Jarvis Refactor Planner 01

Plan low-risk refactors with seams, tests, and rollback points. Use when handling development work that needs repeatable steps, quality gates, and practical...

Security Scan

This is an instruction-only refactor planning skill whose declared purpose, inputs, and runtime instructions are internally consistent and request no credentials or installs.

Purpose & Capability

Name and description match the SKILL.md: a playbook for planning low-risk refactors. There are no unexpected binaries, env vars, or install steps required.

Instruction Scope

Instructions are high-level and limited to producing plans from supplied inputs (outcome, constraints, artifacts). The skill prompts users to provide artifacts (code, logs, screenshots); it does not instruct the agent to read system files, access env vars, or transmit data externally. Exercise caution about what you upload — the skill does not specify data-handling or retention rules.

Install Mechanism

No install spec and no code files — instruction-only skill. Nothing is written to disk or fetched during install.

Credentials

No environment variables, credentials, or config paths are requested. Requested inputs (artifacts, constraints) are proportional to a planning tool.

Persistence & Privilege

always is false and the skill does not request persistent system presence or modify other skills. Autonomous invocation is enabled by default but is not coupled with any elevated privileges or secret access here.

Assessment

This skill appears coherent and low-risk: it only provides planning instructions and asks for project artifacts. Before using it, avoid uploading secrets or full production logs/credentials — redact or supply minimal, representative snippets. Review any suggested commands or checklists before executing them in your environment. If you need automatic execution of suggested commands, prefer manual review or limit the artifacts you share.

Deliver a concrete, reusable workflow for development tasks.

Inputs

• Desired outcome and deadline
• Constraints (time, tools, risk tolerance)
• Available artifacts (code, docs, screenshots, logs)

Playbook

1. Define success and failure criteria in measurable terms.
2. Build a smallest-valid execution path before scaling effort.
3. Execute in checkpoints; record evidence at each checkpoint.
4. Apply quality gates before finalizing recommendations.
5. Return implementation-ready outputs and next actions.

Quality Gates

• Evidence-backed claims only.
• Explicit assumptions and tradeoffs.
• Reversible changes preferred for risky operations.
• Clear owner + ETA for each next step.
• Include a fallback if the primary plan fails.

Output Format

• Situation summary (5 lines max)
• Top findings (ranked by impact)
• Action plan (today / this week)
• Risks + mitigations
• Exact checklist or commands where useful

Example prompts

• "Use this skill to turn my messy notes into a production-ready plan."
• "Run this skill and give me a risk-first action sequence with acceptance checks."