Skip to main content
Pages

Skill Packs

Standalone memory service for AI tools, with durable memory, evidence, team isolation, and MCP access.

Skill Packs

Skill packs package selected Dense-Mem knowledge into portable JSON. Use them for reusable skills such as workflows, project conventions, or operational patterns that should move between teams or profiles.

For exact tool schemas and artifact fields, see Technical Reference.

When To Use A Skill Pack

Use caseExample
Reuse a workflowExport a blog-writing workflow learned from project history.
Share operational knowledgeMove a deployment checklist from one profile to another.
Preserve support evidenceExport the facts plus supporting claims and fragments.
Review an external packInspect a pack before importing anything.

Do not use skill packs for secrets, credentials, or personal data that should not move between profiles.

Workflow

StepToolWrites memory?
Find candidatesfind_skill_pack_candidatesNo
Export selected itemsexport_skill_packNo
Inspect a packinspect_skill_packNo
Import a packimport_skill_packYes
Roll back an importrollback_skill_pack_importYes

inspect_skill_pack is the no-write review path. import_skill_pack creates an import ledger entry and can create or update claims and facts depending on mode, selected items, and conflict decisions.

Find Candidates

json
{
  "query": "blog writing workflow",
  "limit": 10
}

Candidates come from existing active facts and validated claims with supported skill-pack predicates.

Export A Pack

json
{
  "name": "blog-writing",
  "description": "Reusable blog-writing workflow",
  "fact_ids": ["fact_123"],
  "include_support": true
}

The export result includes:

FieldMeaning
canonical_jsonThe portable JSON artifact.
sha256Integrity hash for the canonical artifact.
filenameSuggested .skill-pack.json filename.

Keep include_support=true unless you intentionally need to omit source evidence.

Inspect Before Importing

json
{
  "artifact_json": "{...}",
  "expected_sha256": "..."
}

Inspection reports duplicates, conflicts, superseded matches, matching claims, and any decisions required before a trusted import can proceed.

For a remote artifact, use an HTTPS URL:

json
{
  "url": "https://example.com/blog-writing.skill-pack.json",
  "expected_sha256": "..."
}

Import Modes

ModeBehavior
reviewImports selected items as reviewable claims. It does not promote source facts to active facts.
trustedTreats the pack as trusted source material and can validate claims, promote source facts, or supersede local facts when decisions allow it.

Trusted URL imports require expected_sha256.

Example review import:

json
{
  "artifact_json": "{...}",
  "mode": "review"
}

Example trusted import with a conflict decision:

json
{
  "artifact_json": "{...}",
  "expected_sha256": "...",
  "mode": "trusted",
  "conflict_decisions": [
    { "index": 0, "action": "demote_to_claim" }
  ]
}

Supported conflict actions are:

ActionMeaning
import_anywayImport despite the local match or conflict.
skipDo not import that item.
supersede_localReplace conflicting local active facts.
demote_to_claimKeep source-fact material as a claim instead of an active fact.

Roll Back An Import

json
{
  "import_id": "import_123"
}

Rollback uses the import ledger. It aborts when affected graph entities changed after import, because reverting those changes could erase unrelated later work.