you keep hitting the same wall inside it), so it reads low ratings and recurrence markers, not just session topics. USE WHEN should I create a skill, what skills do I need, suggest skills, skill gap, based on my recent work, am I missing a skill, what should I build. NOT FOR creating/validating/testing/optimizing an individual skill (use CreateSkill) — this only decides WHAT to build, not how.

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。

OpenTelemetry-backed tracing, structured logs, metrics with rollups, alerts, sampling, and baggage for the engine — emit and query telemetry through `engine::*` functions and react to logs with a `log` trigger.

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。

Augment a Wren project with business context that DB schema cannot carry — enum value meanings, units (USD vs cents, ms vs sec), NULL semantics, magic sentinels (-1 = unknown), soft-delete default filters, business synonyms, time-grain / TZ conventions, cross-system identifiers, currency rules, canonical-table preferences, AND named aggregation metrics (ARR, churn, DAU, WAU, NRR) proposed as cubes. Runs in one of two modes selected at session start: `grill` (one question at a time, user-driven) or `auto-pilot` (agent infers and applies, escalates only on conflicts and high-blast-radius additions like new cubes / views / relationships). Reads everything under <project>/raw/ (PDFs, glossaries, handbooks, code, data dictionaries) and optionally samples low-cardinality columns from the live DB (grill mode), compares against the current MDL / cubes / knowledge (rules + NL→SQL pairs), then fills gaps via the ten-category gap catalog and the cube proposal flow. Confirmed findings are written back to the right sink. Use when: user says 'enrich context', 'augment my project', 'grill me on this project', 'auto-fill my context', 'agent doesn't understand our docs / enum values / units / null meanings', 'business context is missing', 'what does status=A mean', 'is this amount in USD or cents', 'we keep getting wrong aggregations', 'add cubes for ARR / DAU / churn', 'we have a handbook / glossary / data dictionary the agent should know'; or after generating an MDL and noticing the agent lacks business semantics.

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。

Privileged applier that LANDS meta-optimize / corpus-audit patches the user approved, with a fresh landing review and human approval. Base Codex review is same-family provisional. Use when the user says "meta apply", "/meta-apply", "land the staged patches", "应用优化", after a /meta-optimize run.

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。

Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via fresh-agent Codex GPT-6-Astra ultra review, fixes each gap with full derivations, re-reviews, and generates an audit report. Base review is same-family provisional. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.

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 a working artifact from a plain "implement X for me" request: a running end-to-end spine first, then one feature per rung, with every under-determined decision written to an assumption ledger BEFORE the code that depends on it and a sweep for the ones that slipped through undeclared (same-family provisional in the base Codex mirror). Use when user says "给我实现", "implement X", "帮我做一个能跑的", "先搭个原型再加功能", "build this feature", "prototype then extend", or hands over a capability description rather than an experiment 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。

Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh Codex reviewer with no prior context; base output is same-family provisional. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.

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 experiment integrity before claiming results. Uses fresh-agent GPT-6-Astra review (same-family provisional in the base Codex mirror) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.

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 and merge duplicate Linear issues — group reports of the same underlying bug, pick the survivor, and move the evidence across. Use when the backlog has grown noisy, someone asks whether an issue is already reported, or you are cleaning up before planning.

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 a brief for an upcoming meeting from Circleback — the calendar event, the history with the same people and company, open commitments on both sides, and what is still unresolved. Use when the user asks to prep for a call, "what do I need to know before", who someone is, or where things stand with a customer or partner.

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。

Runs a route through ScenarioRunner's RouteScenario mode (--route / --route-id) with an autonomous agent driving the ego — the same mechanism the CARLA Leaderboard uses, and the only way to reach the ~34 route-only scenario classes (Accident, ParkedObstacle, HazardAtSideLane, InvadingTurn, HardBreakRoute, YieldToEmergencyVehicle, junction and actor-flow scenarios). Inspects route files, lists route ids and their scenarios, and runs one or all of them. Use when the user asks to "run a route", "drive a route with my agent", "run leaderboard scenarios without the leaderboard", or names a route-only scenario type.

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。

Writes a new Scenic scenario (.scenic) from a natural-language description — "a car cuts in from the right lane", "a pedestrian crosses in front of the ego", "negotiate an unsignalized four-way" — by turning the request into a spec, generating the file from idioms proven on this build, and validating it by compiling and sampling before any simulator is involved. Use when the user asks to "write a Scenic scenario", "create a .scenic file", "turn this description into Scenic", "generate a scenario from text", or wants a Scenic scenario authored or repaired.

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。

Installs Scenic, the probabilistic scenario description language, for the CARLA in use — pip installing it into the same interpreter that holds the CARLA client, optionally cloning the upstream repo for the example scenarios the wheel does not ship, and verifying that the `scenic` CLI, the client and Scenic's version-keyed blueprint table all agree. Use when the user asks to "install Scenic", "set up Scenic", "download Scenic", "pip install scenic", wants to run `.scenic` files, or has a Scenic whose model import or blueprint lookup fails.

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。

Visualises and validates a map's pedestrian navigation mesh by sampling walkable locations (get_random_location_from_navigation) and drawing them as debug points. Use when the user asks to "show/visualise the pedestrian navmesh", "check walkable areas", "validate pedestrian navigation after a map import", or "why won't my walkers move". Confirms the navmesh loaded and how far it covers.

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。

Runs standard-format scenarios through ScenarioRunner — ASAM OpenSCENARIO 1.x (.xosc, via --openscenario, with catalogs and ParameterDeclaration overrides) and OpenSCENARIO 2.0 (.osc, via --openscenario2, the ANTLR/osc2 pipeline). Validates a file against the schema before running, lists the bundled examples, and reports which OSC features ScenarioRunner actually implements. Use when the user asks to "run an xosc", "run an OpenSCENARIO file", "use the OpenSCENARIO standard", "run a .osc / OSC2 scenario", or hands over a scenario file from another tool.

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。