Verification Before Completion
Evidence before claims: run the real verification command fresh before saying anything is done
- What
- Evidence before claims: run the real verification command fresh before saying anything is done
- Cost
- Free
- Needs
- an AI agent harness (Claude Code, Codex, Pi, Antigravity, Hermes, or Muse)
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — one of the original superpowers meta-skills by @obra (the upstream behind the much-forked framework; distinct from the magentosh/bankai-skills forks already in this catalog and from the obra fiches published at lot 33, using-superpowers and executing-plans). The iron law: NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE. The gate function every agent must run before declaring success: 1) IDENTIFY what command proves the claim, 2) RUN it fresh and complete, 3) READ the full output and exit code, 4) VERIFY it confirms the claim, 5) only then make the claim — skipping any step is lying, not verifying. Includes the claims table: "tests pass" requires test output with 0 failures (a previous run or "should pass" is not sufficient), "bug fixed" requires re-running the original symptom, "linter clean" requires linter output. The anti-completion-hallucination skill. Complementary to obra-dispatching-parallel-agents (this lot): verify each delegated result before integrating. By @obra, listed here with credit to its creator. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Prerequisites: an AI agent harness (Claude Code, Codex, Pi, Antigravity, Hermes, or Muse) Install "Verification Before Completion" for me. Evidence before claims: run the real verification command fresh before saying anything is done Repository: https://github.com/obra/superpowers/blob/main/skills/verification-before-completion/SKILL.md 1. Fetch the SKILL.md file for the obra-verification-before-completion skill from the repository into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "obra-verification-before-completion". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. any accounts, API keys, or CLI tools mentioned in the prerequisites above). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. Never ask me to paste secrets in chat — credentials go through the secure vault or environment variables. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.