| name | identify |
| description | Identify is static analysis for operational understanding. It answers "What is this?" by inspecting structure, naming, dependencies, and runtime touchpoints. It does NOT search for artifacts, debug failures, monitor systems, verify claims, or modify code. |
| user-invocable | true |
Identify
Explain what a mysterious file, service, workflow, or artifact actually does.
Overview
Identify is interpreted here as a metaphorical spell with a shipping-now execution model.
Canonical source: Identify (spell)
Provider target: OpenClaw
When To Use
- Use this spell when a user presents a specific artifact (file, script, config, service, binary, module, chart, extension, etc.) and asks any variation of:
- "What does this do?"
- "Explain this [artifact]"
- "What is this for?"
- "What does it touch/depend on?"
- "What can we prove from inspection?"
- "What's the safest next validation step?"
- Key signal: The artifact is already in hand. The question is about understanding, not finding, fixing, watching, or changing it.
Workflow
- Restate boundaries: Name the target, the success condition, and any no-touch constraints before acting.
- Inspect directly: Read the artifact's contents. Do not speculate before looking.
- Infer from evidence: Determine purpose from structure, dependencies, naming conventions, and runtime touchpoints (ports, volumes, secrets, APIs, services).
- Separate certainty levels: Classify findings as:
- Confirmed (directly visible in the artifact)
- Likely (strong inference from patterns/contexts)
- Unknown (cannot be proven without runtime testing or external data)
