skill-z3-research

Other Community

Repo stars 435
Author repo nvim

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Research Z3/SMT tasks. Invoke for Z3-language research. Thin wrapper that delegates Z3 research to z3-research-agent subagent. T…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Trigger Conditions”, “Execution Flow”, “Stage 1: Input Validation”, “Stage 2: Preflight Status Update”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name skill-z3-research directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Trigger Conditions / Execution Flow / Stage 1: Input Validation” before expanding.

Boundaries And Review

Dependencies: It usually needs no extra API key, so start with a small validation task.
Permissions: Declared permissions include read / write / shell-exec; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: Other
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @benbrastmckie · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Guided setup
External API key: No requirement detected
Detected OS requirements: Unspecified
Runtime requirements: Unspecified
Detected file/system behavior: Read-only
Write / modify
Shell exec
Detected network behavior: Local-only
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview skill-z3-research.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# Z3 Research Skill

Thin wrapper that delegates Z3 research to `z3-research-agent` subagent.

## Trigger Conditions

This skill activates when:
- Task type is "z3"
- Research involves SMT solving or constraints
- Z3-specific research is needed

## Execution Flow

### Stage 1: Input Validation
Validate task_number exists.

### Stage 2: Preflight Status Update
Update status to "researching" BEFORE invoking subagent.

### Stage 3: Prepare Delegation Context
Include task_context, focus_prompt, metadata_file_path.

### Stage 4: Invoke Subagent
Use Agent tool with subagent_type: "z3-research-agent".

### Stage 4b: Self-Execution Fallback

**CRITICAL**: If you performed the work above WITHOUT using the Agent tool (i.e., you read files,
wrote artifacts, or updated metadata directly instead of spawning a subagent), you MUST write a
`.return-meta.json` file now before proceeding to postflight. Use the schema from
`return-metadata-file.md` with status value "researched".

If you DID use the Agent tool, skip this stage -- the subagent already wrote the metadata.

## Postflight (ALWAYS EXECUTE)

The following stages MUST execute after work is complete, whether the work was done by a
subagent or inline (Stage 4b). Do NOT skip these stages for any reason.

### Stage 5: Parse Subagent Return
Read the metadata file from `specs/{N}_{SLUG}/.return-meta.json`.

### Stage 6: Update Task Status (Postflight)
Update state.json and TODO.md based on result.

### Stage 7: Link Artifacts
Add research artifact to state.json. Update TODO.md per `@.claude/context/patterns/artifact-linking-todo.md` with `field_name=**Research**`, `next_field=**Plan**`.

### Stage 8: Git Commit
Commit changes with session ID.

### Stage 9: Return Brief Summary

## Return Format

Brief text summary (NOT JSON).

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> Trigger Conditions → Execution Flow → Stage 1: Input Validation → Stage 2: Preflight Status Update → Stage 3: Prepare Delegation Context → Stage 4: Invoke Subagent
terms    -> CRITICAL · Research · Plan · Thin wrapper that delegates Z3 research to z3-research-agent subagent. · If you DID use the Agent tool, skip this stage -- the subagent already wrote the metadata. · The following stages MUST execute after work is complete, whether the work was done by a subagent or inline (Stage 4b). · Brief text summary (NOT JSON).
files/cmd -> z3-research-agent · .return-meta.json · return-metadata-file.md · specs/{N}{SLUG}/.return-meta.json · @.claude/context/patterns/artifact-linking-todo.md · fieldname=Research · nextfield=Plan
body sha256 -> aa18ba4cb378

Decide Fit First

Design Intent

How To Use It

Boundaries And Review

Z3 Research Skill

Trigger Conditions

Execution Flow

Stage 1: Input Validation

Stage 2: Preflight Status Update

Stage 3: Prepare Delegation Context

Stage 4: Invoke Subagent

Stage 4b: Self-Execution Fallback

Postflight (ALWAYS EXECUTE)

Stage 5: Parse Subagent Return

Stage 6: Update Task Status (Postflight)

Stage 7: Link Artifacts

Stage 8: Git Commit

Stage 9: Return Brief Summary

Return Format

Discussion