“jsonl”的搜索结果

Zero-dependency live-preview server providing an agent↔browser bidirectional companion. Watches a content directory, wraps HTML fragments in a frame template, broadcasts live-reload over WebSocket, and captures browser-side click events to a JSONL file. Use when an agent needs to show HTML to the user in a browser and react to clicks — mockups, design exploration, gallery browsing, multi-select choices, prototype iteration. Triggered by "live preview", "browser companion", "preview server", "browser mockup", "show in browser", "arkhe-preview", or any skill that wants to write HTML fragments and have the user see them reload in real time.

中文简介正在准备中。当前显示原文说明。

Use this when the user wants to generate, normalize, verify, deduplicate, or export training datasets for Codex, Antigravity, or Claude Code from topics, URLs, reference material, web research, or existing JSONL/CSV files. Supports SFT and DPO workflows, custom export schemas, and deterministic local pipeline scripts.

中文简介正在准备中。当前显示原文说明。

当您的律师协会来问"给我看看您是如何为 AI 辅助工作计费的"——而 ABA 512、佛罗里达 24-1、加利福尼亚、纽约和哥伦比亚特区都已发布意见——您需要一个经得起审查的工件。billable-time 就能产生它。 从您的 Claude Code 会话日志中，它起草可审查的计时条目，外加可打印的 HTML 审计包，包括：SHA-256 证据链（源文件 + matter.yml + 活动披露包 + 可验证工件自哈希）、律师身份和签名块、包含五个法域起始语言的律师协会意见披露包，以及由文件名和工具形态导出的、内容感知的确定性叙述——默认绝不来自提示文本。 该工具拒绝自行计费。--strict 模式在任何审计不变式失败（宽泛路径、缺少律师、缺失/未核验披露）时拒绝交付工件。提供 Node CLI 和自包含浏览器版本（无后端；JSONL 绝不离开页面）。15 个不变式测试验证该契约。AGPL-3.0。

中文简介正在准备中。当前显示原文说明。

Use when recording, tallying, or triaging stochastic review findings — the append-only JSONL ledger where Tier 2 (advisory, unevidenced) reviewer output goes instead of blocking language. Triggers on "log this finding", "ledger add", "tally the findings", "triage findings", "is this finding recurring", "retire this noise", or whenever a reviewer produces an unevidenced concern that should be measured for recurrence rather than chased. For the review itself see code-review-and-quality or skill-library-review; for verifying formal claims with deterministic evidence see adversarial-claims-reviewer.

中文简介正在准备中。当前显示原文说明。

Content-addressed baseline-archive epoch partitioning. Partition baseline_archive.jsonl + the self-improving hub's baseline serving by a HASH of the full baseline-production+measurement spec — when the spec (margin_rule, fitness/margin logic version, the 4 roles' model+source, rubric/dim-set, bench, seed-pool identity) changes, the hash changes → a new epoch series (like seed-gen gen-*). Triggered by "baseline epoch", "baseline 아카이빙", "epoch partition", "spec hash", "content-addressed", "margin_rule namespace", "production logic 구분", "baseline 하위 서빙" keywords.

中文简介正在准备中。当前显示原文说明。

复盘 v3（Workbench 门禁型）：启动本地 Workbench，用户在独立会话页确认想学的知识点和深度，按选择调研产出复盘文档； 同时落 2-3 条账本条目（记录/复盘/learnings.jsonl）供 bugfix/eng 开工回放与复发检测。 触发方式：用户说"总结知识"、"学习总结"、"复盘"、"可视化复盘"、"/forge-fupan"。

中文简介正在准备中。当前显示原文说明。

复盘 v3（Workbench 门禁型）：启动本地 Workbench，用户在独立会话页确认想学的知识点和深度，按选择调研产出复盘文档； 同时落 2-3 条账本条目（记录/复盘/learnings.jsonl）供 bugfix/eng 开工回放与复发检测。 触发方式：用户说"总结知识"、"学习总结"、"复盘"、"可视化复盘"、"/forge-fupan"。

