Consult frame
6 SKILLs to improve Claude Code memory, derived from Timeln's second brain capability to remember everything.
npx -y skills add Timelnapp/skills --skill consult-frameAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Trigger on "frame the engagement", "consult frame", "problem frame", "scope card", "definition of good", "what decision does this support", "in scope out of scope", "client brief → frame", "one-pager frame". Turns a brief or transcript into a structured engagement frame. NOT the solution arc (use consult-arc), NOT phasing gates (use consult-gates), NOT memory recall (use timeln-find / timeln-decided).
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.4 KB, 489 tokens by cl100k_base, as published. Nobody here has run it
Consult Frame -- Engagement Frame Card
Turn raw client input into one structured frame: decision, success definition, scope boundaries, stakeholders.
Inputs
| Input | Required | Notes |
|---|---|---|
| Brief, transcript, bullets, or notes | yes | Paste as-is if no file |
| Client / industry labels | if known | For naming only |
Optional prefetch (user may ask): timeln-find / timeln-decided for prior domain or settled calls -- cite titles only when using Timeln output.
Workflow
- Extract the decision the work supports (buy/build, fund phase, vendor pick, go/no-go, etc.). If multiple, pick the primary; list secondaries one line each.
- Write definition of good -- observable outcome the client wants, not activity.
- List in scope / out of scope as explicit bullets; flag assumptions that must hold or the frame is wrong.
- Name stakeholders: decision owner, working team, approvers, blockers if mentioned.
- Record open questions that block a firm frame (max 5).
Output -- exactly this shape
## Frame -- <client or "TBD"> -- <YYYY-MM-DD>
**Primary decision:** <one sentence>
**Definition of good:** <one sentence>
**In scope**
- ...
**Out of scope**
- ...
**Assumptions**
- ...
**Stakeholders**
| Role | Name / team | Notes |
|---|---|---|
| Decision owner | |
| Delivery / working team | |
| Other | |
**Open questions**
1. ...
Rules
- Do not write MVP/roadmap/phasing here -- frame only.
- If the source is silent on a section, write
unknown -- confirminstead of inventing. - One primary decision per card unless the source explicitly ties multiple decisions at the same level.
Common failure modes
| Mistake | Fix |
|---|---|
| Bulleted features instead of "good" | Rewrite as outcome the exec would recognize as done |
| Scope creep in "good" | Move extra work to in-scope bullets or out-of-scope |
| Stakeholder = generic "business" | Replace with named role or unknown -- confirm |
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.