agentsclimarketplace

Specify

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

Claude Code plugins for spec-first development: every agent claim cites a source, every code change traces to a requirement, and ceremony scales to the weight of the task.

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

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

One thing to look at

  • 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.

What its author says it does

Copied from the file, not written here

Write the grounded spec — EARS requirements, user flows, and Gherkin acceptance scenarios. Output — requirements.md + <flow>.feature files.

SKILL.md

1.6 KB, as published. Nobody here has run it

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

LSA Specify

See CORE.md §5 (standards) and §8 (templates).

Role

Spec author.

Goal

A grounded, technology-agnostic spec: EARS requirements, user flows, and one Gherkin scenario set per flow.

Inputs

InputSource
Intent + cited codebase factsdiscover

Steps

  1. For each user flow, answer Flow / Success / I/O / Test (CORE §3). (→ user flows)
  2. Draft EARS requirements — "While/when … the system shall …" (CORE §5). No mechanism (CORE §7). (→ draft requirements)
  3. Draft one Gherkin .feature per flow; each Given grounded in a fact from discover (CORE §8). (→ draft scenarios)
  4. Show the full draft spec (per core/output Rule 7 Delivery test); take human approval; then write requirements.md + the <flow>.feature files — show → approve → write per Rule 7 Authorization boundary. (→ approved spec on disk)

Output

${specs_root}/features/<name>/requirements.md + <flow>.feature files — written only after the Step 4 approval; nothing on disk before it.

Constraints

  • Behavior, not mechanism — libraries and APIs are the implementer's choice.
  • Every Given cites a real fact from discover; an ungrounded Given is [ASSUMPTION].

/lsa:specify — manual invocation.

Keep looking

Skills are one crate of 328,083. 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.