ワンクリックでManusで任意のスキルを実行

kg-compliance

スター4

フォーク0

更新日2026年7月12日 15:58

Compliance posture rollup + redacted bulk export — joins the tamper-evident hash-chained audit ledger with governance node counts (Control/Policy/Risk/ ComplianceRequirement/ComplianceGate/Regulation/Assessment/Incident/Finding/... already ingested from CISO Assistant + the TRM portfolio-intelligence engine) into one auditor-facing view, and bulk-exports a redacted subgraph via the engine's own disclosure_level (Full/Skeleton/ExistenceOnly) redaction. Use for "what's our compliance posture", "is the audit chain intact", "export these controls redacted for an auditor", "how many open compliance gaps do we have".

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

Knuckles-Team

Knuckles-Team/agent-utilities

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

kg-compliance

graph_compliance is an aggregation layer over primitives that already exist — it adds no new compliance or redaction logic:

posture joins graph_audit's verify() report (the engine's SHA-256 hash-chained mutation-log check) with a node-count + status-breakdown rollup of the governance labels the CISO Assistant extractor (Control/Policy/Risk/ RiskAssessment/ComplianceAssessment/Framework/Asset/Incident/ SecurityException/Finding/Entity) and the TRM portfolio-intelligence engine (ComplianceRequirement/ComplianceGate/Regulation/Assessment) already ingest into the KG.
export bulk-exports a policy-redacted subgraph: given node_ids (a JSON array) or a read-only cypher query selecting an id column, it calls the engine's OWN explain_belief(node_id, disclosure_level) per id — the SAME per-node redaction primitive kg-epistemic-answer's why action / graph_epistemic use — and collects the results, bounded by limit. disclosure_level is Full (default) / Skeleton / ExistenceOnly.

Invoke

MCP: load_tools(tools=["graph_compliance"]), then graph_compliance(action="posture").
REST twin: POST /compliance with {"action": "posture"}.

Example

graph_compliance(action="posture")
// -> {"surface": "compliance", "audit_ledger": {"ok": true, "entries": 412, ...},
//     "node_counts": {"Control": 58, "ComplianceGate": 6, "Incident": 3, ...},
//     "status_breakdown": {"Control": {"satisfied": 51, "gap": 7}, ...}}

graph_compliance(action="export",
                  cypher="MATCH (n:Control) WHERE n.status = 'gap' RETURN n.id AS id LIMIT 50",
                  disclosure_level="Skeleton")
// -> {"surface": "compliance", "requested": 7, "exported": 7,
//     "entries": [{"node_id": "ciso_assistant_control:...", "belief": {"root": {...}}}, ...]}

Honest limitations

posture's node counts are a live snapshot of whatever the CISO Assistant / Egeria / TRM connectors have already ingested — this tool does not itself sync those sources (see the agent-utilities-source-integration skill for that).
export's redaction is exactly as strong as ExplainBelief's disclosure_level handling on the connected engine build — a build without the epistemic-redaction feature degrades disclosure_level to a no-op (full disclosure), same as kg-epistemic-answer's own documented limitation.

Delegation

If graph-os is reachable, prefer graph_orchestrate(action="execute_workflow") for a recurring posture report or a large bulk export rather than hand-driving the calls yourself.

このリポジトリの他の Skills

同じリポジトリ

ecosystem-validation

Knuckles-Team/agent-utilities

Turns the manual "validate a fleet package/skill, run its tests, delegate a grounded task to it, hunt for known bug-classes, and feed findings back into the KG" process into a SELF-HOSTED, delegation-ready capability the local LLM runs against ANY target — a fleet agent under agent-packages/agents/*, the agent-utilities package itself, or a universal-skill / agent-utilities skill. Composes existing primitives (graph_orchestrate execute_agent, graph_write, graph_feedback, pytest via the tier4 pattern, deterministic structural/bug-class scans) rather than re-implementing them. Use when asked to "validate <target>", "test this agent/skill end to end", "bug-hunt the fleet", "run ecosystem validation", or to set up continuous automated fleet validation via the loop engine or the scheduler.

2026-07-134

agent-utilities-self-evolution

Knuckles-Team/agent-utilities

Evolve the agent-utilities repository by implementing the latest research concepts against it. Orchestrates research-scanner → kg-ingest → comparative-analysis → SDD implementer into a unified pipeline. Queries the KG for hot topics, finds relevant papers, ingests them, runs comparative analysis, and generates SDD plans with constitution-mandated artifact requirements baked in. Can run as a background daemon (every 60 minutes) via the KG engine's evolution cycle. Triggers on "evolve agent-utilities", "run evolution pipeline", "find and implement research", "research-driven development", "auto-evolve", "evolution scan". Also includes AST-based wiring sweep for concept traceability, dead code detection, and import graph analysis. Triggers on "wiring sweep", "concept audit", "dead code analysis", "traceability check", "code health".

