Persona management
Use when the user wants to view, modify, or reset their Alfred persona, or when running /personaFrom its SKILL.md
npx -y skills add DrakeCaraker/alfred --skill persona-managementAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.9 KB, as published. Nobody here has run it
Persona Management
Manages the user's evolving persona stored in .claude/alfred-persona.yaml.
When to Use
- User runs
/personaor asks about their persona - User says "show my persona" or "what does Alfred know about me"
- User wants to adjust autonomy, explain level, or known concepts
Algorithm
View Persona
- Read
.claude/alfred-persona.yaml - If missing, say: "No persona file yet. It will be created automatically after your first
/self-improverun, or you can run/persona initto create one now." - Display the persona in a readable format:
=== Your Alfred Persona ===
Name: <name or "not yet named">
Domain: <primary> (+ <secondary list>)
Explain level: <level>
Autonomy: <autonomy>
Known concepts: <list or "none yet">
Custom rules: <count> rules learned
Corrections received: <count>
Last evolved: <date or "never">
Initialize Persona (/persona init)
- Read
.claude/.onboarding-state.jsonfor persona and coding_level - Read
.claude/alfred.yamlfor project type and tools - Create
.claude/alfred-persona.yamlfrom defaults:
name: ""
domain:
primary: "<from onboarding persona>"
secondary: []
explain:
level: "<from coding_level: beginner→novice, intermediate→intermediate, advanced→expert>"
known_concepts: []
behavior:
autonomy: suggest-then-do
commit_style: conventional
patterns:
preferred_tools: ["<from alfred.yaml formatting.tool>"]
avoided_tools: []
custom_rules: []
evolution:
correction_count: 0
last_evolved: null
Modify Persona
Users can adjust specific fields:
/persona autonomy just-do-it→ setbehavior.autonomy/persona explain expert→ setexplain.level/persona know SHAP cross-validation→ add toexplain.known_concepts/persona forget SHAP→ remove fromexplain.known_concepts/persona prefer ruff pytest→ add topatterns.preferred_tools/persona avoid jupyter→ add topatterns.avoided_tools/persona name "The Notebook Hater"→ setname
After any modification:
- Read current
.claude/alfred-persona.yaml - Apply the change
- Write back
- Confirm: "Persona updated: <field> → <new value>"
Reset Persona (/persona reset)
- Ask: "This will reset your persona to defaults. Your correction history will be preserved. Continue? (yes/no)"
- If yes, regenerate from defaults (same as init)
- Confirm: "Persona reset to defaults."
Important
- Never create the persona file without user action (init, self-improve, or explicit modify)
- The persona file is gitignored — it's local to each user
- Known concepts are never removed automatically — only the user can
/persona forget - Autonomy changes require explicit user request — auto-evolution only suggests