Install
$ agentstack add skill-lvcoi-solidjskills-solid-refactor-assistant ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
solid-refactor-assistant
Trigger
Use this skill when existing SolidJS code needs structural or behavioral changes with low regression tolerance.
Required Inputs
- Current behavior and invariants to preserve.
- Refactor objective and non-goals.
- Public interfaces that cannot break (props/events/routes/contracts).
- Validation surface: tests, manual scenarios, and performance constraints.
Workflow
- Capture baseline invariants as pass/fail statements.
- Break refactor into rollback-safe increments; each step must be independently verifiable.
- Preserve reactivity semantics: avoid effect-driven derivations and accidental dependency widening.
- Flag API changes and provide compatibility branch (adapter/deprecation note) when needed.
- Include targeted SSR/hydration and async-state checks where rendering paths changed.
- Output regression checklist and command sequence aligned to touched scope.
Failure Modes
- Invariants undefined: fail early and request explicit invariant list.
- Multi-axis refactor in one step: split into smaller ordered steps.
- Missing rollback path: output is invalid until rollback instructions exist.
- Refactor touches async/render logic without state matrix: add matrix before finalizing.
Output Contract
Return output matching RefactorPlanOutput schema at ../../skills/contracts/refactor-plan-output.schema.json with:
summary,invariants,stepwise_plan,risk_controls, androllback_strategy.verification_checklist,validation_commands.citations: each claim must cite normalizeddoc_identries.
Validation
node tools/scripts/validate-skills.mjs --skill solid-refactor-assistantnode tools/scripts/validate-output-contracts.mjs
References
../../references/solidjs-normalized/manifest.jsonl../../references/solidjs-normalized/taxonomy.json../../references/solidjs/reactivity-core.md../../references/solidjs/performance-ssr.md../../references/solidjs/async-data.md
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: lvcoi
- Source: lvcoi/solidJSkills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.