Menu

Individual skill

define-goalstate

Use when the user wants the finished-system contract for a piece of work: behavior, protocols, allowed, forbidden, and impossible states with a state-space proof. Not for runtime verification.

.devin/skills/define-goalstate/SKILL.md

Read pinned source

Source commit b0e8ce89a19fac880251dc3ea1babfeb4503a4fe

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
Yes
Observed behavior
Instructions only
Last checked
Nov 4, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
55
Repository last updated
Sep 28, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Define goalstate

## Contract

| Field | Bound contract |
|---|---|
| Trigger | The user wants to write the finished-system contract for a piece of work. |
| Authority | Reversible local: writes only the named local contract document; rollback is deleting or overwriting it. No remote mutation. |
| Side effect | A finished-system contract document describing behavior, protocols, a concrete state-space proof, allowed states, forbidden states, impossible states with their structural invariants, a falsifiable success predicate, and terminal failure behavior. No other file, credential, or remote target is touched. |
| Done | An approved success-predicate document exists, naming behavior, protocols, allowed states, forbidden states, impossible states, falsifiable success predicate, state-space proof, and terminal failure behavior, structured for consumption by downstream wayfinding. |

## Inputs

The user must supply the intended finished system: what it must do (behavior) and the rules governing its interaction (protocols). The user must classify states as allowed, forbidden, or impossible. An impossible state is only admitted if the user can name the structural invariant or boundary that makes it unreachable; "unlikely" or "undesired" is not enough. The success predicate must be falsifiable: it must be able to return true for at least one allowed state and false for at least one forbidden state. No external skill, map, or prior artifact is required.