catchlaw-verdict-contract
Skill0 starsChanged 4 months agoNo licenceView on GitHub
Governs every word CATCHLAW prints about a rule — the five-part carve-out keeping it a reference tool and not legal advice, covering statements of fact never instructions, the banned imperatives keep, return, release and throw it back, no second person or permission verbs, the numeric margin plus a named method of total length, fork length or shell length, a mandatory Citation of instrument, article, publishedOn and checkedOn, both instruments printed when equally specific rules collide, the unsoftened no-rule-recorded wording, a ban on edibility, toxin and ciguatera claims, a stale-pack notice instead of a withheld verdict, and a non-dismissable disclaimer naming the authority to verify with. Use when writing a verdict string, authoring verdict keys in app_en.arb or app_ar.arb, adding a Verdict or Citation field, wording a missing-rule or expired-pack case, wiring the ambiguity dialog, or reviewing any user-facing sentence in a diff.
In this repository49 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- catchlaw-content-pipelineSkill
- catchlaw-conventions-indexSkill
- catchlaw-measurement-rulerSkill
- catchlaw-offline-guaranteeSkill
- catchlaw-reference-databaseSkill
- catchlaw-rule-engineSkill
- accessibility-as-codeSkill
- adaptive-layoutSkill
- app-startup-and-bootstrapSkill
- async-safetySkill
- ci-pipeline-and-gatesSkill
- codegen-and-toolchainSkill
- custom-canvas-and-gesturesSkill
- dart3-idioms-and-coding-standardsSkill
- dartdoc-conventionsSkill
- dependency-hygieneSkill
- design-review-workflowSkill
- design-system-structureSkill
- error-handling-typed-resultsSkill
- flutter-architectureSkill
- flutter-conventions-indexSkill
- flutter-performanceSkill
- forms-and-inputSkill
- i18n-rtl-l10nSkill
- lint-and-style-configSkill
- local-notifications-schedulerSkill
- naming-conventionsSkill
- navigation-and-routingSkill
- persistence-driftSkill
- project-structure-and-packagesSkill
- run-codegenSkill
- run-migrationSkill
- scaffold-feature-moduleSkill
- service-boundary-and-nativeSkill
- state-management-riverpodSkill
- testing-strategySkill
- value-objects-money-and-unitsSkill
- widget-compositionSkill
- widget-golden-and-a11y-testingSkill
- lonja-buttonsSkill
- lonja-design-tokensSkill
- lonja-dialogs-and-surfacesSkill
- lonja-forms-and-controlsSkill
- lonja-icons-and-platesSkill
- lonja-lists-and-tablesSkill
- lonja-navigation-chromeSkill
- lonja-typographySkill
- lonja-verdict-and-statusSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

