← ClaudeAtlas

logic-checklisted

Audit a verifiable, step-wise computation (arithmetic, financial calculation, algorithm trace, constraint solve, scheduling problem) by having the reviewer separately re-derive the answer from the original problem statement and comparing — not by asking the reviewer to "check the work," which anchors on the existing derivation. Use when the user says "audit this calculation," "double-check my math with the reviewer," "verify these computations," "check this trace," "is this cap table right," "re-derive this with the reviewer," "audit my arithmetic," "logic-check this," or "is this number right." Also offer this proactively when the active primary has just performed a long multi-step calculation, an algorithmic trace (DP table, graph traversal, constraint propagation), a financial computation (cap table, tax math, unit conversion, currency-adjusted aggregate), or any computation where a wrong intermediate state silently corrupts the final answer.
sumitake/agent-collab · ★ 0 · AI & Automation · score 63
Install: claude install-skill sumitake/agent-collab
## Unified runtime invocation Resolve the **plugin root** from this loaded file: `SKILL.md` is at `<plugin-root>/skills/<skill-name>/SKILL.md`. Invoke only `python3 "<plugin-root>/coordinator.py"` and send one bounded JSON routing request on EOF-delimited stdin, without a PTY. Use the Python invocation example in the **Routing request** section in `<plugin-root>/README.md` and the co-packaged manifest's signed `wire_contract`; never invent fields or provider actions. Supply one caller-defined work unit per independently useful deliverable, with this skill's logical action and a bounded opaque payload. Use `depends_on` only for actual dependencies. Honor an operator-named provider with `explicit_target`. For an authorized independent review or governance task without an operator-named provider, also use that field to bind the caller-verified distinct reviewer selected by the caller or designated by the workflow. Carry the same target into planning and live dispatch; verify returned native lineage before accepting independence. Otherwise use normal untargeted routing. Choose quality and effort for the workload; include context/output token estimates when known. Read the current manifest digest and actual cwd device/inode; do not copy example values. The runtime owns its timeout; do not wrap it in a shorter fixed timeout. Repository identity, source-head verification, disposable copies, patch capture, and cleanup remain caller-owned where applicable. The shim runs standalone fr