Install
$ agentstack add skill-lvcoi-solidjskills-solid-reviewer ✓ 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-reviewer
Trigger
Use this skill for PR/diff audits where findings must be prioritized and mapped to concrete remediation.
Required Inputs
- Diff or changed files.
- Runtime context (client, SSR, SolidStart server usage if applicable).
- Known risk constraints (performance budget, accessibility requirements, release urgency).
Workflow
- Triage by severity in strict order: correctness, performance, maintainability, accessibility.
- Validate reactive boundaries first: derivations vs effects, dependency explosion, stale closures.
- Evaluate control flow and async completeness (
loading,empty,error,success). - Check SSR/hydration and browser-only assumptions in render paths.
- Ensure every finding includes file reference and concrete fix direction.
- Return validation commands relevant to touched surface.
Failure Modes
- Missing diff context: fail and request files or patch.
- Findings without reproducible impact: downgrade to question or remove.
- Suggestions without file-level anchor: invalid until anchored.
- No findings detected: explicitly state "No findings" and list residual test gaps.
Output Contract
Return output matching ReviewOutput schema at ../../skills/contracts/review-output.schema.json with:
summary,findings,open_questions,validation_commands.findingsordered by severity and containingfile(andlinewhen available).citations: every standards claim must include normalizeddoc_id+claim.
Validation
node tools/scripts/validate-skills.mjs --skill solid-reviewernode tools/scripts/validate-output-contracts.mjs
References
../../references/solidjs-normalized/manifest.jsonl../../references/solidjs-normalized/taxonomy.json../../references/solidjs/review-checklist.md../../references/solidjs/control-flow.md../../references/solidjs/performance-ssr.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.