Vercel Prune

Reports stale Vercel PREVIEW deployments for a named frontend project — dry-run only, never deletes anything on its own. Use when the product owner asks to "check stale previews", "run vercel prune", "how many dead previews are there", "clean up Vercel previews", or as the nightly ops routine's second step. Wraps scripts/vercel-prune-previews.mjs with the open-PR-protected branch list computed fresh each run. --apply is a SEPARATE, human-confirmed action this skill never takes on its own — see Stage 3.

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add danybgoode/golden-frijoles --skill vercel-prune
Manual install
git clone --depth 1 https://github.com/danybgoode/golden-frijoles.git /tmp/golden-frijoles
mkdir -p ~/.claude/skills
cp -r /tmp/golden-frijoles/.claude/skills/vercel-prune ~/.claude/skills/vercel-prune

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# vercel-prune — nightly stale-preview report (dry-run by default, apply is human-gated)

> **Running this skill's scripts.** Each `node scripts/<name>.mjs <args>` below means, from the project root:
> `if [ -f scripts/<name>.mjs ]; then node scripts/<name>.mjs <args>; else npx -y @golden-frijoles/kit@0.45.0 <name> <args>; fi`
> The project's own copy always wins. The kit needs no install and copies nothing into the repo. If npx fails on
> the network or the registry (ENOTFOUND, ECONNREFUSED, ETIMEDOUT, E404, a proxy error), report **could not
> look: the kit is unreachable**, not a broken project, and offer to retry online or to copy the script into
> `scripts/`. This covers the scripts the kit carries (`frijoles-kit --list`). Any other `scripts/` command here is
> project tooling: if the project lacks it, say so and stop. Never re-implement a script's logic inline.
> If a script prints `GF-NEEDS-SETTING {"key",…}`, ask the user that question once, save the answer with
> `npx -y @golden-frijoles/kit@0.45.0 config set <key> <value>` (always the kit, never local-wins: a project
> may own an unrelated `scripts/config.mjs`), tell them they can change it later the same way, and run the
> script again if it exited 7.

> **This skill's scheduled/default action is ALWAYS a dry-run report.** `--apply` is a distinct,
> explicitly-requested action (Stage 3) that only runs when the product owner asks for it in the
Read the full skill on GitHub

Details

Skill name
vercel-prune
Path
.claude/skills/vercel-prune/SKILL.md
Repo updated
17 November 2026

FAQ

What does the Vercel Prune skill do?

Reports stale Vercel PREVIEW deployments for a named frontend project — dry-run only, never deletes anything on its own. Use when the product owner asks to "check stale previews", "run vercel prune", "how many dead previews are there", "clean up Vercel previews", or as the nightly ops routine's second step. Wraps scripts/vercel-prune-previews.mjs with the open-PR-protected branch list computed fresh each run. --apply is a SEPARATE, human-confirmed action this skill never takes on its own — see Stage 3.

How do I install the Vercel Prune skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add danybgoode/golden-frijoles --skill vercel-prune. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Related skills

Babysit PR

danybgoode/golden-frijoles

Advisory PR watch for a single open PR — retries flaky CI (re-runs failed workflow runs) and surfaces merge conflicts via one comment; never merges, never a required check. Use when the product owner asks to "babysit this PR", "check on open PRs", "retry flaky CI", "is this PR stuck", "why isn't this PR moving", or as the nightly ops routine's third step (once per open PR across the project's repos). Runs scripts/babysit-pr.mjs, which does the gh reads, the retry, and the comment post. A clean PR (no conflict, no failing checks) gets NO comment — this tool never adds nightly noise to a healthy

Git & Code ReviewIn 1 list

Build Order Sync

danybgoode/golden-frijoles

Regenerates Roadmap/00-ideas/BUILD-ORDER.md when it has drifted from the SSOT (each epic README's frontmatter status:) and opens a claude/ docs PR with the fix — never hand-edits the board. Use when the product owner asks to "sync the build order", "regenerate BUILD-ORDER.md", "check board drift", "is the build-order board stale", "open a build-order PR", or as the nightly ops routine's first step. Runs scripts/build-order-sync.mjs, which does the check, the regen, and (on real drift) the branch/commit/ push/PR — this skill just invokes it and reports the result.

Git & Code ReviewIn 1 list

Doc Hygiene

danybgoode/golden-frijoles

Keeps the always-read session-start docs (this project's AGENTS.md, Roadmap/WAYS-OF-WORKING.md, Roadmap/LEARNINGS.md, Roadmap/README.md poster) from re-bloating after the one-time de-noise sweep. Use when the product owner asks to "check doc hygiene", "measure LEARNINGS size", "is LEARNINGS bloated again", "run the doc hygiene report", or as the weekly Routine C hygiene pass. Runs scripts/doc-hygiene.mjs, reviews its flagged candidates against the source docs, and emits a dated advisory report. Never edits Roadmap docs — proposals only, the product owner or the builder hand-merges.

Writing & ContentIn 1 list

Yaml Master

jeremylongshore/claude-code-plugins-plus-skills

PROACTIVE YAML INTELLIGENCE: Automatically activates when working with YAML files, configuration management, CI/CD pipelines, Kubernetes manifests, Docker Compose, or any YAML-based workflows. Provides intelligent validation, schema inference, linting, format conversion (JSON/TOML/XML), and structural transformations with deep understanding of YAML specifications and common anti-patterns.

DevOps & Cloud

Setting Up Synthetic Monitoring

jeremylongshore/claude-code-plugins-plus-skills

This skill automates the setup of synthetic monitoring for applications. It allows Claude to proactively track performance and availability by configuring uptime, transaction, and API monitoring. Use this skill when the user requests to "set up synthetic monitoring", "configure uptime monitoring", "track application performance", or needs help with "proactive performance tracking". The skill helps to identify critical endpoints and user journeys, design monitoring scenarios, and configure alerts and dashboards.

DevOps & Cloud

Setting Up Log Aggregation

jeremylongshore/claude-code-plugins-plus-skills

This skill sets up log aggregation solutions using ELK (Elasticsearch, Logstash, Kibana), Loki, or Splunk. It generates production-ready configurations and setup code based on specific requirements and infrastructure. Use this skill when the user requests to set up logging infrastructure, configure log aggregation, deploy ELK stack, deploy Loki, deploy Splunk, or needs help with observability. It is triggered by terms like "log aggregation," "ELK setup," "Loki configuration," "Splunk deployment," or similar requests for centralized logging solutions.

DevOps & Cloud

Browse the most popular Claude skills, all devops & cloud skills, or write your own with the skills generator.