wrap-up — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited wrap-up (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.
Produces a clear, honest closing summary for work sessions. The goal is to give both the user and any future session a complete picture of what was done, how it compares to what was intended, and what comes next. Think of it as the handover document — precise enough to resume work cold, honest enough to flag what didn't get done.
Professional but not stiff. Direct and accurate. This isn't a celebration or a post-mortem — it's a clear-eyed account of where things landed. Flag incomplete items plainly without over-explaining.
Scan the full conversation for:
If no formal spec exists, infer the intended goal from the opening of the conversation.
Produce the following sections. Omit any section that has nothing meaningful to put in it.
Goal One or two sentences stating what this session set out to accomplish, based on the spec, PRD, or stated intent at the outset. If goals evolved during the session, note that briefly.
What was done A clear account of what was actually accomplished versus what was intended. Be specific — reference file names, features, decisions, outputs where relevant. If explicit checkpoints or acceptance criteria were set at the outset, review each one here: was it met, partially met, or skipped, and why? If no formal checkpoints exist, a single honest account of what was done versus the stated goal is sufficient.
What wasn't completed Anything that was in scope but didn't get done — deferred, blocked, or deprioritised. Be plain about it. Include brief context if it's useful (why it was deferred, what's needed to unblock it).
Omit if everything in scope was completed.
Known issues and open questions Bugs, rough edges, unresolved decisions, or things that need a second look. Distinct from "not completed" — these are things that exist in the current output but may need attention.
Omit if there are none.
Next steps The concrete actions that should follow from this session — ordered by priority where obvious. These should be specific enough to act on: not "improve the UI" but "add loading state to the submit button" or "write tests for the auth module".
References A list of any external resources directly relevant to this session — formatted like references in a formal paper. Include where applicable:
Omit if no external references were mentioned or used.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.