capture — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited capture (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Turn something worth keeping — a debugging pattern, a process lesson, a decision, a "this could be a post" idea — into a canonical journal entry. Capture must be cheaper than not capturing: draft the entry for the user from the conversation; never make them format it.
managed journals accept entries. If exactly oneis configured, use it. If several (e.g. a journal per project), ask which. list_themes shows the configured journals and their themes.
title — concise and specific (a future search matches on it).body — freeform: a whole-session dump, a single lesson, or a tidied-uplist are all valid. This is the substance.
themes — the topic(s) it belongs to. If the user named none, callsuggest_themes(title + body) and propose what it returns (existing themes ranked by similarity); confirm, then use those. Reuse existing themes so pattern-finding stays coherent; add a new one only when nothing fits. Multi-valued.
tags — optional finer labels.blog_angles — when the insight is post-worthy, propose one or more angles(working titles). This is the raw material for later writing; don't let it evaporate.
entry_date — defaults to today; set only when backdating.blog_angles?, entry_date?)`. One call writes the entry, regenerates the views, and rebuilds the index.
blog_angles, not prose.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.