Imported from ProfRandom92/comptext-sparkctl (.agents/skills/10_generated_artifact_policy/SKILL.md). Install upstream with npx skills add ProfRandom92/comptext-sparkctl --skill 10_generated_artifact_policy. Copyright stays with the author.

Agent Skill 10 - Generated Artifact Policy

Name: 10_generated_artifact_policy
Author: ProfRandom92

This skill records how Codex sessions should handle generated CompText artifacts.

Non-Commit Defaults

Generated runtime files are not automatically commit candidates:

reports/latest.json
reports/performance_baseline.json
artifacts/spark/*
Rust target/ outputs

Do not stage or commit generated reports unless the human explicitly approves the exact files.

Artifact Hygiene

Prefer validation commands that do not regenerate reports when the task does not require new artifacts.
Do not run agy-ct run or agy-ct benchmark during governance-only work.
Treat generated artifacts as evidence trail material, not source-of-truth implementation.
Preserve deterministic and replayable outputs; do not fake hashes or rewrite reports to satisfy a claim.

Claim Hygiene

Generated reports and handoff text may describe local validation results, deterministic packaging behavior, and tamper-sensitive checks when evidenced by commands. They must not claim production readiness, legal proof, forensic certainty, EU AI Act compliance, official SPARK compatibility, or autonomous approval.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

{ "ocm": "1", "id": "profrandom92-comptext-sparkctl-10-generated-artifact-policy", "kind": "skill", "name": "10_generated_artifact_policy", "description": "Records how Codex sessions should handle generated CompText artifacts.", "publisher": "ProfRandom92", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "github" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Records how Codex sessions should handle generated CompText artifacts." ], "primary": false, "metadata": { "source": { "provider": "github", "repository": "https://github.com/ProfRandom92/comptext-sparkctl", "path": ".agents/skills/10_generated_artifact_policy/SKILL.md", "ref": "720ac786969ce63a5586aa2e70b21e3bdbb746aa", "url": "https://github.com/ProfRandom92/comptext-sparkctl/blob/720ac786969ce63a5586aa2e70b21e3bdbb746aa/.agents/skills/10_generated_artifact_policy/SKILL.md", "key": "ProfRandom92/comptext-sparkctl/.agents/skills/10_generated_artifact_policy/SKILL.md" } }, "instructions": "# Agent Skill 10 - Generated Artifact Policy\r\n\r\nThis skill records how Codex sessions should handle generated CompText artifacts.\r\n\r\n## Non-Commit Defaults\r\n\r\nGenerated runtime files are not automatically commit candidates:\r\n\r\n- `reports/latest.json`\r\n- `reports/performance_baseline.json`\r\n- `artifacts/spark/*`\r\n- Rust `target/` outputs\r\n\r\nDo not stage or commit generated reports unless the human explicitly approves the exact files.\r\n\r\n## Artifact Hygiene\r\n\r\n- Prefer validation commands that do not regenerate reports when the task does not require new artifacts.\r\n- Do not run `agy-ct run` or `", "cost": { "context_tokens": 296 } }

10_generated_artifact_policy

About

Agent Skill 10 - Generated Artifact Policy

Non-Commit Defaults

Artifact Hygiene

Claim Hygiene

Use it

Manifest

Reviews