Frank
02883d3ed2
Copy of the legacy ~/.pi/agent/docs tree rebuilt as the command-center knowledge base: concept files promoted to path identity, index listings stripped of frontmatter, all wikilinks/relative links resolved, every checkable claim verified against the live fleet (Dankserver = Ryzen 7 7700X + RTX 3090; Strix Halo is Dankclaw), unverifiable claims tagged. kb-lint exits 0.
1.3 KiB
1.3 KiB
type, title, description, tags, timestamp, verified
| type | title | description | tags | timestamp | verified | ||||
|---|---|---|---|---|---|---|---|---|---|
| reference | How Pi Loads Skills | The discovery flow, progressive disclosure pattern, and system prompt integration for skills in pi. |
|
2026-07-18 | 2026-08-28 |
How the Pi Agent Loads and Uses Skills
Discovery Flow
- Pi scans all configured skill locations at startup
- Extracts names and descriptions from each
SKILL.md - Builds the system prompt with skill descriptions in XML format
- The LLM decides which skill(s) to activate based on the user's prompt
- When activated, the agent reads the full SKILL.md using the
readtool
Progressive Disclosure Pattern
System prompt (always in context):
- "Available skills: brave-search (Web search...), browser-tools (Browser automation...), ..."
User: "Search for information about React hooks"
Agent decides: activate brave-search
Agent reads: ~/.pi/agent/skills/brave-search/SKILL.md (full file)
Agent executes: {baseDir}/search.js "React hooks"
This is progressive disclosure: only descriptions are always in context, full instructions load on-demand.
Related
- Skills Specification — What the agent sees in the system prompt
- Skill Commands — The
/skill:nameoverride