Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Polyglot

ASecurity

Detect the stack in the touched files and run the right build, test, and lint commands for Python, Go, Rust, Node, Java, or Docker

54 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentstypescriptpythonrustgojavanodedockergit

Works with

cli

Security Analysis

A92/100
mediumInstalls packages at runtime which could introduce malicious dependencies

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add fordaaaa/panoply --skill polyglot --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Polyglot?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Polyglot
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fordaaaa-polyglot-panoply/badge)](https://www.skillsdirectory.com/skills/fordaaaa-polyglot-panoply)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: polyglot
description: Detect the stack in the touched files and run the right build, test, and lint commands for Python, Go, Rust, Node, Java, or Docker
---

Use this when a command needs to verify code and the repo's stack is unknown or mixed. Detect from the files and manifests actually present — never assume a runner, a package manager, or a test suite exists.

## Detection — manifests beat vibes

Check the touched area for these signals, in order. Several may match at once — that means polyglot, and each area reports its own stack.

- Python: `pyproject.toml`, `setup.cfg`, `requirements*.txt`, `uv.lock`, `.venv`
- Go: `go.mod`
- Rust: `Cargo.toml`
- Node/TypeScript: `package.json` (read `packageManager` + `scripts`; never assume `npm`)
- Java: `pom.xml`, `build.gradle*`
- Docker: `Dockerfile`, `compose*.yml`, `docker-compose*.yml` (note presence only — never build or start images unasked)

## Commands matrix

Prefer the repo's declared script over the raw tool (e.g. `scripts.test` before bare `pytest`). Probe cheaply (`--version` / `--help`) before running anything long.

| Stack | Test | Lint / typecheck | Notes |
|:--|:--|:--|:--|
| Python | `pytest -q` (or `uv run pytest -q`) | `ruff check .`, `mypy` only if configured | Activate `.venv` if present; never install packages unasked |
| Go | `go test ./...` | `gofmt -l .`, `go vet ./...` | No venv; module-aware via `go.mod` |
| Rust | `cargo test --quiet` | `cargo clippy -- -D warnings`, `cargo fmt --check` | First build may be slow — say so before running |
| Node/TS | `npm test -- --runInBand` (or pnpm/yarn per `packageManager`) | `npm run lint`, `npm run typecheck` if declared | Never run `npm install` unasked; respect lockfile |
| Java | `mvn -q test` or `./gradlew test` | `mvn -q checkstyle:check` only if configured | Wrapper script (`mvnw`/`gradlew`) wins over system binary |
| Docker | n/a | `docker compose config --quiet` to validate only | Validate, never `up` — starting services is a separate decision |

## Rules

- Read-only first: manifests and scripts before any execution.
- Cheapest probe first: `--version` before the suite, one package before `./...`.
- If no runner exists for a stack, report `no-framework` loudly. An unverifiable claim is not a satisfied one.
- Never touch `.github/workflows/`, CI config, lockfiles, or secrets to make a check pass.

## Report-back format (required)

End any verification block with one line per command run:

```
[polyglot: <stack> `<cmd>` → exit <n> · <summary line or "none found">]
```

If no command was run, the line reads `[polyglot: <stack> no command — <why>]`. This is the artifact that makes the skill checkable: a reader can point at the line and say whether the check ran.

Attribution

fordaaaafordaaaa
View sourceMore from fordaaaa →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →