/manage-pragma
Manage Pragma Experts, Teams, Flows, Evaluations, Missions and Automations, and discover their Host resources through authorized pragma manage CLI commands.
$ npx -y skills add pqpo/pragma --skill manage-pragma --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/manage-pragma
Context preview
The summary Claude sees to decide when to auto-load this skill.
Manage Pragma Experts, Teams, Flows, Evaluations, Missions and Automations, and discover their Host resources through authorized pragma manage CLI commands.
SKILL.md
manage-pragma.SKILL.mdname: manage-pragma
description: Manage Pragma Experts, Teams, Flows, Evaluations, Missions and Automations, and discover their Host resources through authorized pragma manage CLI commands.
Manage Pragma
Use `pragma manage` through the Runtime's process tool. This version requires the current Execution's authorized command channel; loading this Skill does not grant access. If the command or endpoint is missing or revoked, report its diagnostic. Never edit authoritative Pragma storage.
Choose the relevant workflow
Read only the references needed for the user's task:
- [DSL](references/dsl.md): create or update Experts, ExpertTeams and their dependencies using file drafts.
- [Flow](references/flow.md): build or repair graphs through incremental typed draft operations.
- [Evaluation](references/evaluation.md): test an exact committed Flow and save an independent Evaluation.
- [Resources](references/resources.md): discover workspaces, home task presets and ready knowledge stores.
- [Missions](references/missions.md): create persistent tasks, query work, send follow-ups or interrupt them.
- [Automations](references/automations.md): save schedules and Host bindings, enable/disable, delete or reset continuity.
Read Resources before choosing Host bindings for a Mission or Automation. Use `pragma manage dsl resources list|read` for canonical DSL refs; Host store IDs and home presets are separate identities. Flow and Evaluation are independent transactions. Create tests only when requested. Persistent Missions are separate tasks and do not replace current Execution subagent lifecycle tools.
Command and approval rules
Read the relevant subcommand's `--help` for current fields. Pass bounded JSON using `--input FILE` or `--input -`, with request files in the authorized workspace. Use `--format json`, bounded pagination, and the exact draft or Project revision returned by the Host.
Shell permission does not approve publication or other managed mutations. Preserve Host approval; `input_required` returns control to the owning Execution, and the CLI cannot approve for the user. Reuse a stable `--request-id` UUID only with identical command and input to retrieve its original receipt. After uncertain completion inspect the receipt/state before issuing another mutation. On conflicts reread and explicitly reapply intended changes. Cancellation does not undo publication or accepted work. Explicit recovery preserves data, requires separate approval, and cannot take over a known foreign owner; subsequent publication still requires its own approval.
Read more
name: manage-pragma description: Manage Pragma Experts, Teams, Flows, Evaluations, Missions and Automations, and discover their Host resources through authorized pragma manage CLI commands.
Manage Pragma
Use `pragma manage` through the Runtime's process tool. This version requires the current Execution's authorized command channel; loading this Skill does not grant access. If the command or endpoint is missing or revoked, report its diagnostic. Never edit authoritative Pragma storage.
Choose the relevant workflow
Read only the references needed for the user's task:
- [DSL](references/dsl.md): create or update Experts, ExpertTeams and their dependencies using file drafts.
- [Flow](references/flow.md): build or repair graphs through incremental typed draft operations.
- [Evaluation](references/evaluation.md): test an exact committed Flow and save an independent Evaluation.
- [Resources](references/resources.md): discover workspaces, home task presets and ready knowledge stores.
- [Missions](references/missions.md): create persistent tasks, query work, send follow-ups or interrupt them.
- [Automations](references/automations.md): save schedules and Host bindings, enable/disable, delete or reset continuity.
Read Resources before choosing Host bindings for a Mission or Automation. Use `pragma manage dsl resources list|read` for canonical DSL refs; Host store IDs and home presets are separate identities. Flow and Evaluation are independent transactions. Create tests only when requested. Persistent Missions are separate tasks and do not replace current Execution subagent lifecycle tools.
Command and approval rules
Read the relevant subcommand's `--help` for current fields. Pass bounded JSON using `--input FILE` or `--input -`, with request files in the authorized workspace. Use `--format json`, bounded pagination, and the exact draft or Project revision returned by the Host.
Shell permission does not approve publication or other managed mutations. Preserve Host approval; `input_required` returns control to the owning Execution, and the CLI cannot approve for the user. Reuse a stable `--request-id` UUID only with identical command and input to retrieve its original receipt. After uncertain completion inspect the receipt/state before issuing another mutation. On conflicts reread and explicitly reapply intended changes. Cancellation does not undo publication or accepted work. Explicit recovery preserves data, requires separate approval, and cannot take over a known foreign owner; subsequent publication still requires its own approval.
Build portable agent teams across models and harnesses, with shared memory, skills, tools, and workflows — then bring them into Codex, Claude Code, or any AI system you build. 构建跨 harness 和模型的可移植 Agent Team，共享记忆、技能、工具和工作流，一次构建，接入 Codex、Claude Code 或任何 AI 系统。