中文简介正在准备中。当前显示原文说明。

Regenerate docs/THIRD-PARTY-NOTICES.md from provenance/borrows.jsonl after any ledger change — even a single new entry — never hand-edit the notices file

中文简介正在准备中。当前显示原文说明。

Comprehensive, measurement-driven performance optimization for latency, throughput, memory/GC, and tail behavior. Use when the user asks to optimize/speed up, reduce latency (p95/p99), increase throughput/QPS, lower CPU/memory/allocations/GC pauses, profile hot paths, or run a benchmarked perf pass (including JSONL/query-heavy code). Requires before/after measurement on a runnable workload (or an explicit `UNMEASURED` plan) plus a correctness gate.

中文简介正在准备中。当前显示原文说明。

How to MEASURE this repo instead of eyeballing it — interpret the loop-station context-budget trend (history.jsonl, thresholds, the tokenizer-switch gotcha), read a session trace, use the eval ledger (cost-per-success), and pick the right evidence tool (app-shots, smoke-deployed, db-counts, --check modes). Use when asked "is the harness bloating", "how big is CLAUDE.md really", "did this agent run actually succeed", "prove this works", "what evidence do we have", or when tempted to declare a capability (browser, tool) unavailable. For RUNNING the loop-station scripts, defer to the loop-station skill — this skill is interpretation + the wider evidence toolkit.

中文简介正在准备中。当前显示原文说明。

Analyze Codex provider rollout JSONL and ego-benchmark-harness run artifacts to identify slow or failed individual tasks, tool retries, token/cost anomalies, and differences in agent execution paths. Use when users ask to analyze a Codex session or rollout, explain why a Codex task was slow or failed, inspect a Codex provider execution trace, compare Codex runs, count function_call or tool output events, or investigate agent-home/.codex/sessions.

中文简介正在准备中。当前显示原文说明。

Export Codex rollout/session JSONL as a self-contained HTML report that can be opened offline. Use when a user provides a complete session file path or Codex session ID, or asks to export a Codex session to HTML, generate a session report, or convert a rollout to HTML. Supports exact full-ID lookup in the CODEX_HOME sessions and archived_sessions directories.

中文简介正在准备中。当前显示原文说明。

Plan and prepare an OpenAmer-specific fine-tune from the collected brain data: data curation, ChatML JSONL, training, evaluation. 'The organism becomes its own brain'.

中文简介正在准备中。当前显示原文说明。

Open-format data ingestion for NV oOS Pro toolkits — the reusable pattern behind the F&B data-ingestion track (Proposal 078). Covers structural (header) matching over filename mapping, the configurable table_map + header-matcher + name-guess resolution order and the slug-first regression, the multi-format loader (CSV/TSV/JSON/JSONL/XLSX/ODS/PDF/photo), the Observation + terminology-map layer (vitals/FHIR analogue) with raw preservation, dedupe/retention/out-of-band banding, complete-by-default/resumable (offset) imports, and the read-only ingest-review dashboard anatomy (edit_posts review vs manage_options write, dry-run-first). Use when adding or extending data ingestion to a toolkit, ingesting heterogeneous owner files, wiring XLSX/PDF/photo imports, building an ingest/review dashboard, or debugging partial/truncated imports.

中文简介正在准备中。当前显示原文说明。

Analyze graded `trial_result` JSONL outputs from the eval pipeline, including reliability and custom slicing.

中文简介正在准备中。当前显示原文说明。

Turns data/commitments.jsonl (flat list) into a who-owes-what-to-whom graph. Surfaces overdue chains and cross-PA dependencies that the flat list hides. Triggers: "what's overdue", "what did X promise", "commitment graph", "who's blocking whom".

