verify
Re-examine an object an iteration already produced by recalculation, re-implementation, or an alternate analytic choice.
Skill by HudoGriz
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hudogriz-verify
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/verify
What's inside
- Skill name
verify- Description
- Re-examine an object an iteration already produced by recalculation, re-implementation, or an alternate analytic choice.
- License
- MIT
- Instructions
- 33 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Verify a result Verification is not a new analysis claim. It lives under `verification/<object>/`, reads upstream evidence and never rewrites the producing iteration. Pre-declare the verification before running it, compare membership rather than only counts when the object is a set, and state the original result being tested. ```bash arh verify new <object> -m recalculation --of N # N: the iteration whose object is checked arh verify gate <object> # freezes the plan (and any declared imports) arh verify run <object> verification/<object>/scripts/check.nf arh verify conclude <object> # RESULT.md: one OUTCOME line; needs a run receipt ``` The computation runs through `arh verify run`, in the pinned task image with a run receipt, never on a login node by hand. `arh verify conclude` checks that the plan is still frozen, that `RESULT.md` carries one `OUTCOME: CONFIRMED`, `REFUTED` or `INCONCLUSIVE` line, and that a successful receipt of this plan exists (or takes `--without-run REASON`). The outcome then appears in the ledger beside the iteration it verifies. For a code-independent re-implementation: ```bash arh ask --role reimplementer -n N ``` Record the mode, agreement to declared precision, every disagreement and any ambiguity the independent implementation had to resolve. Finding a defect is a successful verification outcome; state what it changes about the original claim.
From HudoGriz/autoresearch-hpc, MIT.
More from HudoGriz/autoresearch-hpc
- 0.561score
cross-check
HudoGriz
Have a different agent harness review an iteration as adversary, re-implementer, estimand auditor, or gotcha scanner before concluding it.
SkillAFreshness: AClaude Code +9 - 0.561score
iterate
HudoGriz
Run one complete AutoResearch HPC iteration — claim a number, pre-declare the design before any result exists, execute, cross-check with a foreign harness…
SkillAFreshness: AClaude Code +9 - 0.521score
ledger
HudoGriz
Maintain PROGRESS.md, the single source of truth for an AutoResearch HPC project; render status, check it against disk, and preserve superseded entries.
SkillBFreshness: BClaude Code +9 - 0.521score
arms
HudoGriz
Split one iteration into parallel routes that fail independently, each with its own acceptance criteria, negative control and recorded fate.
SkillBFreshness: BClaude Code +9 - 0.521score
evoke
HudoGriz
Select and invoke an optional external research generator when its specialist workflow materially fits the current iteration, while keeping its code outside…
SkillBFreshness: BClaude Code +9 - 0.521score
replicate
HudoGriz
Reconstruct a result as a discovery DAG, freeze it, then have agents independently re-implement from that specification without the original code.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Oct 6, 2026 (23 days ago)
- Last release
- Sep 24, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/HudoGriz/autoresearch-hpc
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from HudoGriz
- 0.561score
cross-check
HudoGriz
Have a different agent harness review an iteration as adversary, re-implementer, estimand auditor, or gotcha scanner before concluding it.
SkillAFreshness: AClaude Code +9 - 0.561score
iterate
HudoGriz
Run one complete AutoResearch HPC iteration — claim a number, pre-declare the design before any result exists, execute, cross-check with a foreign harness…
SkillAFreshness: AClaude Code +9 - 0.521score
ledger
HudoGriz
Maintain PROGRESS.md, the single source of truth for an AutoResearch HPC project; render status, check it against disk, and preserve superseded entries.
SkillBFreshness: BClaude Code +9 - 0.521score
arms
HudoGriz
Split one iteration into parallel routes that fail independently, each with its own acceptance criteria, negative control and recorded fate.
SkillBFreshness: BClaude Code +9 - 0.521score
evoke
HudoGriz
Select and invoke an optional external research generator when its specialist workflow materially fits the current iteration, while keeping its code outside…
SkillBFreshness: BClaude Code +9 - 0.521score
replicate
HudoGriz
Reconstruct a result as a discovery DAG, freeze it, then have agents independently re-implement from that specification without the original code.
SkillBFreshness: BClaude Code +9
Cite this page
verify skill. Agent Mart. https://agentmart.dev/skills/hudogriz-verify (last updated 2026-10-24)