re0-upgrade
Bring your installed paperthin skills up to the full current catalog in one step: retire…
Verify the model's understanding of a user's instruction before spending non-trivial work. Use when a request is long, bundled, high-stakes, hard to undo, or has ambiguous scope or referents such as this, that, it, the other one, whatever is cleaner, or whichever order makes
$ npx -y skills add LilMGenius/paperthin --skill readchk --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/readchkContext preview
The summary Claude sees to decide when to auto-load this skill.
Verify the model's understanding of a user's instruction before spending non-trivial work. Use when a request is long, bundled, high-stakes, hard to undo, or has ambiguous scope or referents such as this, that, it, the other one, whatever is cleaner, or whichever order makes
name: readchk description: "Verify the model's understanding of a user's instruction before spending non-trivial work. Use when a request is long, bundled, high-stakes, hard to undo, or has ambiguous scope or referents such as this, that, it, the other one, whatever is cleaner, or whichever order makes sense. Restate internally, cross-check against available context, proceed silently when resolved, and surface only a genuine surviving fork."
Check the read before acting: did you understand the instruction correctly enough to spend the work?
`readchk` catches misread instructions before they become coherent work against the wrong target. It verifies a claim about the requester's intent against available context: the current message, session history, project memory, files on disk, and established conventions.
This is not `factchk`: the question is what was meant, not whether a world claim is true.
1. Recognize the signal: a long or multi-part instruction, ambiguous scope or referents, deliberately flexible wording, or stakes high enough that a wrong guess would cost real work. 2. Restate the instruction internally in different words. Do not copy the user's wording back to yourself and treat that as understanding. 3. Cross-check the restatement against available context. Look for contradictions, missing antecedents, or two plausible readings that context cannot choose between. 4. If context resolves the read, proceed silently. Do not ask the requester to confirm what the available context already answered. 5. If a real fork survives, surface one specific clarifying question anchored to the restated understanding. Name the choice; do not ask a vague "does this look right?" 6. For substantial work, log one durable "understood as: ..." line before beginning so a later reader can audit whether the work matched the confirmed read.
Before proceeding with the work: the restatement is a paraphrase, every surfaced fork is genuinely unresolved by available context, and no substantial work starts without either a silent pass or a resolved fork.
Turning old engineering wisdom into reflexes your agent reaches for on its own. On any agent | Claude Code, Codex, OpenCode, Antigravity, Copilot, Cursor, Grok-Build, Pi, Hermes, OpenClaw, etc.
Repo: LilMGenius/paperthin
Bring your installed paperthin skills up to the full current catalog in one step: retire…
Audit and consolidate a fact that's scattered across places into one canonical source, after…
Rebuild the human's lost context on a project from live state, in plain language: what needs…
Read the live cycle state and return the single highest-leverage next best action, not a…
Run repeated build -> QA -> re0-memo -> re0-work cycles while preserving learning and letting…
Turn a finished, failed, or disappointing work cycle into portable lessons, anti-patterns,…