double-check

Solid

Targeted re-verification of a specific claim, output, or decision. Re-read sources, challenge, cross-reference, and deliver a verdict. Trigger when the user runs /double-check or asks to "verify this", "re-check this", "are you sure about this", "go over this again", or "make sure this is right". Not /verify (formal phase gate needing intent+plan+execution artifacts) or /insight-critique (advisory review of an output) — double-check is a quick targeted re-read of one claim.

AI & Automation 0 stars 0 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 78/100

Stars 20%
0
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# /double-check Multi-pass re-verification of a plan, output, decision, or document — re-read from scratch, challenge assumptions, propose improvements, and iterate until solid. > **Re-Read & Improve Protocol — not a single-pass gate.** The agent re-reads the target fresh, challenges each part, proposes improvements, and iterates. Each pass tightens the result. > **Structured execution spec:** [`protocol.yon`](protocol.yon). It carries the five phases, the scope/verdict gates, and the rules as validatable records; this file is the explanation. Keep the two in sync — edit one, update the other and refresh the `@STAMP` date. > **Caller Options.** Before executing, run the Caller Options protocol (`caller-options/SKILL.md`): triage this invocation for material optionality across the venues and modes declared in front-matter; if one path clearly dominates, proceed silently; otherwise surface the options to the caller. A resolved-invocation marker means COP already ran — execute the fixed combination directly, do not re-enter COP. --- ## Phase 1: Scope Identify what is being double-checked — a plan, an output, a decision, a document. Load it fresh. Do not rely on prior context or cached understanding. **Gate:** Cannot double-check without a clear target. If the target is ambiguous, ask before proceeding. --- ## Phase 2: Fresh Re-Read Re-read the target from scratch as if seeing it for the first time. Go back to the **actual sources** — files, code, docs. Do not verify f...

Details

Author
allemaar
Repository
allemaar/open-skills
Created
1 months ago
Last Updated
today
Language
JavaScript
License
Apache-2.0

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

doublecheck

Adversarial verification of implementation correctness. Runs 4 subagents that attack from different angles: gap finding, assumption attacking, ground truth verification, and devil's advocacy. Use after completing work, before releases, or to attack a plan before implementation.

0 Updated yesterday
0merUfuk
AI & Automation Listed

double-check

Use whenever the user asks to double-check, cross-check, verify, recheck, sanity-check, or confirm prior analysis or results — including "are you sure", "are you confident", "is this true", "still true?", "prove it", "triple check", "check against" some artifact, "look again", "repeat the analysis", or "repeat your findings in full". Re-derives the answer from source artifacts and returns it standalone in the original request's structure — never a revision log of the prior turn. Also invoke before re-running any analysis whose output the user has already seen once. To repair a chat where a diff-shaped answer already happened, use the `double-check-align` skill.

2 Updated today
tony
AI & Automation Listed

double-check

Exhaustively validate every claim, number, calculation, code-fact, and command in a document or outbound communication. Extracts all claims into a prioritized ledger (flagging what is NOT covered), validates each by the right method (run the math, run the command, cite the file:line, quote the primary source), then calibrates certainty with CIA Words of Estimative Probability and a provenance tier — and proposes corrected, properly-hedged rewrites for any overclaim. Use before sending a message, filing an issue, committing analysis, or whenever you state exact numbers/assertions others will rely on.

0 Updated yesterday
DazzleML