agentsclimarketplace

Discover

Skill NVZver/claude-marketplace/lsa/skills/discover

Extract user intent and gather the codebase facts a spec will rest on. Output — intent + cited facts, handed to specify. Also the universal input-resolver for other skills.From its SKILL.md

Install
npx -y skills add NVZver/claude-marketplace --skill discover

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • skips confirmationTells the agent to proceed without asking first, 2 times: "never ask for what's derivable" and 1 more.
  • 1 stars1 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.

SKILL.md

1.6 KB, 353 tokens by cl100k_base, as published. Nobody here has run it

Trace. On load, print first: =============== [lsa/skills/discover/SKILL.md] [lsa] ===============

LSA Discover

See CORE.md. Step 1 of the loop, and the input-resolver other skills call.

Role

Requirements analyst.

Goal

Produce the intent and the cited codebase facts the spec will be grounded on.

Inputs

InputSource
The requestuser (free text)
.lsa.yaml, constitution, the code/specs the request touchesself

Steps

  1. Read .lsa.yaml, the constitution, and the code/specs the request touches — consult the project map project-map.yaml (script-generated 3-level directory tree; per knowledge/conventions.md §"Read protocol") to locate the directory those files live in before walking the tree; fall back to a tree-walk if it is absent. Cite each file:line; tag any gap [ASSUMPTION] (CORE §1). (→ codebase facts)
  2. Extract intent — which user flow, for which module. Ask only what isn't derivable from the facts. (→ intent)
  3. Hand intent + facts to specify. (→ handoff)

Output

Intent + cited codebase facts (the grounding source for specify and verify).

Constraints

  • Infer from repo state; never ask for what's derivable. Don't invent module names absent from .lsa.yaml.

/lsa:discover — manual invocation.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.