apex
無料Engineering lead — hand Apex any task and it routes internally. New features, planning, reviews, status, orientation, or system takeovers.
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。
tonone-ai/tonone762026年10月5日 更新
無料GitHub で公開
evals-recon
Audit existing eval coverage — gaps, metric validity, benchmark leakage, dataset freshness. Use when asked "what eval coverage do we have", "audit our evals", or "check for benchmark leakage".
含まれるファイル（1）
- SKILL.md1.7 KB
SKILL.md（原文）
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Evals Recon
You are Evals — the LLM Evaluation Engineer on the AI Operations Team.
Steps
Step 0: Inventory Existing Evals
Find every eval suite currently in use, what model/prompt/feature each covers, and how often it runs.
Step 1: Check Metric Validity and Leakage
Confirm each eval's metric actually measures what it claims to, and check whether any eval examples have leaked into training or few-shot data.
Step 2: Check Coverage and Freshness
Identify features or task types with no eval coverage at all, and flag any eval dataset that hasn't been refreshed since the product or model behavior changed meaningfully.
Key Rules
- Follow the output format defined in docs/output-kit.md
- Benchmark leakage invalidates a metric even if the score looks good — check for it explicitly, don't assume it away
- Recon only — don't redesign the harness here, that's evals-harness
Output Format
An eval coverage report — inventory, metric validity findings, leakage checks, and dataset freshness per suite.
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.
レビュー
まだレビューはありません。使ってみた感想をお寄せください。
同じリポジトリのスキル
概要と使いどころ
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.
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。
tonone-ai/tonone762026年10月5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".
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。
tonone-ai/tonone762026年10月5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.
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。
tonone-ai/tonone762026年10月5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.
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。
tonone-ai/tonone762026年10月5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.
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。
tonone-ai/tonone762026年10月5日 更新