中文简介正在准备中。当前显示原文说明。

Read the network instead of the DOM. Snoop JSON API responses, wait for a request instead of sleeping, collect items while scrolling, record a QA flight trace (jsonl, HAR, screenshots), and intercept requests with routes.

中文简介正在准备中。当前显示原文说明。

The default code-driven browser path for interactive browsing work: drives any browser from code with token-efficient a11y snapshots (57% smaller via compactSnapshot), ref-based clicks, coordinate control (CUA), viewport pinning, CAPTCHA solving (reCAPTCHA, Turnstile, hCaptcha, slider, OCR), Chrome MV3 APIs (tabs/bookmarks/history/downloads/topSites), network snoop (read API JSON instead of DOM), flight-recorder trace (jsonl + HAR + screenshots), OOPIF-aware snapshots, dialog policy, human handoff for login/OTP, device emulation, request routes, stealth via CloakBrowser as the default owned engine with zero exposed CDP ports, and an attached engine that drives the user's own signed-in browser through BrowserSkill (connectBrowserSkill, bskSnapshot, one-click onboarding via bskOnboard). MUST USE for interactive browser work: scraping, blocked/WAF/JS-rendered pages, logins, the user's logged-in sites and open tabs, extension popups, form filling, screenshots, web QA, CAPTCHAs. The ulw-research browsing lane runs on ultimate-browsing, not this skill.

中文简介正在准备中。当前显示原文说明。

Guide for dataset construction — SupervisedDatasetBuilder, RLDatasetBuilder, ChatDatasetBuilder, and custom dataset creation from JSONL, HuggingFace, or conversation data. Use when the user asks about datasets, data loading, data preparation, or custom data formats.

中文简介正在准备中。当前显示原文说明。

Export PostHog events, persons, or sessions on demand and download the resulting files. Use when the user asks to download/export raw PostHog data, create a one-off file export, fetch a Parquet or JSONLines export, or use the file_download_batch_exports API. Covers starting the export with MCP, polling completion, and downloading via the existing REST redirect endpoint.

中文简介正在准备中。当前显示原文说明。

Listens to a CARLA sensor and either saves its data to files, shows it live in a window, prints a one-shot summary, or (ros-info) reports the native ROS 2 topics, QoS and enabled-for-ROS state so you can echo it from ROS instead. Cameras save as PNG (depth/semantic auto-colourised) and display in a pygame window; lidar saves as .ply and shows as a top-down scatter; IMU/GNSS/radar/collision stream to JSONL or the console. Use when the user asks to "show/view the camera", "display the lidar", "save the sensor data / capture a dataset", or "what is this sensor reading". Select the sensor by id, type, or the actor it's attached to.

中文简介正在准备中。当前显示原文说明。

Edit EcoSIM PFT-parameter NetCDF files such as ecosim_pftpar_20260303.nc with the ParEditor class from applications/notebooks/scripts/ParamEditor.py. Use when asked to modify, scale, copy, compare, or delete PFT parameter records for a plant functional type (six-character pfts code such as gr3s43 or ndlf34), update microbe parameter NetCDF values, or maintain the JSONL change log that records past parameter changes. Never modify plant_trait.*.desc files; they are read-only references.

中文简介正在准备中。当前显示原文说明。

Inspect, rebuild, or verify the append-only SDD Composy semantic trace (events.jsonl) and its derived projection (trace.json). Use for 'o que aconteceu nessa task', 'histórico do fluxo', 'verificar o trace', 'rebuild the trace projection'. Do NOT use for a status overview (sdd-status), evidence manifests (sdd-evidence), or to edit trace history.

中文简介正在准备中。当前显示原文说明。

Enable, record, query, summarize, or verify the opt-in PWDEV Flow semantic audit trail. Use when the user asks what Flow actions occurred, wants audit integrity checked, or needs a portable JSONL record of workflow gates and artifacts.

中文简介正在准备中。当前显示原文说明。