2026-07-124

kg-uql

Knuckles-Team/agent-utilities

Runs UQL — the epistemic-graph engine's native cross-modal Unified Query Language — a single pipelined text query that composes graph traversal, vector/ANN ranking, BM25 text search, relational (DataFusion) filtering, bi-temporal AS-OF/WINDOW, OWL reasoning, federation, and epistemic belief/evidence ops over ONE snapshot with no impedance mismatch between modalities. Use when a question spans more than one modality in one breath — "find docs about X, then rank by similarity to this vector, then only the ones live as of last month", "traverse citations then diversify the top results", "what supports this claim, discounted by our confidence at the time" — or whenever you'd otherwise chain several separate Cypher/SQL/vector calls by hand.

2026-07-124

kg-audit

Knuckles-Team/agent-utilities

Tamper-evident audit ledger (G23): verifies the engine's hash-chained durable-mutation audit log and reconstructs "what happened to entity X" from the KG's own :ToolCall provenance. Use for "verify the audit chain", "is our audit log tamper-evident", "has anything mutated entity X and in what order", "reverse-index the tool calls that touched this node".

2026-07-124

kg-epistemic-answer

Knuckles-Team/agent-utilities

Answers a question and returns its full epistemic justification, not just the row — calibrated confidence + provenance/evidence refs + bitemporal valid/tx time (the KnowledgeBatch "currency upgrade"), the belief's justification tree (Asserted / DerivedSupport / DerivedContradiction / BayesianUpdate), the acceptance capstone (believed? since when? on what evidence? what would flip it?), a bitemporal what-changed diff between two transaction times, and — when policy hid something — which rows were denied and why. Use when an answer alone isn't enough — "why do we believe this", "how confident are we and why", "what would invalidate this", "what changed between these two points in time", "why was this row filtered out".

2026-07-124

kg-incident

Knuckles-Team/agent-utilities

Browse the cross-layer Incident Brain: correlate recent hardware/os/orchestration/ service/network :HealthAnomaly rows into deduplicated :Incident nodes, list open incidents, and pull one incident's full detail. Read-only — proposes and executes no remediation. Use for "what's broken right now", "show me open incidents", "run a correlation pass", "what's the root-cause layer for this incident".

2026-07-124

name	kg-compliance
skill_type	skill
description	Compliance posture rollup + redacted bulk export — joins the tamper-evident hash-chained audit ledger with governance node counts (Control/Policy/Risk/ ComplianceRequirement/ComplianceGate/Regulation/Assessment/Incident/Finding/... already ingested from CISO Assistant + the TRM portfolio-intelligence engine) into one auditor-facing view, and bulk-exports a redacted subgraph via the engine's own disclosure_level (Full/Skeleton/ExistenceOnly) redaction. Use for "what's our compliance posture", "is the audit chain intact", "export these controls redacted for an auditor", "how many open compliance gaps do we have".
license	MIT
tags	["graph-os","compliance","audit","governance","redaction"]
tier	core
metadata	{"author":"Genius","version":"0.1.0"}

kg-compliance

graph_compliance is an aggregation layer over primitives that already exist — it adds no new compliance or redaction logic:

posture joins graph_audit's verify() report (the engine's SHA-256 hash-chained mutation-log check) with a node-count + status-breakdown rollup of the governance labels the CISO Assistant extractor (Control/Policy/Risk/ RiskAssessment/ComplianceAssessment/Framework/Asset/Incident/ SecurityException/Finding/Entity) and the TRM portfolio-intelligence engine (ComplianceRequirement/ComplianceGate/Regulation/Assessment) already ingest into the KG.
export bulk-exports a policy-redacted subgraph: given node_ids (a JSON array) or a read-only cypher query selecting an id column, it calls the engine's OWN explain_belief(node_id, disclosure_level) per id — the SAME per-node redaction primitive kg-epistemic-answer's why action / graph_epistemic use — and collects the results, bounded by limit. disclosure_level is Full (default) / Skeleton / ExistenceOnly.

Invoke

MCP: load_tools(tools=["graph_compliance"]), then graph_compliance(action="posture").
REST twin: POST /compliance with {"action": "posture"}.

Example

graph_compliance(action="posture")
// -> {"surface": "compliance", "audit_ledger": {"ok": true, "entries": 412, ...},
//     "node_counts": {"Control": 58, "ComplianceGate": 6, "Incident": 3, ...},
//     "status_breakdown": {"Control": {"satisfied": 51, "gap": 7}, ...}}

graph_compliance(action="export",
                  cypher="MATCH (n:Control) WHERE n.status = 'gap' RETURN n.id AS id LIMIT 50",
                  disclosure_level="Skeleton")
// -> {"surface": "compliance", "requested": 7, "exported": 7,
//     "entries": [{"node_id": "ciso_assistant_control:...", "belief": {"root": {...}}}, ...]}

Honest limitations

posture's node counts are a live snapshot of whatever the CISO Assistant / Egeria / TRM connectors have already ingested — this tool does not itself sync those sources (see the agent-utilities-source-integration skill for that).
export's redaction is exactly as strong as ExplainBelief's disclosure_level handling on the connected engine build — a build without the epistemic-redaction feature degrades disclosure_level to a no-op (full disclosure), same as kg-epistemic-answer's own documented limitation.

Delegation

If graph-os is reachable, prefer graph_orchestrate(action="execute_workflow") for a recurring posture report or a large bulk export rather than hand-driving the calls yourself.