Use before claiming any work is complete, fixed, done, or passing — run the most relevant verification first and report evidence rather than assumptions.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add norton77930/Provost --skill verification-before-completion --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Verification Before Completion?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/norton77930-verification-before-completion)More formats (shields.io, HTML) on the badges page.
---
name: verification-before-completion
description: Use before claiming any work is complete, fixed, done, or passing — run the most relevant verification first and report evidence rather than assumptions.
---
# Verification Before Completion
A completion claim is a statement about evidence, not intent. Before saying "done", "fixed", or "passing":
1. Name the check that would most quickly prove the claim wrong — a targeted test, build, lint, type check, or the original repro command.
2. Run it now, in this session, and read the output.
3. Report the claim together with the evidence: what changed, what you ran, and what it printed. Quote failures verbatim.
Treat this as one planned final verification for the declared Completion Contract. Do not use this skill to open optional review, testing, analysis, refactoring, or documentation work.
Calibrate the claim to the evidence:
- Code written but never run is unverified — say so instead of implying it works.
- Partial checks make partial claims: "the targeted tests pass; the full suite was not run."
- If the check fails, the failure is the result to report — do not soften it into progress.
- If verification is impossible here (no environment, missing credentials), state what is missing and exactly what you would run.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.