.claude/skills/speckit-superb-clarify/SKILL.md
Orchestrates the obra/superpowers brainstorming skill within the spec-kit specify workflow. Loads the authoritative SKILL.md at runtime, binds spec-kit context, and produces an intent summary for speckit.specify.
npx skillsauth add pradeepmouli/lspeasy speckit-superb-clarifyInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Skill origin: obra/superpowers
brainstormingInvocation: Pre-hook forspeckit.specify. Optional — skip if the requirement is already fully understood.
Locate and internalize the superpowers brainstorming skill using this priority chain:
skills/brainstorming/SKILL.md from the workspace root
(present when superpowers is installed as a plugin).https://raw.githubusercontent.com/obra/superpowers/main/skills/brainstorming/SKILL.mdOne question at a time. Explore 2-3 design approaches with trade-offs. YAGNI ruthlessly. Never commit to a single path before comparing. Incremental validation — get confirmation before the next question.
You must internalize the full SKILL.md content before proceeding. Its rules govern the dialogue structure for this session.
Before asking the user anything, silently read:
$ARGUMENTS
spec.md or constitution.md in the feature directorygit log --oneline -20) to understand adjacent work.specify/init-options.json to understand project conventionsIf the intent is fully clear from context (e.g., tiny bug fix with exact reproduction steps), output a one-line summary and exit:
Intent is unambiguous: [one sentence]. Proceeding to spec creation.
Apply the loaded brainstorming skill with these spec-kit guardrails:
<HARD-GATE> above — no spec files, no code, no scaffoldingAfter the user selects an approach, output the following structured summary.
This is the sole deliverable of this command — it becomes input for
speckit.specify:
## Intent Summary
**Feature:** [name]
**Problem being solved:** [one sentence]
**Chosen approach:** [approach name]
**Success criteria:**
- [ ] [measurable criterion 1]
- [ ] [measurable criterion 2]
**Out of scope (explicit):**
- [thing that was considered and excluded]
**Open questions for the spec:** (if any)
- [question that the spec author needs to answer]
tools
Use for ANY rename, file-move, or move-symbol refactor — especially rename-heavy work across multiple files. Claude Code's built-in LSP tool is READ-ONLY (find references, but no rename / file-move / move-symbol). Hand-editing those refactors silently misses re-exports, aliased imports, type-only imports, and {@link} doc references. This skill drives a real language server via the `lspeasy` CLI to apply a correct WorkspaceEdit that catches every reference. Trigger when the user asks to rename a function/class/variable/type project-wide, move a file and fix its importers, or pull a symbol out into another module.
tools
Documentation site for lspeasy Use when: You are building a browser-based LSP client, a WebSocket-backed language....
tools
Documentation site for lspeasy Use when: You are implementing a custom client layer and need the same validation....
tools
Use when working with lspeasy (client, core, server). Covers: lsp, language-server-protocol, lsp-client, language-client, jsonrpc, transport, lsp-server, language-server.