cash-truth
Enforce one canonical cash authority and honest mirror/reconciliation states. Use when cash appears in multiple stores or UI rows, negative cash may mean margin or missing inflow, mirror rows disappear, or missing balances risk being treated as zero or reconciled.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- cash-truth
- description
- Enforce one canonical cash authority and honest mirror/reconciliation states. Use when cash appears in multiple stores or UI rows, negative cash may mean margin or missing inflow, mirror rows disappear, or missing balances risk being treated as zero or reconciled.
02 资源文件 1
- 参考文档agents/openai.yaml140 B
03 SKILL.md 正文
Cash Truth
Rule
Missing cash is not zero cash.
Workflow
- Identify the canonical cash authority before inspecting mirrors or UI rows.
- Classify canonical state as known, unknown, or unavailable. Do not infer zero from absence.
- Compare mirrors only when both sides exist. A non-zero canonical balance with a missing mirror is drift, not agreement.
- Interpret negative cash from account capabilities and evidence; do not label every negative value as margin or error.
- Route all canonical cash writes through one atomic writer. A mirror must never become a second authority.
- Expose drift with a reason precise enough to choose the correct repair path.
Falsify it
Try to reconcile canonical cash, mirrors, and consumers without treating absence as zero. A nonzero authority with a missing mirror is drift, not agreement.
Stop conditions
- Canonical authority cannot be identified.
- A requested repair would zero or overwrite cash without evidence that the economic balance is zero.
A stop is an output, not an excuse. State what evidence or authority would unblock the work.
Output
CANONICAL CASH · MIRROR STATE · DRIFT · CAPABILITY CONTEXT · SAFE REPAIR PATH · WITHHELD ASSUMPTIONS.
Keep the report short enough to act on. Preserve hard facts, unknowns, and blockers.
04 同仓库更多 Skills
verify-before-cite
Live-verify work state before reporting or relying on it, and reconcile every place that state is recorded. Use before a status report, standup, handoff, or "what's open" answer; when a tracker, queue, memory note, or prior session says something is pending, merged, shipped, or blocked; after any merge, release, or promotion; or when records in two places disagree. Do not use to judge whether a claim about data or numbers is proven.
truth-boundary
Enforce provenance and uncertainty boundaries. Use when a system mixes observed, authoritative, user-attested, derived, estimated, inferred, reconstructed, or unknown values; when missing data could become zero; or when downstream output may overstate certainty. Also use when told to fill a missing, failed, or empty value with zero, a default, or a guess so the work can keep going.
systemic-bug-instinct
Use first, before reading, searching or editing code, whenever a defect, wrong value or balance, stale state, edge-case failure, broken workflow, or misleading UI is reported and a fix is requested, even when the request names the one file to patch. Diagnoses the bug as a possibly systemic failure to find the root mechanism, failure class, blast radius across sibling consumers, fix location, and regression guard. Do not use for a one-line typo or syntax fix, for two components that disagree about one concept (use seam-audit), for a dense screen whose value may be a presentation problem (use operator-ui-audit), or for financial records that contradict each other (use accounting-integrity).
swarm
Design and run the smallest effective multi-agent harness for complex work. Use when the user explicitly says SWARM or asks for a swarm, multi-agent workflow, adaptive orchestration, harness design, parallel investigation, independent falsification, architecture reconciliation, broad audit, competing root-cause hypotheses, or high-risk work that benefits from independent reasoning lanes. Do not use for trivial edits or linear tasks one agent can complete cheaply; the best swarm may use zero subagents. SWARM grants orchestration, not broader implementation, merge, deploy, credential, financial, or destructive authority.
shipping-lanes
Design, run, or adopt a pipeline in which agent-written changes are reviewed and merged without a person in the routine loop, with review and landing matched to each change's risk. Use when setting up or changing how PRs get reviewed and merged by agents; when every change waits on one person, or none gets reviewed; when a reviewer is only reached if the author asks for it; when docs and permission changes take the same path; or when bringing a new repository onto the shared shipping system. Do not use to decide whether one specific merge is authorised (use merge-authority), to judge a finished-looking result (use false-competence-check), or to prove a single guard is reached (use reachability-proof).
seam-audit
Audit the boundary where two components represent the same concept, because each side can pass its own tests while the combined system is wrong. Use when a value looks coherent but is wrong, when a projection or compatibility view stands in for a full record, when sync or merge involves deletes, when status codes or result shapes cross a boundary, or when "unknown" may become zero, false, or success as it crosses between two components. Do not use for a defect inside one component (use systemic-bug-instinct), for grading one claim's certainty (use truth-boundary), or for a financial repair's preview and commit (use ledger-repair).