Consult arc
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-arcAssembled 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 "solution arc", "current state target state", "consult narrative", "storyline for proposal", "MVP pilot full as risk", "sequencing rationale". Builds one arc: as-is → target capability → why this order, with options tied to risk reduction. NOT the frame card (use consult-frame), NOT gate tables (use consult-gates), NOT diagrams (use arch-diagrams).
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, 503 tokens by cl100k_base, as published. Nobody here has run it
Consult Arc -- Solution Story
One coherent narrative: current state → target capability → why this sequence; options framed as risk reduction.
Inputs
| Input | Required |
|---|---|
Frame card from consult-frame | yes |
| Capability target or constraints from source | yes |
Optional: timeln-shipped / timeln-find for proof and analogs -- one line each, no fake past work.
Workflow
- Current state -- 3-6 bullets: what exists today (people, data, systems, process). No blame tone.
- Target capability -- one paragraph: what the org can do after engagement, not tool names unless source names them.
- Sequencing rationale -- ordered list: what you prove first vs later; each step names risk removed or decision unlocked.
- Options -- exactly three rows unless source forbids: MVP, Pilot, Full. Each: intent, primary risk reduced, what you explicitly do not claim yet.
- Single-thread check -- one sentence: "This arc answers: <primary question from frame>."
Output -- exactly this shape
## Arc -- <client or "TBD"> -- <YYYY-MM-DD>
**Current state**
- ...
**Target capability**
<short paragraph>
**Why this sequence**
1. ... → reduces: ...
2. ...
**Options (risk-reduction framing)**
| Option | Intent | Risk reduced | Not claiming yet |
|---|---|---|---|
| MVP | | | |
| Pilot | | | |
| Full | | | |
**Thread**
This arc answers: "<primary decision / question>".
Rules
- Options are not feature shopping lists -- every cell must tie to risk or decision.
- If MVP/Pilot labels do not fit, rename rows to match source language but keep three graduated commitment levels max.
- Do not duplicate phasing gates -- stop at narrative; phase mechanics go to
consult-gates.
Common failure modes
| Mistake | Fix |
|---|---|
| "We will implement X, Y, Z" in options | Reframe as risk removed and decision proven |
| Target = vendor name | Rewrite as capability; put vendor in a note only if cited |
| Two arcs for two audiences | One arc; consult-package splits audience later |
What ships with it: 1 file
1.8 KB alongside SKILL.md
- FRAMEWORK-VARIANTS.md1.8 KB