Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.getpioneer.dev/llms.txt

Use this file to discover all available pages before exploring further.

Skills are how you teach Pioneer reusable behavior. Without a skill, you repeat the same instructions in prompts: how your repo is organized, how a report should be formatted, which checks matter, which commands are safe, which output shape you expect. A skill packages that knowledge so it can be installed, reviewed, enabled, disabled, and reused. A skill can be small, like a writing style guide. It can also be more capable, with dependency checks and dynamic tools. Either way, treat it as part of the gateway’s working environment. Pioneer skills are compatible with the Agent Skills specification. In practice, that means a skill follows the open Agent Skills format built around a SKILL.md file plus optional scripts, references, assets, and supporting resources.

When Skills Help

Use a skill when the same behavior should show up again and again. A team might use a skill for repository conventions or support workflows. A researcher might use one for literature notes. A company might package an internal API helper. A solo user might create a skill for how they want documents summarized. If the instruction is one-off, put it in the thread. If it should become part of how Pioneer works in a workspace, make it a skill.

Where Skills Live

Skills are installed on a gateway and made available through the current workspace. That means your work gateway can have approved work skills, your home gateway can have personal skills, and your sandbox gateway can be where you test new or untrusted packages. One desktop app can connect to all of those gateways without sharing their skill state.

Enabled And Implicit Skills

Installed skills can be enabled or disabled. A disabled skill stays installed on the gateway, but agents should not use it. Enabled skills can be implicit or not implicit. An implicit skill is available automatically when Pioneer decides it is relevant. A not implicit skill is available only when you explicitly ask for it, for example by naming the skill in your prompt. Use implicit mode for trusted, general-purpose behavior that should naturally apply in many threads. Use not implicit mode for specialized, risky, noisy, or rarely needed skills.

Using Skills Safely

Installing a skill should not be treated like pasting a harmless prompt. Skills can include dynamic tools, dependency expectations, and workflow instructions that affect what agents do.
Skill tools run through the gateway, and tool runs are not sandboxed yet. Test unfamiliar skills on a sandbox gateway first.
Before trusting a skill, look at what it adds, what commands or services it expects, and whether it asks for broad file or network access. Then try it with a low-risk prompt before using it on important work.

Typical Flow

Install the skill, review validation results, fix missing dependencies if needed, confirm it is enabled in the current workspace, choose whether it should be implicit, and try it in a thread. If it behaves well, use it in tasks too. If it is too broad or surprising, disable it or make it not implicit.

Installing Skills

Add a skill package and read validation results.

Managing Skills

Enable, disable, update, or remove installed skills.

Skill Security

Decide what is safe to trust on a gateway.