Turn raw mess — a Slack thread, meeting transcript, Jira ticket, half-written Notion page, email chain, or paragraph of free-form context — into a structured brief that the downstream skill (adr-generator, design-doc, runbook-generator, exec-summary, slide-outliner) can consume without further intake. Use whenever the user has unstructured source material and is about to invoke another skilldrop skill, or when a draft is missing the load-bearing context the next step will need.
Pack coreTier standardJob Get a draft ready to shipv0.1.2
In Claude Code, with the core plugin installed, invoke it as:
/core:brief-intake
Try it
A realistic prompt from the skill's acceptance evals:
Here's a messy Slack thread about our caching problem — turn it into a brief I can hand to design-doc.
What a good result looks like
Quote, don't paraphrase, when extracting. When a field is [explicit] or [implied], include a 5–15 word verbatim snippet from the source so the downstream skill (and the user) can verify nothing was hallucinated.
Convert relative dates to absolute dates. "Next Friday", "EOQ", "the sprint after this one" all become YYYY-MM-DD with (implied) if you had to compute it. Today's date is in the system context — use it.
Don't invent people. If the source says "someone from platform should…", the owner is unowned, not a guess.
Don't merge across sources unless the user asked. If the user pastes a Slack thread *and* a doc, ask whether you should treat them as one brief or extract separately.
Strip noise aggressively. Greetings, off-topic banter, "lol", and emoji reactions get dropped. The brief is the signal, not the conversation.
How it's checked
Measured against plain Claude Code (2026-10-23): it met 69% of its checks, against 58% without it, and a blind judge preferred the agent without it. How skills are checked
18 assertions across 3 acceptance evals, and 8 trigger queries. Every skill's checks
What the output must do
Extracted fields marked [explicit] or [implied] carry a short verbatim snippet from the source so nothing is hallucinated
Relative dates are converted to absolute YYYY-MM-DD, marked implied where computed
Gaps are named as missing rather than filled in with plausible invention
The output names the downstream skill the brief is shaped for
The brief is structured into the fields that downstream skill needs, not a summary
Flags that the 06:10 sailing's average is 38 passengers in the email but 83 in the meeting notes, and does not silently pick one figure
Notes that the Option C savings listed (£84k + £51k + £20k = £155k) do not add up to the stated 'about £165k'
Treats the £120k subsidy cut as a proposal awaiting the council vote on 26 Nov 2026, not as approved
Records that Option B falls below the licence minimum of four return crossings a day, so it is ruled out on weekdays
Lists the tourism impact as missing information rather than supplying a figure or estimate for it
Does not invent figures, dates, decisions or people not in the two files
Stays within one page and is a brief for the summary writer, not the exec summary itself
Delivers the bullets without first stopping to ask questions (open questions can sit inside the bullets)
Captures that Jen can only cover alternate Sundays, so the other Sundays have no staff named
Notes that rent does not change, so it is not an extra cost of opening
Names what is still unknown that the proposal needs, such as how many Sunday bookings to expect and what staffing Sundays would cost
Does not invent prices, demand figures, wages or opening hours
Keeps to a few short bullets in plain language
When it should and shouldn't activate
Should activate:
Turn this Slack thread into a structured brief
I have a messy transcript — get it into shape for the design-doc skill
Structure this raw context into a brief before I run the next skill
Take this half-written Notion page and extract a clean brief
Should leave to another skill:
Extract the decisions, owners, and due dates from this discussion