跳到主要内容
知仓学习社ZHICANG

history-explorer

Query the per-turn DecisionEntry log for skill co-occurrence patterns, meta-skill usage stats, and the router fixture corpus. Returns a JSON summary…

读凭据严重 0 · 高危 4TokenRhythm/opensquilla

它会碰到什么

扫了多少2 个文本文件,9 KB
它会碰到什么读凭据
命中总数4 处
命中统计严重 0 · 高 4 · 中 0 · 低 0
逐条看命中(4 条严重或高危)
  • scripts/explore.py:39cred-envread
    home = os.environ.get("HOME") or os.environ.get("USERPROFILE")
  • scripts/explore.py:39cred-envread
    home = os.environ.get("HOME") or os.environ.get("USERPROFILE")
  • scripts/explore.py:61cred-envread
    env_log = os.environ.get("OPENSQUILLA_LOG_DIR")
  • scripts/explore.py:64cred-envread
    env_state = os.environ.get("OPENSQUILLA_STATE_DIR")

这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。

技能内容

History Explorer

Lightweight read-only view over ~/.opensquilla/logs/decisions-*.jsonl. Aggregates DecisionEntry.skills_invoked (SCHEMA_VERSION 10) into co-occurrence frequencies, joins with SkillLoader.list_meta_specs() for meta-skill usage stats, and surfaces the tests/test_skills/router_fixtures/ corpus.

Usage

uv run python {baseDir}/scripts/explore.py \
  --log-dir ~/.opensquilla/logs \
  --query "Co-occurring chains for PDF workflows" \
  --window-days 30 \
  --include co_occurrences,meta_usage,router_fixtures \
  --top-k 10

Output

JSON to stdout with keys co_occurrences, meta_usage, router_fixtures, and a placeholder string when the log is empty.

Fallback

If no decision-log exists, return an empty result with a placeholder string explaining "no history; downstream should rely on user intent only".

想直接用这个技能?

本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。

它属于哪个仓库

星标★ 7,018
本站分层T1
该仓技能数68
原文件路径src/opensquilla/skills/bundled/history-explorer/SKILL.md

同一个仓库里的其他技能

看这个仓库的全部 68 个技能