Imported from rickardvh/agentic-workspace (generated/memory/python/_payload/.agentic-workspace/memory/skills/memory-consultation-and-residue/SKILL.md). Install upstream with npx skills add rickardvh/agentic-workspace --skill memory-consultation-and-residue. Copyright stays with the author.

Memory Consultation And Residue

Name: memory-consultation-and-residue
Author: rickardvh

Use the configured AW start --target . --task "<task>" --format json and known changed paths. Follow the decision packet. Use the directly delivered selected advisory_context; no-match needs no further Memory work.

Keep the useful conclusion with its smallest existing owner. Planning owns execution continuity, Verification owns proof, and repository decisions retain their deciding authority. A passing test does not establish a durable lesson or authorize a Memory write.

For a selected note or advisory fact, follow Memory Hygiene. Current native disposition requests preserve external source ownership and need an exact bounded human answer. Promotion additionally needs current receiving-owner admission of the complete lesson. If that admission is unavailable, preserve advisory value or expose reconciliation.

Do not create a record just to show consultation, archive the conversation, or revive retired summary/report/promotion commands. Report the selected source, useful lesson or no-signal result, and unresolved owner only when those facts help continuation.

# 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": "rickardvh-agentic-workspace-memory-consultation-and-residue", "kind": "skill", "name": "memory-consultation-and-residue", "description": "Distinguish current Memory selection, useful durable residue and stronger-owner work without making Memory a required closeout step.", "publisher": "rickardvh", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "github" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Distinguish current Memory selection, useful durable residue and stronger-owner work without making Memory a required closeout step." ], "primary": false, "metadata": { "source": { "provider": "github", "repository": "https://github.com/rickardvh/agentic-workspace", "path": "generated/memory/python/_payload/.agentic-workspace/memory/skills/memory-consultation-and-residue/SKILL.md", "ref": "4b35b55995191b6bcbaddaa539c2029442cdfa0d", "url": "https://github.com/rickardvh/agentic-workspace/blob/4b35b55995191b6bcbaddaa539c2029442cdfa0d/generated/memory/python/_payload/.agentic-workspace/memory/skills/memory-consultation-and-residue/SKILL.md", "key": "rickardvh/agentic-workspace/generated/memory/python/_payload/.agentic-workspace/memory/skills/memory-consultation-and-residue/SKILL.md" } }, "instructions": "# Memory Consultation And Residue\n\nUse the configured AW `start --target . --task \"<task>\" --format json` and known changed paths. Follow the decision packet. Use the directly delivered selected `advisory_context`; no-match needs no further Memory work.\n\nKeep the useful conclusion with its smallest existing owner. Planning owns execution continuity, Verification owns proof, and repository decisions retain their deciding authority. A passing test does not establish a durable lesson or authorize a Memory write.\n\nFor a selected note or advisory fact, follow [Memory Hygiene](../memory-hygiene/SKIL", "cost": { "context_tokens": 285 } }

memory-consultation-and-residue

About

Memory Consultation And Residue

Use it

Manifest

Reviews