create-client-decision-brief
Skill2 starsChanged 56 days agoMITView on GitHub
Create a client-facing brief for a pending choice from consultant notes, options, quotes, and evidence. Use when a client needs to assess a recommendation and authorize a next step; not for recording an already-made decision or replacing a contract or approval workflow.
In this repository5 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Read the decision method before drafting.
- Distinctive: line 16
Read evidence and limits when explaining or revising the method.
- Very specific: line 25
Keep real text, semantic headings, language/title/viewport metadata, embedded CSS, accessible contrast, and a clear narrow-screen reading …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Create a client decision brief
Help a client understand a pending choice, its tradeoff, and what they are being asked to authorize. No account, connection, or product-specific tool is needed. Preserve an explicitly requested email, Word, PDF, slide, or other format. Otherwise produce a readable, self-contained static HTML brief.
Read the decision method before drafting. It is the
canonical method used by the first-party client-decision-brief recipe.
Read evidence and limits when explaining or revising
the method; its structure is not a guarantee of a correct decision.
For HTML, brief.html is an optional structural starter, not a fixed layout or a source of case facts. Replace bracketed instructions, remove unused sections, and adapt the number of options to the actual choice. Honor supplied visual preferences. Use aligned comparisons to expose a real tradeoff rather than repeating prose across decorative cards.
Keep real text, semantic headings, language/title/viewport metadata, embedded CSS, accessible contrast, and a clear narrow-screen reading order. Use static HTML without JavaScript, forms, SVG, canvas, frames, remote assets, live calls, or automatic refresh. Normal audience-safe source links are fine. Important conditions must remain visible without opening a disclosure. Include useful print styling; the page must not imply it captures a signature or approval.
Inspect the rendered result on desktop and a narrow screen, including 320px where practical, plus print when useful for the recipient. Check long labels, comparison mappings, keyboard navigation, and the actual sanitized result when available. Fix defects and re-render. Disclose checks that could not be run. For another requested format, review that format instead of forcing HTML.
Return the draft and the few unresolved questions that materially change the decision. Read the optional sharing adapter only when recipe retrieval or publishing through share/artifacts is relevant. Creating the brief does not authorize sending, publishing, changing access, committing files, or making the client's decision.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

