governancedeclare-agent-capability
Declares an agent capability statement for a bounded context.
Installation
Suivez les instructions du dépôt pour votre agent. Consultez les fichiers et dépendances avant l’installation.
Voir la source ↗GuidesInstructions
Governance: Declare Agent Capability
1. Context
This skill records a capability declaration for an agent or system, including scope and measures, so session admission can be audited against explicit ability statements.
2. Inputs
- context (required): Bounded context name (safe path segment).
- capability_id (required): Capability identifier (safe path segment).
- title (required): Short capability title.
- work_scope (required): Semicolon-delimited work scope entries.
- work_measures (required): Semicolon-delimited work measures entries.
- holder (optional): Holder/system identifier for the capability.
- valid_from (optional): ISO-8601 start timestamp.
- valid_until (optional): ISO-8601 end timestamp.
- notes (optional): Freeform notes.
- agent_type (optional): Agent type declaring the capability.
- agent_model (optional): Agent model identifier.
- role_assignment (optional): RoleAssignment for U.Work logging (default: Strategist).
- decisions (optional): Semicolon-delimited DRR ids/paths.
- timestamp_start (optional): ISO-8601 timestamp for deterministic output.
3. Outputs
-
runtime/contexts/<context>/capabilities/<capability_id>.capability.yaml
4. Procedure
- Validate inputs and ensure the target file does not already exist.
- Write the capability declaration YAML with scope and measures.
- Emit U.Work via
telemetry/log-workwhen available.
Exemples
Consultez les exemples du dépôt source.
Voir la source ↗Historique source
- Date d’indexation
- 2026-01-20
- Mise à jour de l’index
- 2026-01-26
- Branch
- main
Les dates concernent ce répertoire. Consultez le dépôt pour l’historique du code.
GitHub ↗chat Comments (0)
Sign in to join the discussion and leave a comment.
No comments yet. Be the first to share your thoughts!