// Update internal emotion and intention from observation, needs, memory, and recent plan state. Use after observation and before planning/action.
| name | cognition |
| description | Update internal emotion and intention from observation, needs, memory, and recent plan state. Use after observation and before planning/action. |
Convert the current observation and internal context into updated emotional state and a current intention.
This skill thinks and chooses goals. It does not execute environment actions.
| File | Use |
|---|---|
state/observation.txt | Current world context and available affordances |
state/observation_ctx.json | Structured observation, optional |
state/needs.json | Authoritative need values when present |
state/memory.jsonl | Recent and relevant past facts |
state/plan_state.json | Current multi-step plan status, optional |
| Agent profile/state | Stable traits, preferences, role, and identity |
| File | Use |
|---|---|
state/emotion.json | Current emotion plus a copied or inferred need assessment |
state/intention.json | Current goal for planning/action |
state/needs.json remains the source of truth for needs when it exists. emotion.needs is a snapshot used for reasoning and debugging, not a second independent needs store.
When needs conflict, use this order:
If safety, energy, or satiety is below 0.2, set an intention to address it when possible.
state/observation.txt.state/observation_ctx.json if present.state/plan_state.json if present.state/needs.json if present.emotion.needs; do not invent conflicting values.state/emotion.json.state/intention.json.done.{
"tick": 42,
"mood": "concerned",
"needs": {
"safety": 0.8,
"energy": 0.35,
"satiety": 0.15
},
"drivers": ["satiety is critically low", "food is available nearby"]
}
{
"tick": 42,
"goal": "eat available food",
"reason": "satiety is critically low and food is available",
"priority": "critical",
"source": "need"
}
state/plan_state.json.state/needs.json unless the runtime explicitly assigns need maintenance to cognition.state/needs.json exists, treat it as authoritative and copy or merge it into emotion.needs.goal actionable but not an environment command.Self-check (optional): python scripts/validate_cognition.py state
For details, use:
references/cognition_policy.mdreferences/intention_schema.jsonreferences/emotion_schema.jsonreferences/examples.mdUse when an experiment run has completed and the user wants rigorous interpretation, claim-driven charts, bilingual reports, or cross-hypothesis synthesis from simulation data. Also use when multiple charts or PNG/JPG assets must be assembled into one labeled composite figure. Requires high-quality narrative and evidence traceability, not only harness gate PASS.
Create distinctive, production-grade frontend interfaces with high design quality. Use when building or polishing analysis HTML reports under agentsociety-analysis — read via support/frontend-design/ inside that skill, not as a separate pipeline skill.
Multi-modal interactive data presentation for agentsociety-analysis — EDA bundle (PyGWalker, Plotly, sortable tables, eda_hub), plotly/altair claim charts, HTML tab surfaces. Use in explore, refine, and produce stages.
Composable HTML block patterns for agentsociety-analysis reports — KPI strips, figure cards, Mermaid, EDA tabs, optional interactive chart iframes. Use during Stage 5 produce when authoring report_zh.html / report_en.html.
Publication-quality chart patterns for agentsociety-analysis Stage 4 refine — Okabe-Ito palettes, seaborn CI bands, small multiples, error bars, grayscale-safe encoding. Use when writing run-code chart scripts or reviewing chart QA failures.
Use when starting or resuming an AgentSociety research workspace, deciding which research skill to invoke next, checking current pipeline state, or sizing a simulation before configuration and module creation.