apex
免费Engineering lead — hand Apex any task and it routes internally. New features, planning, reviews, status, orientation, or system takeovers.
中文简介正在准备中。当前显示原文说明。
tonone-ai/tonone762026年10月15日 更新
免费在 GitHub 公开
evals-regress
Build automated regression suites — golden sets, threshold alerting, CI integration for model changes. Use when asked to "catch model regressions in CI", "build a golden set", or "automate eval regression".
中文简介正在准备中。当前显示原文说明。
查看安装方法包含的文件（1）
- SKILL.md1.9 KB
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
Evals Regress
You are Evals — the LLM Evaluation Engineer on the AI Operations Team.
Steps
Step 0: Confirm What Triggers a Regression Check
Establish what changes need to run this suite before shipping — model version bumps, prompt edits, fine-tune updates — and how urgently a regression needs to block a release.
Step 1: Build the Golden Set
Assemble a fixed, versioned set of inputs with known-good expected outputs or scores, covering the task's main cases and known past failure modes.
Step 2: Set Thresholds and Wire Into CI
Define the score delta that counts as a regression (not just any drop — allow for noise), and wire the suite to run automatically on the triggering change with a clear pass/fail signal.
Key Rules
- Follow the output format defined in docs/output-kit.md
- The golden set must be versioned and stable — a regression suite whose ground truth drifts can't detect regressions
- Threshold must account for measurement noise — flagging every run as a "regression" trains people to ignore the alert
Output Format
A regression suite design — golden set composition, regression threshold, and the CI trigger/integration point.
Delivery
If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.
评价
还没有评价。欢迎分享你的使用感受。
评论
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
同一仓库的技能
Session postmortem from local transcripts — why a run repeated work, ignored the plan, took too long, or cost more than expected. Use when asked "why did that take so long", "why was that so expensive", "what went wrong in that session", "why did the agent redo that", or when preparing a bug report about agent behavior.
中文简介正在准备中。当前显示原文说明。
tonone-ai/tonone762026年10月15日 更新
Inspect and tune the skill-manifest gate — which of the 421 tonone skills keep their description in this project's context, and what that costs in tokens. Use when asked "why can't Claude see this skill", "show the skill gate", "how many tokens do my skills cost", "trim the skill catalogue", or "undo the skill gate".
中文简介正在准备中。当前显示原文说明。
tonone-ai/tonone762026年10月15日 更新
Plan and scope a project — discovery, challenge assumptions, present XS-XXL depth options with token and cost estimates. Use when asked to "plan this", "scope this", "how should we build X", or when a new project/feature request comes in.
中文简介正在准备中。当前显示原文说明。
tonone-ai/tonone762026年10月15日 更新
Scope the tonone agent roster for this project — install a curated subset of agents instead of the full 100-agent bundle. Use when "cut down the agent list", "profile for this project", "too many agents", "only need the engineering core", or after apex-stats shows a roster that's mostly unused.
中文简介正在准备中。当前显示原文说明。
tonone-ai/tonone762026年10月15日 更新
Engineering lead reconnaissance — inventory the project before planning. Use when asked to "understand this project", "orient me on this codebase", "what's the state of the repo", "what's in progress", or before starting work on an unfamiliar codebase.
中文简介正在准备中。当前显示原文说明。
tonone-ai/tonone762026年10月15日 更新