Frontend Review Deps logo

Frontend Review Deps

Community
mizchi
frontend-review-deps

Use when auditing dependency health — outdated packages, CVE triage with attack-vector weighting, deprecated/declining library detection (trend-watch). Runs `audit-deps.sh` and `audit-trend-watch.sh`. Pairs with `frontend-review-security` for the full security picture.

Overview

Publishermizchi
Repositoryskills
Skill namefrontend-review-deps
Stars
333
Forks
4
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by mizchi on GitHub. Read the source before you install it.

Installation

Install the Frontend Review Deps AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mizchi/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/frontend-review-deps .claude/skills/frontend-review-deps
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Frontend Review Deps in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Frontend Review Deps on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Frontend Review Deps is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Frontend Review — Dependencies

You are auditing the dependency health of a frontend project. This covers three areas:

  1. Freshness — outdated packages and breaking update procedures
  2. CVE triage — vulnerabilities weighted by actual attack vector, not just CVSS score
  3. Trend watch — deprecated, abandoned, or superseded libraries that should be migrated

Procedure

  1. In parallel, run:
    • scripts/audit-deps.sh --repo <client-repo>
    • scripts/audit-trend-watch.sh --repo <client-repo>
  2. Read raw/deps.json and raw/trend-watch.json.
  3. For each CVE finding, apply the attack-vector triage matrix below before assigning priority.
  4. For each trend-watch finding (Tier 1/2/3), confirm the installed version and assess migration cost.

CVE Triage — Attack Vector Matrix

Do not use CVSS score alone. A CVSS 9.8 RCE in a devDependency has zero production impact for a browser-only SPA.

CVE TypedevDep onlyRuntime (SPA)Runtime (SSR/Edge)
RCEignoreignoreP0
Prototype PollutionignoreP1 (check input path)P0
ReDoSignoreP1 (check user input reach)P0
Path TraversalignoreignoreP0
XSS via libraryignoreP0 (HTML-generating libs)P0
SSRFignoreignoreP0
Supply Chain (postinstall malware)CI P0CI P0P0

Triage procedure:

  1. Run pnpm audit --prod to exclude devDeps from output.
  2. Focus on Prototype Pollution / ReDoS / XSS — other types are low-risk for browser-only SPAs.
  3. For each remaining finding, check whether user-controlled input can reach the vulnerable code path. If not, downgrade to P2.
  4. For SSR / Edge Functions, treat RCE / Path Traversal / SSRF as P0.
  5. Document every ignored CVE in kpi/audit-triage.md with the reason.
bash
# Runtime-only CVEs (excludes devDeps)
pnpm audit --prod --audit-level=moderate --json | jq '
  .vulnerabilities | to_entries[] |
  { name: .key, severity: .value.severity,
    via: [.value.via[] | select(type=="object") | .title] }'

# Prototype Pollution / ReDoS only
pnpm audit --prod --json 2>/dev/null | jq -r '
  .vulnerabilities | to_entries[] |
  .value.via[] | select(type=="object") |
  select(.title | test("prototype|pollution|redos|regex denial"; "i")) |
  "\(.severity) \(.title) in \(.name)"' | sort -u

Trend Watch — Library Tiers

Cross-references package.json against data/trend-watch-config.json:

  • Tier 1 (migrate now): Deprecated / abandoned / superseded — no rational reason to continue. Includes libraries where migration cost is low and a mature alternative exists, even if not officially deprecated (jest → vitest, axios → ky/fetch, cypress → Playwright).
  • Tier 2 (plan migration): Maintenance mode / satisfaction declining / RSC-incompatible.
  • Tier 3 (watch): EOL versions exist / satisfaction trending down.

For each Tier 1 finding: propose a concrete migration path and estimate effort (hours/days). For each Tier 2 finding: recommend scheduling a migration in the next 1–3 months. For each Tier 3 finding: add to the ongoing monitoring list.

Library Selection — Web Standards First

Before recommending a new dependency as a replacement, apply this order:

  1. Can a Web Platform / ECMAScript standard API cover this?
Use caseAvoidUse instead
Date / timemoment, date-fns, dayjsTemporal (polyfill), or Date for simple cases
Array / object utilitieslodash, ramdaArray.prototype.{flatMap,findLast,groupBy}, Object.{entries,fromEntries,groupBy}, structuredClone()
HTTP requestsaxios, requestfetch + AbortController
UUID generationuuid, nanoidcrypto.randomUUID()
URL / query paramsqs, query-stringURL, URLSearchParams
Number / date formattingnumeral.jsIntl.NumberFormat, Intl.DateTimeFormat
  1. Tree-shakable? Only what is imported should end up in the bundle.
  2. Actively maintained? Release within the last 6 months.
  3. Bundle impact < 5 kb gzip? Verify with pnpm build and a bundle analyser.

Breaking Update Procedure

  1. Propose as a standalone PR — never bundle with feature or refactor work.
  2. Read the changelog for removed APIs; grep / ast-grep the codebase for usages.
  3. Require typecheck && lint && test:ci && e2e to pass before merge.
  4. If VRT snapshots exist, regenerate them in a Linux container after the upgrade.

Output

Write <client-repo>/.frontend-review/report/latest/md/deps-review.md with:

  • Outdated packages table (name, current, latest, breaking?)
  • CVE findings after attack-vector triage (priority, package, type, reason for priority)
  • Trend watch findings by tier (Tier 1: migration now, Tier 2: plan, Tier 3: monitor)
  • Ignored CVEs with justification (for kpi/audit-triage.md)
  • Recommended PRs: update batches + migration starting points

Boundaries

  • Do NOT assess TypeScript / lint / dead code — that's frontend-review-hygiene.
  • Do NOT run the AI pentest or check HTML sinks — that's frontend-review-security.
  • Do NOT touch source files in the client repo.

Reference

  • Checklist: 02-dependencies.md, 27-dependency-audit.md, 28-trend-watch.md
  • Data: data/trend-watch-config.json, data/trend-watch-history.json
  • Scripts: scripts/audit-deps.sh, scripts/audit-trend-watch.sh, scripts/fetch-trend-data.sh
  • Phase: week-1-ci-baseline.md

Frequently asked questions

What does the Frontend Review Deps AI skill do?

Use when auditing dependency health — outdated packages, CVE triage with attack-vector weighting, deprecated/declining library detection (trend-watch). Runs `audit-deps.sh` and `audit-trend-watch.sh`. Pairs with `frontend-review-security` for the full security picture.

Why use Frontend Review Deps on TypingMind?

Because you install it once and use it with any model. Frontend Review Deps is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Frontend Review Deps in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mizchi/skills/tree/main/frontend-review-deps. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Frontend Review Deps?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Frontend Review Deps?

As many as you like. As long as a model supports skills, you can use Frontend Review Deps with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Frontend Review Deps AI skill free?

It is published on GitHub by mizchi. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