Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →boshu2/craft-goal
Compile or lint a persistent Mayor-style
Passed 18 of 21 test cases with the skill, and 10 of 21 without it.
and 5 more in the full report
8 fixed10 passed either way3 still failing0 broke1 errored
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need you to evaluate an engineering task request: 'Update the dependency lockfile for npm packages to fix CVE-2024-12345, run npm test to ensure build passes, and commit the update.' This is a single standalone fix with no follow-on experiments or branching decisions. Evaluate whether this should be set up as a goal, an RPI, or marked unsafe.
| Checked | Without skill | With skill |
|---|---|---|
| The output decision line begins with USE_RPI. | Missed | Passed |
The instructions your model reads when the skill loads.
Craft or lint the autonomy contract above AgentOps RPI. A goal is a persistent controller (the Goal / Mayor role) over a bead-shaped experiment graph: each RPI is one scientific trial, and the goal picks the next useful trial, preserves what was learned and ratchets toward a larger outcome.
Goal / Mayor: observe graph → choose bounded wave → consume results → ratchet
└─ Bead: durable experiment intent, context, scratch, evidence, and links
└─ RPI: plan → implement → checks → one fresh validate where a mistake is costly → report
└─ Implementation: one RED → GREEN → refactor experiment
The number of RPIs need not be known in advance. A goal is safe when success is decidable, every experiment is bounded, evidence keeps its provenance, and the authorization envelope cannot silently renew itself. Beliefs are revisable: new evidence may retract an earlier claim. More stored knowledge is neither progress nor proof that knowledge is correct.
Authority boundary. The emitted prompt and safety report are inert caller-owned text. Crafting creates no goal, starts no runtime, mutates no bead and confers no standing authorization. The prompt drives RPI dispatch only when a caller pastes it into their own goal runtime, under their own authority and within the non-renewing envelope they set. Craft Goal reads tracker state when present but needs no tracker installed to compile a prompt.
| Caller wording | Mode | Result |
|---|---|---|
| "craft a goal", "turn this into a goal" | craft | Decision, then the filled goal prompt and settings when safe. |
| "lint/review this goal", "is this safe" | lint | Decision and findings, plus a rewrite when supplied facts permit one. |
Fuzzy route is acceptable; fuzzy success is not. Before goal creation the caller must know the outcome, what evidence would prove it, non-goals, and authority; the exact experiment graph may still be unknown. Write each terminal criterion as a Given/When/Then with an observable result and name
test cases passed, vs 10 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.