Definition
Agent skill
An agent skill is a reusable, named agent capability: a packaged workflow with a description, a system prompt, an allowed set of tools, and triggers that decide when it runs. Instead of re-explaining a task every time, you define the skill once and the agent applies it on demand — turning ad-hoc prompting into a library of repeatable, governed capabilities.
Key takeaways
- An agent skill is a reusable, named capability: a description, system prompt, allowed tools, and triggers that decide when it runs.
- It turns ad-hoc prompting into a library — define a recurring task once and apply it consistently on demand.
- Because a skill names its allowed tools, it is also a capability boundary, not just a convenience.
- Planoda's skills run under propose/approve with tools clamped to the real registry, can be distilled from a session, and are shareable.
Skills are how agentic work becomes a reusable asset rather than a one-off conversation. A skill bundles the instructions for a recurring task ('triage incoming bugs,' 'draft a release note from merged PRs'), the specific tools the agent may use while doing it, and the conditions that fire it — a schedule, a label, an @mention. Linear's Skills and comparable 2026 features let teams build up a catalog of these so the same expertise applies consistently.
The governance dimension is essential: a skill encodes which tools an agent may call, so it is also a capability boundary, not just a convenience. Distilling a skill from a past session, or authoring one by hand, should clamp the allowed tools to ones that actually exist and route any consequential action through approval — otherwise a reusable skill becomes a reusable way to do damage at scale.
Planoda's agent skills run under propose/approve with their allowed tools clamped to the real tool registry, can be distilled from a finished session, and are shareable — a marketplace of governed capabilities — so a team's best workflows become safe, repeatable agent behavior rather than tribal prompt knowledge.
Related terms
- AI AgentAn AI agent is a software system that uses a large language model to pursue a goal across multiple steps — reading context, choosing tools, and taking actions — rather than answering a single prompt. In a work platform, agents triage issues, draft updates, and execute multi-step tasks as autonomous teammates, bounded by the permissions and approvals their operators set.
- Agentic WorkflowAn agentic workflow is a process in which one or more AI agents carry out a multi-step task with some autonomy — planning, calling tools, and acting on results in a loop — rather than a human driving each step. The agent decides the next action toward a goal, within boundaries its operator sets, turning AI from a single-response assistant into a worker.
- Coding agentA coding agent is an AI agent that takes a tracked issue all the way to a reviewed pull request — reading the codebase, planning a change, writing and running tests, and opening a PR a human merges. It is distinct from inline code completion: it owns a multi-step task end to end, under review, rather than suggesting the next line.
- Propose / Approve (AI Governance)Propose/approve is a governance pattern for autonomous software: instead of executing a consequential action directly, an AI agent emits it as a proposal that a human or policy must approve before it runs. It keeps fast, read-only work autonomous while gating destructive or irreversible operations — the practical way to give agents real power without surrendering control.
- Tool CallingTool calling is the capability that lets a language model invoke external functions — query a database, search the web, create a record — by emitting a structured request the surrounding system executes. Instead of only producing text, the model can take actions and pull in live data, turning it from a text generator into the reasoning core of an agent.