How do I install the Staffdeck API Manage Resources skill?

Run npx skillmds@latest add openbmb/staffdeck-api-manage-resources in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Staffdeck API Manage Resources safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Staffdeck API Manage Resources?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Staffdeck API Manage Resources free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Staffdeck API Manage Resources?

OpenBMB (@openbmb) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Staffdeck API Manage Resources by openbmb

Name: Staffdeck API Manage Resources
Author: OpenBMB

Staffdeck API Manage Resources

Manage StaffDeck employee capability resources through Open API v1, including knowledge bases and cited search, general skills, HTTP tools, MCP servers and discovery, resource bindings, capability snapshots, and scheduled tasks. Use for adding, testing, publishing, binding, diagnosing, or scheduling an employee's executable capabilities.

OpenBMB 7a3e51d 3 files · 4.7 KB Updated Sep 17, 2026

File contents

Manage StaffDeck capability resources

Inspect before writing

Confirm the target agent_id and credential write access.
Fetch GET /agents/{agent_id}/resources and /capabilities.
Fetch live OpenAPI for payload schemas before creating HTTP tools, MCP servers, or scheduled tasks; those schemas may evolve.
Use the route inventory in references/resources-api.md.

Apply capability scope

Use general for capabilities the Harness may discover for ordinary tasks.
Use sop_specific when a capability must be hidden unless the current SOP node explicitly references it.
After creating or publishing a resource, bind it to the employee and re-read /capabilities to verify actual executability and any unavailable reason.
Do not assume a stored resource is executable merely because creation succeeded.

Knowledge

Prefer knowledge search when answering policy or factual questions and preserve returned citations. Use stable external_id values for repeatable entry upserts. Poll persistent Jobs for document ingestion and report failed stage and retryability.

Skills, tools, and MCP

Create as draft or disabled where supported, test first, then publish or enable. Never place plaintext secrets in skill files or logs; use secret references and verify that read responses remain masked. Run MCP discovery before sync, inspect the discovered tool schemas, and sync only the intended tools.

Scheduled tasks

Scheduled tasks use the same Harness v2 and SOP-specific rules as chat. Validate the employee's capability snapshot before activating a schedule. Prefer forbid concurrency unless overlapping runs are explicitly safe.

Mutating operations

Use a unique Idempotency-Key for retryable creates. Archive rather than physically delete. Do not update a resource owned by another account merely because it is visible through the gallery.

---name: staffdeck-api-manage-resourcesdescription: Manage StaffDeck employee capability resources through Open API v1, including knowledge bases and cited search, general skills, HTTP tools, MCP servers and discovery, resource bindings, capability snapshots, and scheduled tasks. Use for adding, testing, publishing, binding, diagnosing, or scheduling an employee's executable capabilities.---# Manage StaffDeck capability resources## Inspect before writing1. Confirm the target `agent_id` and credential write access.2. Fetch `GET /agents/{agent_id}/resources` and `/capabilities`.3. Fetch live OpenAPI for payload schemas before creating HTTP tools, MCP servers, or scheduled tasks; those schemas may evolve.4. Use the route inventory in [references/resources-api.md](references/resources-api.md).## Apply capability scope- Use `general` for capabilities the Harness may discover for ordinary tasks.- Use `sop_specific` when a capability must be hidden unless the current SOP node explicitly references it.- After creating or publishing a resource, bind it to the employee and re-read `/capabilities` to verify actual executability and any unavailable reason.- Do not assume a stored resource is executable merely because creation succeeded.## KnowledgePrefer knowledge search when answering policy or factual questions and preserve returned citations. Use stable `external_id` values for repeatable entry upserts. Poll persistent Jobs for document ingestion and report failed stage and retryability.## Skills, tools, and MCPCreate as draft or disabled where supported, test first, then publish or enable. Never place plaintext secrets in skill files or logs; use secret references and verify that read responses remain masked. Run MCP discovery before sync, inspect the discovered tool schemas, and sync only the intended tools.## Scheduled tasksScheduled tasks use the same Harness v2 and SOP-specific rules as chat. Validate the employee's capability snapshot before activating a schedule. Prefer `forbid` concurrency unless overlapping runs are explicitly safe.## Mutating operationsUse a unique `Idempotency-Key` for retryable creates. Archive rather than physically delete. Do not update a resource owned by another account merely because it is visible through the gallery.

Frequently asked questions