sno-ai/sno-station-skills / skills/T-delegation-and-work-orders/deliver/skill
deliver
VerifiedCarry out a released charter to a proven result: plan only as much as the work needs, do the work through the project's own workers, prove every success check with a recorded real run, get one independent review, and close honestly. Invoke explicitly as `$deliver <charter>` (Codex) or `/deliver <charter>` (Claude, Cursor), or the way your agent invokes a skill, or when a dispatch names you the executor of a charter.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.7 KB |
| references/proof.md | markdown | 1.8 KB |
| scripts/deliver-proofexecutable | script | 6.4 KB |
| scripts/deliver-proof.t | other | 13.6 KB |
| scripts/selftest/run-selftest.shexecutable | script | 1.7 KB |
references/proof.md
View on GitHub# Functional proof
Choose the smallest check that tells the requested result apart from the reported problem. Do
not repeat the same behavior at several layers unless each layer catches a different defect.
## Any project
- A check starts at the ordinary entry and observes the destination.
- A document: open the produced file and read the sentence the check names.
- A message: read it at the receiver, not the sender's "sent" line.
- Data: recount from the independent source and compare.
- A model's answer: judge the actual answer against the criterion the charter states.
- The expected result is written in the charter or comes from independent known data, not from
output pasted after the fact.
- A failed check stays failed until the work changes and the check passes again. Keep the real
output and exit status.
## A code project
- Bug fix: reproduce the bug and show it fail, then show it pass after the repair.
- New behavior: the smallest check of its real outcome. When the promise crosses components,
run the real journey from its ordinary entry to its destination (retrieve the saved value,
read the delivered message at its receiver) instead of a call-level test.
- A changed detector: test the smallest real defect it must catch and the normal case.
- Test code supplies inputs and observes the result; it never implements a missing product
step and never proves only its own mock.
- Use the project's existing test setup. Check only the dependencies this check needs.
- Estimate the run from existing timings first, run only the changed behavior and what
directly depends on it, and run a full suite only on the owner's request.
- Commit, push and deploy only within the owner's authorization. Use the project's cleanup
skill on the final diff when it has one.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |