agentleFS
faizkhairifaizkhairi/claude-code-blueprint/skills/tech-radar/SKILL.md

tech-radar

Skill73 starsChanged 4 months agoMITView on GitHub

MUST use when user asks 'what's new?', 'any updates?', 'latest versions?', 'breaking changes?', 'should we upgrade?', 'what changed in X?', or when starting a new project. Detects dependencies dynamically from `package.json` / `requirements.txt` / `go.mod` / `composer.json` first, then reports per-package: latest version (vs. installed), breaking changes since installed version, security advisories (CRITICAL/HIGH), and deprecation warnings. Falls back to a generic stack table only when no manifest file is found.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Parse arguments: If user specified a package/framework, focus on that.

    line 30
  2. Very specific:

    Search: "{package} CVE {current_year}" or "{package} security advisory"

    line 43
  3. Distinctive:

    Only report packages actually used in the active project (check the project manifest)

    line 76
  4. Distinctive:

    If checking all projects: deduplicate (report each package once with all affected projects)

    line 79

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Tech Radar: Stack Update Scanner

Checks for latest versions, breaking changes, deprecations, and security advisories across the user's core stack.

Core Stack to Monitor

Example only, replace with your own stack. The table below reflects one project's dependencies (a JS/TS stack). The skill detects your actual dependencies from the project manifest at runtime (package.json, requirements.txt, go.mod, composer.json, etc., see the description); this table is just a fallback of well-known packages to watch.

CategoryPackages
Frontendnuxt, vue, next, react, tailwindcss, formkit, pinia
Backend@nestjs/core, express, fastify
Databaseprisma, @prisma/client, knex, better-auth
Testingvitest, @vue/test-utils, @testing-library/react
Mobileexpo, react-native, nativewind
AIai (vercel ai-sdk), @ai-sdk/openai, @ai-sdk/anthropic
CLIcommander, chalk, ora, inquirer
Buildtypescript, tsup, turbo, vite
Cloud@aws-sdk/client-s3, @aws-sdk/client-ec2

Execution Steps

  1. Parse arguments: If user specified a package/framework, focus on that. Otherwise scan full stack.
  2. Check latest versions using WebSearch:
    • Search: "{package} latest version {current_year}"
    • Compare against currently installed version (check the project manifest: package.json, requirements.txt, go.mod, composer.json, etc.)
    • Flag major version bumps (potential breaking changes)
  3. Check for breaking changes:
    • For major version bumps: search "{package} v{new_major} migration guide"
    • Summarize key breaking changes that affect our patterns
    • Cross-reference against known patterns in MEMORY.md
  4. Check security advisories:
    • Search: "{package} CVE {current_year}" or "{package} security advisory"
    • Flag any HIGH or CRITICAL severity issues
  5. Check deprecations:
    • Search: "{package} deprecated features {current_year}"
    • Note any APIs we currently use that are deprecated

Output Format

## Tech Radar Report: {date}

### Upgrades Available
| Package | Current | Latest | Breaking? | Priority |
|---------|---------|--------|-----------|----------|
| nuxt    | 4.0.0   | 4.1.0  | No        | Low      |
| prisma  | 6.2.0   | 7.0.0  | YES       | High     |

### Breaking Changes (Action Required)
- **prisma 7.0**: No `url` in datasource block, driver adapter required [details]

### Security Advisories
- (none found / list any CVEs)

### Deprecation Warnings
- (none / list deprecated APIs we use)

### Recommendation
[1-2 sentences: upgrade now / wait / specific actions needed]

Smart Filtering

  • Only report packages actually used in the active project (check the project manifest)
  • Skip patch/minor version bumps unless they contain security fixes
  • Prioritize: Security > Breaking Changes > Major Upgrades > Minor Upgrades
  • If checking all projects: deduplicate (report each package once with all affected projects)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.