「harness」の検索結果

Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs).

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。

Retune a skill corpus for a new model, measurement-first: mine the run archive for a baseline, establish a noise floor, audit the corpus adversarially, then cut in measured passes until a pre-registered bar clears. Requires a benchmark harness that can A/B two builds of the corpus; refuses without one.

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。

How to read, write, and curate project memory in `memory/` — the project brain. Load this skill whenever you (or the harness-reflector agent) need to add, update, or reorganize what this project knows about itself. Defines the rubric for what belongs in memory, the file structure, and the change-request flow for landing memory edits on `main`.

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。

Improve LifeOS from what the best practitioners are shipping around AI harnesses — Anthropic first (changelogs, docs, releases), then trusted creators, trending repos, and the system's own reflections — extracting concrete techniques and filtering them against verified current state so nothing already-done or rejected is re-recommended. USE WHEN upgrade, system upgrade, check Anthropic, new Claude features, algorithm upgrade, LifeOS upgrade, mine reflections.

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。

Persistent world-model harness that stress-tests ideas, strategies, and investments against 11 time horizons from 6 months to 50 years, each a deep analysis of geopolitics, tech, economics, society, and security, in Fast/Standard/Deep tiers. USE WHEN threat model, world model, test idea, future analysis, time horizon, stress test against future, long-term risk. NOT FOR single-shot idea attack (use RedTeam).

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。

Drives cmux as an agent cockpit to boot, race, and monitor visible agent teams. Mac-only. USE WHEN cmux, agent cockpit, boot an agent team, orchestrate agents, three-tier orchestration, agent race, needle-in-haystack hotfix, agent fleet, 2x2 fleet, watch/monitor my agents, scale compute to scale impact, send a prompt to a running agent, multiplexer, terminal cockpit, orchestrator lead worker. NOT FOR one-shot in-harness subagents with no terminal to watch (use Agent/Workflow), the Pulse dashboard itself (cmux feeds it, use Pulse), browser deploy-verification (use Interceptor), or Linux/Windows (cmux is Mac-only — use tmux).

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。

This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal task briefs that define terms and an exact success predicate linguistically, enumerate non-counting outcomes, set persistence rules with explicit stop and return conditions and effort floors, manage a diverse portfolio of parallel approaches with an approach registry and blocked-route bookkeeping, and gate the return on adversarial audit. Route agent topology and coordination protocols to multi-agent-patterns, runtime control surfaces and loop governance to harness-engineering, evaluator and quality-gate construction to evaluation, judge design to advanced-evaluation, and compaction or memory mechanics to context-compression and memory-systems.

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。

A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, evaluating, or debugging agent systems that require effective context management and reliable operating loops.

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。

Launch and supervise OpenShell gator agents. Use when starting gator on issues or PRs, checking gator sandboxes, building the gator sandbox image, restarting stuck gators, inspecting gator logs, or experimenting with gator harness/model overrides. Trigger keywords - launch gator, start gator, run gator, gator sandbox, supervised gator, gator logs, restart gator.

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。

This skill should be used when the user asks to "merge a PR", "review and merge pull requests", "integrate external contributions", "handle PR conflicts", "cherry-pick from a PR", or needs to merge GitHub PRs while maximizing contributor attribution.

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 LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

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 users /learn, save, remember, or distill lessons.

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。

生成 Ian 风格的中文正文配图。用于用户要求为中文文章、帖子、博客、Notion 文档、工作流文档、方法论、流程、结构、状态、隐喻或观点生成“怪诞”“小黑”“手绘”“正文配图”“文章插图”“配图建议”“shot list”“去标题/改图”等任务；默认使用小黑 IP、纯白手绘、少量红橙蓝批注、简洁清爽但天马行空的视觉风格。

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。

Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task (monthly trends, recent activity).

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。

Your capability catalog — read this at boot. Lists the temporal date-range skills and the external integrations (reached via the loopback broker) available to you as a spawned worker, and exactly how to call each. Read-only. Consult it whenever you're unsure what tools/integrations you have or how to invoke them.

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。

Resolve "thisYear" to a concrete ISO date range relative to your run time — this year so far (Jan 1 → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a year-to-date task (YTD metrics, "so far this year").

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。

Resolve "lastWeek" to a concrete ISO date range relative to your run time — the previous full week (Mon → Sun). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a task over the last complete week (weekly digests, week-over-week).

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。

Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively suggest at the start of a new task if you haven't checked your hive inbox in this conversation. (munder-difflin)

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。

Resolve "lastMonth" to a concrete ISO date range relative to your run time — the previous full calendar month. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a task over last month (monthly reports, month-end summaries).

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。

Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity, weekly standups).

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。

Resolve "thisMonth" to a concrete ISO date range relative to your run time — this month so far (1st → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a month-to-date task (MTD metrics, "so far this month").

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-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this codebase". (munder-difflin)

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。

Resolve "yesterday" to a concrete ISO date range relative to your run time — yesterday. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a task scoped to yesterday (daily reports, "what changed yesterday").

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。

Resolve ANY named time window — today, yesterday, thisWeek, lastWeek, last7Days, last30Days, last90Days, thisMonth, lastMonth, thisQuarter, lastQuarter, thisYear, lastYear, last12Months — or an arbitrary range (lastNdays / lastNweeks / lastNmonths) to a concrete ISO date range relative to your run time. Read-only: no writes, no network. Use whenever a task is time-scoped and you need exact start/end dates without computing them by hand.

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。