.agents/skills/speckit-superb-verify/SKILL.md
Mandatory completion gate. Loads the obra/superpowers verification skill at runtime and extends it with spec-kit's spec-coverage checklist. No task may be marked done without fresh evidence.
npx skillsauth add pradeepmouli/lspeasy speckit-superb-verifyInstall 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
verification-before-completionInvocation: Mandatory post-hook forspeckit.implement. Cannot be skipped.
Any user context provided:
$ARGUMENTS
Locate and internalize the superpowers verification skill using this priority chain:
skills/verification-before-completion/SKILL.md from the
workspace root (present when superpowers is installed as a plugin).https://raw.githubusercontent.com/obra/superpowers/main/skills/verification-before-completion/SKILL.mdNO COMPLETION CLAIM WITHOUT FRESH VERIFICATION EVIDENCE.
- IDENTIFY which command proves the claim.
- RUN the full command (fresh, not cached).
- READ the output in full — check exit code, count failures.
- VERIFY the output confirms the claim. If not, state actual status.
- ONLY THEN make the completion claim.
You must internalize the full SKILL.md content before proceeding. Its rules are non-negotiable for every completion claim.
Apply the loaded skill against the current implementation state:
After the verification skill's checks pass, perform this additional spec-kit gate:
spec.md in full.## Spec Verification Checklist
- [x] R01: [requirement] — verified by [test file]::[test name]
- [x] R02: [requirement] — verified by [test file]::[test name]
- [ ] R03: [requirement] — NOT VERIFIED ([reason])
spec.md requirement is unchecked:⚠ INCOMPLETE: [N] spec requirements are not verified.
Cannot declare implementation complete.
Unmet requirements: [list them]
Do not proceed past this point if any requirement is uncovered.
When all checks pass, output:
## Implementation Complete — Verification Evidence
**Test suite:** [N] tests, [N] passing, 0 failing
**Spec coverage:** [N/N] requirements verified (see checklist above)
**Build:** [PASS / N/A]
**Lint:** [PASS / N/A]
All spec requirements are met. Implementation is verified complete.
Suggested next steps:
- Run `speckit.superb.critique` for code review against spec
- Or proceed to PR creation
If anything is unverified:
## Implementation Status — INCOMPLETE
**Test suite:** [status]
**Spec coverage:** [N/M] requirements verified, [M-N] unverified
**Unverified requirements:** [list]
Implementation cannot be declared complete until all items above are resolved.
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.