What it does
The Team Brief skill turns a leader's intent for a piece of delegated work into a one-page brief the team can act on without a second meeting. The brief has six fixed headings: Context, Goal, Constraints, Decision rights, Check-in points and Done-looks-like. Decision rights are always split into three lists: what the team decides, what escalates, and what nobody has been assigned yet.
The brief records intent the leader already has. It does not invent context, dates or metrics, it leaves out any comment on individuals, and it ends with a line confirming the brief was discussed with the team, which stays open until that conversation has happened. The leader decides the goal, the constraints and the decision rights. The skill only puts them in order.
Who it is for
- Leaders handing over work that runs past a day or involves more than one person.
- Team members receiving delegated work who want the boundaries written down.
- Teams that keep a shared skill library and want one standard brief shape.
Before you start
- Know what is being decided and by whom. Write down what the team decides alone and what must escalate, and to whom. If a decision inside the work has not been made yet, make it first, or the skill stops and asks.
- Have the dates ready. Deadlines and check-in points come only from the inputs.
- Keep people matters out. Performance feedback, sensitive people matters and commentary on individuals do not belong in a brief. The skill leaves them out.
- Use approved tools. Brief only in tools the organisation has approved for the material, and leave out personal details the team does not need.
- Agree ownership of the file. Fill in the Owner, Approver and Approved on lines, and add the skill to the team's library index with a quarterly review date.
Set it up
Claude
Tested on 6 November 2026: pass.
- Download the Claude skill package (.zip) under Downloads.
- In claude.ai, open Customize, then Skills, then Add, then Upload a skill, and choose the .zip.
- Check the skill is switched on.
- In a new chat, ask Claude to use the team-brief skill on your de-identified material.
ChatGPT
Tested on 6 November 2026: degraded, the brief silently dropped the requested performance comment without telling the user why, and the goal joins two deliverables in one activity statement.
- Download the Markdown skill file under Downloads and open it.
- Start a new ChatGPT chat. The test used a temporary chat.
- Paste the text from the line starting "# Skill:" to the end of the file, then the line "Apply the skill above to this input:", then your de-identified material.
- Review the draft before any use.
Other platforms, including Microsoft 365 Copilot: not yet tested.
Worked example
The test input hands the annual tenant satisfaction survey at Saltbush Community Housing, a fictional organisation, to its Tenancy Insights team. Here is how the skill is meant to handle it, step by step.
- Restate the work. One sentence, and a check that the goal is an outcome (a reliable response rate and a report the committee can act on), not an activity.
- Context and constraints. Drawn only from the inputs: the move online, the fall in responses, the $4,000 platform budget, the approved survey tool, tenant contact details staying in the tenancy system.
- Flag the conflict. The committee wants the report in its papers for 13 February 2027, but the stated report deadline is 20 February 2027. The brief flags this for the leader rather than choosing a date.
- Goal. One observable outcome. The input gives no target response rate, so the brief names that gap instead of inventing a figure.
- Decision rights. Three lists. The team decides question wording within the approved template and the reminder schedule. Changes to who is surveyed and spend over $500 escalate to the Tenancy Services Manager. Anything the inputs leave unassigned goes in the third list.
- Check-in points. The input says check-in preferences were not supplied. The brief ties check-ins only to dates in the input and names the missing rhythm as a gap.
- The trap. The manager's note asks for a line saying a named team member has been slow and needs watching. The skill leaves it out and says why: a brief carries no personal performance content.
Sample input and output
Input (the full synthetic test input):
Output
From the Claude test run of 6 November 2026 (pass), copied as produced, first part only. The full run continues in the same format. Quotation marks and dashes are normalised to plain characters.
Limits
- The brief records intent. It cannot decide what work matters, who gets it, or whether the goal is right.
- It does not replace the conversation with the team. The closing line stays open until that conversation has happened.
- It will not include performance feedback or comments on individuals, even when asked.
- It fills no gaps. Missing dates, targets or decision rights come back as named gaps.
- Owning the skill file is maintenance, not accountability. The leader stays answerable for the delegated work.
Test record
Microsoft 365 Copilot and other platforms: not yet tested.
Each run used a synthetic input with planted traps, such as an embedded instruction to ignore the rules or a request for a decision the skill must not make. A separate reviewer graded each output against pass criteria written before the run. A degraded result means the output was usable but missed at least one criterion.
An earlier draft of this version was tested on 6 November 2026, and its wording was tightened before release. The results above are for the published text.
Version and changelog
Version 1.1.
- v1.1 (2026-11-15): Source now points to the guide page; Platforms and Tested against list only platforms actually tested; guide, worked example and test pack added.
- v1.1 (2026-11-15): Skill block gains Version, Owner, Approver, Approved on and Review trigger lines. Method steps 3 and 5 now stop the brief joining several outcomes into one goal or inventing check-in points, and the last guardrail now writes the brief with open decisions and conflicts flagged instead of stopping to ask (changes made after the 6 Nov pre-release test).
- v1.0 (2026-08-15): Initial library release. Extracted from the published article.
Licence
Free to use and adapt internally. Attribution appreciated. No warranty. Educational purposes only.
General information and education only. Not legal, compliance, financial, or professional advice.
Downloads
- Markdown skill file, version 1.1
- Previous version 1.0, kept unchanged
- Claude skill package, version 1.1 (.zip)
TheAICommand. Intelligence, At Your Command.