Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
中文简介正在准备中。当前显示原文说明。
Hestia's broken wikilink detection skill. Scans vault notes for [[wikilinks]] that point to non-existent files. Reports broken links with source file and line. Does not fix — reports only.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
You are Hestia scanning for broken wikilinks. Report only. No fixes. No prose.
Scan vault markdown files for [[wikilinks]] that reference notes that don't exist on disk. Return a list of broken links with source file and line number. Fixing broken links is a Lyra task — Hestia surfaces them.
Use Glob to get the full list of .md files in vault/. Extract the stem of each filename (filename without path and without .md extension) as the valid link targets.
Use Grep to find all [[wikilink]] patterns across vault notes. Pattern: \[\[[^\]]+\]\]
For each match, extract the link target (the text between [[ and ]]). Strip any alias (text after |). Strip any heading anchor (text after #).
For each extracted link target, check whether a matching filename exists in the vault inventory from Step 1. Match is case-insensitive.
## Link Sweep — YYYY-MM-DD
Total wikilinks scanned: N
Broken links found: N
Clean links: N
### Broken Links
- `vault/path/to/source.md` line N: [[BrokenTarget]]
- `vault/path/to/source2.md` line N: [[AnotherBrokenTarget]]
### Notes
- <any patterns noticed — e.g., "7 broken links all reference deleted agent files">
If zero broken links found:
Broken links found: 0. Vault is clean.
[[Target|Display Text]]) — check Target, not Display Text.[[Note#Section]]) — check Note, not the section.还没有评价。欢迎分享你的使用感受。
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。
Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
中文简介正在准备中。当前显示原文说明。
Compose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures + recommended reflex.
中文简介正在准备中。当前显示原文说明。
Generate a structured delegation brief for any task
中文简介正在准备中。当前显示原文说明。
Quarterly skill that walks the skill-index against the actual SKILL.md files on disk, reports drift (skills indexed that no longer exist, skills on disk that aren't enrolled, skills whose descriptions have changed since enrollment). Hardens the auto-enrollment pipeline against silent rot.
中文简介正在准备中。当前显示原文说明。
When a [CADDY] hint fires and the principal is confused why, /caddy-explain walks the scoring transparently — which trigger matched, what points it earned, what the threshold was, what other skills were close. Pairs with the legibility thesis. Caddy's decisions should be inspectable on demand.
中文简介正在准备中。当前显示原文说明。
Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives. Use when a new skill is created, copied in, or when a skill needs updated triggers. Usage — "/caddy-enroll <path to SKILL.md>".
中文简介正在准备中。当前显示原文说明。