agent-skill-stack

1# Build an Agent Skill Stack
2 
3Build the smallest useful stack for the user's actual outcome. Never force a domain example or a fixed lifecycle onto a different request.
4 
5## 1. Choose the user-facing depth
6 
7Default to **plain-language mode**. Assume the user does not need to understand paths, revisions, hashes, manifests, static analysis, or runtime details.
8 
9In plain-language mode, show:
10 
11- what the user is trying to accomplish;
12- the steps in everyday language;
13- which capabilities are already available;
14- which Skills are recommended, optional, overlapping, or unsuitable;
15- how widely each candidate is used;
16- whether it passed an installation safety check and a safe trial;
17- what account access or external actions it may require.
18 
19Keep source paths, revisions, file fingerprints, raw scores, audit evidence, and dependency details in the internal record. Show them only when the user asks for technical details or when a specific technical fact is necessary for informed consent.
20 
21## 2. Derive the workflow dynamically
22 
23Read [references/workflow-model.md](references/workflow-model.md). Begin with the final result the user wants, not the domain words in the request.
24 
25Ask only questions whose answers materially change the result, access boundary, cost, or stack. Derive the workflow backward from success, then validate it forward from the available starting point.
26…