How do I install the Skill0 Arde Runtime skill?

Run npx skillmds@latest add pingqlin/skill0-arde-runtime in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Skill0 Arde Runtime skill do?

Implement or review SKILL-0 ARD runtime contracts, append-only effect ledgers, dry-run policy gates, compensation recovery, and Evidence projections while preserving the existing Action/Rule/Directive decomposition. It is listed under Coding & Dev Tools on SkillMD.

Is Skill0 Arde Runtime safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Skill0 Arde Runtime?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Skill0 Arde Runtime free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Skill0 Arde Runtime?

pingqLIN (@pingqlin) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Skill0 Arde Runtime by pingqlin — Agent Skill

Name: Skill0 Arde Runtime
Rating: 4.2 (5 reviews)
Author: pingqLIN

File contents

SKILL-0 ARD Runtime Governance

Use this repository-scoped skill for work involving skill-runtime-contract.schema.json, runtime/, runtime migrations, recovery tests, governed adapters, or Evidence projections.

Required sequence

Read the nearest AGENTS.md and the approved ExecPlan.
Confirm audit/v4-phase0/repo-baseline.json matches the current git rev-parse HEAD or explicitly refresh the audit.
Read docs/ADR-0004-ard-plus-evidence.md, docs/ADR-0005-event-ledger.md, and docs/ADR-0006-runtime-boundary.md.
Preserve the semantic invariants in references/semantic-invariants.md.
Make one issue-sized, reversible change.
Run focused tests, failure-injection tests, and the repository regression suite.
Record validation evidence and unresolved risks in the ExecPlan.

Fail-closed rules

Do not evaluate arbitrary code or expressions from Skill documents.
Do not enable real execution by default.
Do not treat semantic similarity as authorization or safe replay.
Do not report rollback success without a terminal ledger event.
Do not use framework checkpoints as evidence that an external effect was reversed.
Stop and escalate when a write effect lacks durable identity, idempotency, or a recovery path.

Review

Use references/review-gates.md before marking an issue complete.

Frequently asked questions

Skill0 Arde Runtime