perq is a skill in davepoon/buildwithclaude, last changed 28 Oct 2026. It can install more skills, run shell commands, reach the network and name web addresses — read the findings before installing.

From the author
Find verified free AI credits, free tiers, startup programs and student perks for LLM APIs, GPUs, voice, databases and dev tools through Perq's read-only search API or hosted MCP server. Use when the user asks what free credits they can get, the cheapest way to try a model or API, or which startup or student programs apply. Every answer carries the vendor's source link and a last-verified date.

At a glance

What it can touch

How much a skill can do, not whether it is risky.

Pattern check

Nothing flagged

That isn't proof the skill is harmless.

Commit 75c22ad · 29 Oct 2026

How the check works

Pattern check: nothing flagged

That isn't proof the skill is harmless.

Install

Each tab says whether it installs commit 75c22ad, the one we checked, or the latest version.

Read SKILL.md first
MIT
Licence
3.7k
Repo stars
Publisher
Files

What it can touch

From the files and frontmatter at commit 75c22ad. This is how much a skill can do, not whether it is risky.

Pattern check

Pattern check: nothing flagged · commit 75c22ad · 29 Oct 2026

We checked every text file in this skill, at commit 75c22ad on 29 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

  • https://perq.sh
  • https://perq.sh/mcp
  • https://perq.sh/api/search
  • https://perq.sh/api/offers/deepgram-200-credit
  • https://perq.sh/api/packs.json
  • https://perq.sh/agents

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses with warnings

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • Warning

      Fields outside the spec: category. Uploads to the Claude apps and API, and the spec's validator, reject the file; most agents ignore these fields. O1

      Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.

    • Note

      There is no license field, so readers can't tell whether they may reuse the skill. O2

      Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

  • Claude CodePasses

    Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

    • Note

      Claude Code ignores fields it doesn't know: category. O1

      Fix: Check the spelling against Claude Code's field list, or delete them.

  • Claude apps & API uploadFails

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Error

      Upload and packaging fail on fields outside the spec: category. O1

      Fix: Delete them, and keep your own data under metadata as text values.

    • Note

      The description is 397 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

      Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

  • OpenAI (Codex & API)Passes with warnings

    Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.

    • Warning

      Fields outside the spec: category. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1

      Fix: Delete them, or move your own data under metadata as text values.

  • VS Code & CopilotPasses

    VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.

    • Note

      VS Code ignores fields it doesn't support: category. O1

      Fix: Delete them unless another agent you target reads them.

SKILL.md

Files

1 file

PathSize
SKILL.md (opens in a new tab)4.3 KB

More from davepoon/buildwithclaude

SkillWhat it can touchPattern checkLicenceUpdated
  • Names web addresses
Pattern check: Nothing flaggedMIT11 Mar 2026
  • Names web addresses
Pattern check: Nothing flaggedMIT17 Feb 2026
  • Names web addresses
Pattern check: Nothing flaggedMIT14 Oct 2026
  • Runs shell commands
  • Names web addresses
Pattern check: Nothing flaggedMIT6 Mar 2026
  • Names web addresses
Pattern check: Nothing flaggedCC0 1.012 Aug 2026
  • Runs shell commands
Pattern check: Nothing flaggedMIT22 Aug 2026
All skills in davepoon/buildwithclaude

Other AI & ML engineering skills

Same category, most repo stars first.

SkillWhat it can touchPattern checkLicenceUpdated
  • Runs shell commands
Pattern check: Nothing flaggedMIT11 Aug 2026
  • Runs shell commands
  • Names web addresses
Pattern check: Nothing flaggedMIT11 Aug 2026
claude-apiReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

anthropics/skills

  • Touches credentials
  • +6 more

Pattern check: 1 item to reviewApache 2.0Updated 9 Oct 2026

  • Touches credentials
  • Downloads software
  • +5 more
Pattern check: 1 item to reviewApache 2.09 Oct 2026
  • Touches credentials
  • Runs shell commands
  • +3 more
Pattern check: Nothing flaggedApache 2.028 Oct 2026
benchmark-modelsCross-model benchmark for gstack skills. (gstack)

garrytan/gstack

  • Runs shell commands
  • +1 more

Pattern check: 1 item to reviewMITUpdated 26 Oct 2026

  • Runs shell commands
  • Pre-approves tools
Pattern check: 1 item to reviewMIT26 Oct 2026
  • Runs shell commands
  • Pre-approves tools
Pattern check: 1 item to reviewMIT27 Oct 2026