suggest-next — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited suggest-next (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.
Seeds future conversations and tasks by surfacing what the current session implies but didn't cover. The goal is to plant ideas that will benefit from being "slept on" — things the user might want to return to, explore further, or act on in a future session.
This is generative and lateral, not administrative. It's not a task list or a project management tool — it's more like a well-read colleague saying "oh, while we're on this topic, have you thought about..."
Before writing, determine which mode applies based on the conversation:
Exploratory mode — the session was a discussion, brainstorm, research dive, or conceptual conversation. Suggestions lean toward: related ideas and concepts, books and articles, rabbit holes worth exploring, questions worth sitting with, future conversations to have.
Work mode — the session involved building, fixing, or shipping something. Suggestions lean toward: related tasks and improvements, adjacent technical concerns, relevant tools or libraries, recent news or developments in the tech area worked in, further learning directly applicable to the work.
Many sessions will mix both — surface suggestions from both modes where relevant, but weight toward whichever dominated.
If you want to go deeper Ideas, topics, or questions that extend directly from what was discussed or built. These are the natural "next chapter" — not tangents, but continuations. 2–4 items, each with a sentence of context explaining the connection.
Related things worth exploring Lateral suggestions — adjacent topics, alternative approaches, contrasting perspectives. Things that aren't a direct continuation but are meaningfully connected and would enrich understanding or expand the work. 2–4 items.
Worth reading / watching / listening to Specific recommendations — books, articles, talks, podcasts, documentation — that are directly relevant to what came up. Be specific: title, author/source, and one sentence on why it's relevant here. Omit vague genre suggestions ("you might enjoy books about AI"). Only include if genuinely relevant recommendations exist.
Tasks this session implies (work mode only) Concrete tasks that weren't in scope for this session but are clearly implied by it. Framed as actionable items, specific enough to become a ticket or task. Omit in exploratory mode.
Loose thread... One single observation, question, or provocation to carry forward — something that didn't get proper attention this session but deserves to be the starting point of a future one. This should feel like a good conversation ender: something worth sitting with.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.