AGENT SKILL

jsonl-agg

Aggregate records_*.jsonl in the workspace into aggregates.json

License 许可
MIT
所属仓库
ZJU-REAL/ageval
最近更新
2026-11-14
Stars
★ 81
Forks
3

01 前言 Front Matter

name
jsonl-agg
description
Aggregate records_*.jsonl in the workspace into aggregates.json

03 SKILL.md 正文

jsonl-agg

Read every records_*.jsonl file in the current working directory. Do not invent numbers. Write aggregates.json in the cwd with exactly:

{
  "top_5_users_by_amount": {
    "<user>": {"total_amount": <float rounded to 2 decimals>, "total_items": <int>}
  },
  "top_5_tags_by_count": {
    "<tag>": {"count": <int>}
  }
}
  • Sum amount and items per user. Keep top 5 users by total_amount descending. Ties: higher total_items, then user name ascending.
  • Count tag occurrences across all tags arrays. Keep top 5 tags by count descending. Ties: tag name ascending.
  • After the file is written, reply with the same JSON object or {"status":"completed"}.

04 同仓库更多 Skills

ZJU-REAL
ZJU-REAL/ageval

echo

暂无简介

★ 81
ZJU-REAL
ZJU-REAL/ageval

verify-ageval

Verify ageval by driving the public CLI: doctor, a lock that rejects a bad profile, and one minimal-demo task on local plus openai-http against the in-repo loopback gateway. Use when checking lock/run, seal invariants, or whether a credential skip was reported honestly. Triggers: verify ageval, loopback gateway, AGEVAL_SKIP_REAL_ACP, not run.

★ 81
ZJU-REAL
ZJU-REAL/ageval

eval-ops-pitfalls

Pre-run environment checks and suite troubleshooting: dead proxies, invocation timeouts, package mirrors, model routing, environment_image_unresolved, widespread failures, evaluator dependencies, permissions, and CLI/schema mismatches. Use when preparing an evaluation run or diagnosing acp_timeout, HTTP_PROXY, AGEVAL_AGENT_INVOKE_TIMEOUT, AGEVAL_APT_MIRROR, PEP668, or test collection failures.

★ 81
ZJU-REAL
ZJU-REAL/ageval

ageval-sdk-harness

Write dataset run.py with ageval_sdk (RunContext, Agent/AgentSession, ToolSet, RunTerminal, publish). Use for task run.py, sessions, tool guards, optional evaluator.py LLM-as-judge. Triggers: AgentSession, RunTerminal, ScriptError, ctx.publish_json, write run.py, evaluator.py. SDK never decides PASS or holds host credentials.

★ 81
ZJU-REAL
ZJU-REAL/ageval

ageval-plugin

Author ageval.plugin/1: exclusive and chain slots, registry resolve, environment or executor implementations, image_layers bake. Use for plugin.yaml, attach_stdio hosts, trajectory_collect, README capability and parameter tables. Not an app store. Never invent slots.

★ 81
ZJU-REAL
ZJU-REAL/ageval

ageval-platform

ageval platform map: authority (docs/design vs ARCHITECTURE vs Issues), Core vs dataset ownership, red lines (no secrets, mechanism-named adapters), evidence grades, which sibling skill to load. Use when entering the repo, asking "what is ageval", "who owns PASS", "read order", or "evidence grade". Not a substitute for docs/design.

★ 81