Claude Skill

tool-finder

Imported from paulrberg/agent-skills/skills/tool-finder.

LLM Mart · 0 points · 0 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download paulrberg-agent-skills-skills_tool-finder-913232a.zip · 2 KB

paulrberg/agent-skills 94 7 forks MIT Updated 5h ago

Part of paulrberg/agent-skills — 42 skills

Install

skills CLI npx skills add https://github.com/PaulRBerg/agent-skills/tree/main/skills/tool-finder

Claude Code

claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install paulrberg-agent-skills@llmmart

Git git clone https://github.com/PaulRBerg/agent-skills.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole paulrberg/agent-skills collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Tool Finder

This skill is coordination-exempt: skip the ai-coord gate for its declared work.

Recommend the current option that best fits the user's actual constraints, backed by fresh primary evidence.

Workflow

Infer the ecosystem, existing stack, must-haves, switching cost, and decision criteria from the request and repository. Ask only when an unknown would materially change the recommendation.
Check whether the standard library, platform, or an already-installed tool is sufficient before adding a dependency.
Search current authoritative sources. Read references/tool-finder.md only for the relevant ecosystem's source routing, fallback criteria, install conventions, and red flags.
Compare the viable options against the user's criteria. Use adoption, maintenance, security, documentation, performance, operational cost, and ecosystem fit only where they affect this decision; do not force fixed weights or a fixed number of candidates.
Recommend one option when the evidence supports it. State the decisive tradeoff, material red flags, and the closest alternative. Say when the evidence is too close or no external tool is justified.

Defaults

With no repository evidence, default to JavaScript/TypeScript and Node.js tooling.
For JavaScript installs, prefer the repository's package manager and otherwise ni; for macOS CLIs, prefer an official or well-maintained Homebrew formula.
Prefer registries, official docs, repositories, changelogs, and security advisories over secondary comparisons. For agent skills, search registries and GitHub because no single index is complete.

Completion

The answer is complete when the recommendation is traceable to current sources, the deciding criteria are explicit, installation guidance matches the user's environment, and uncertainties or disqualifying risks are visible. Use a table only when repeated fields make the comparison easier to scan.

Lead with ### 🏆 Pick: <tool> and the decisive reason. Follow with ### 📦 Install and the exact command, a compact criteria/evidence table only when fields repeat, ### 🥈 Closest alternative only for a credible material runner-up, and ### ⚠️ Caveats only when material. Use symbols in comparison cells only with text; never manufacture scores. Keep URL targets exact and use descriptive Markdown links for human output. Keep install commands, versions, security advisories, and installer-risk wording exact and undecorated.

Files (agent-skills)

agents

openai.yaml 42 B

policy:
  allow_implicit_invocation: true

references

tool-finder.md 3.3 KB

# Tool Finder Reference

Use secondary comparisons to discover candidates or corroborate material claims. Match primary sources and criteria to
the ecosystem:

| Ecosystem                | Primary evidence and decision criteria                                                                                                                                                   |
| ------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| JavaScript/TypeScript    | npm, package docs, repository, changelog, advisories; types, ESM fit, bundle and dependency cost                                                                                         |
| Python                   | PyPI, package docs, repository; supported Python, typing, stdlib alternative, native-extension cost                                                                                      |
| Rust                     | crates.io, docs.rs, repository; safety, compile impact, `no_std` need, documentation                                                                                                     |
| Go                       | pkg.go.dev, standard library docs, repository; stdlib fit, dependencies, Go support, cancellation                                                                                        |
| CLI                      | official repository and package metadata; install path, structured output, startup, platform support                                                                                     |
| VS Code                  | Marketplace or Open VSX, repository, changelog; permissions, activation cost, editor compatibility                                                                                       |
| Databases/infrastructure | product and cloud-provider docs, migration and operations guidance; workload, backup, scaling, operational cost                                                                          |
| Agent skills             | [skills.sh](https://skills.sh), vendor docs, GitHub topics, GitHub code search for `path:SKILL.md`, and web search; valid metadata, portability, token use, license, bundled-script risk |

If evidence is otherwise close, prefer: stronger TypeScript support then smaller bundle then recency; Python or Go
standard library, then typed/current Python support or fewer dependencies with idiomatic cancellation; safer,
better-documented Rust; simpler-install, structured-output CLIs; and agent skills with progressive disclosure and fewer
execution risks.

Treat a credible advisory, unsupported platform, stale or missing documentation, disruptive release churn, excess
dependencies or bundle size, weak maintenance, excessive editor permissions, or unsafe bundled scripts as a material red
flag only when evidence and the user's environment make it consequential.

## Installation guidance

For a private JavaScript package (`"private": true`), install into dependencies (`ni package-name`, never `ni -D`);
translate to the repository's package manager when it has one.

Suggest an official installer script only after the user accepts its risk. Confirm the target package and environment
before giving the exact command.

SKILL.md 2.7 KB

---
coordination: exempt
name: tool-finder
description:
  Use to find, compare, and recommend current tools, packages, libraries, CLIs, VSCode extensions, agent skills,
  databases, or infrastructure options for a development task.
---

# Tool Finder

This skill is coordination-exempt: skip the ai-coord gate for its declared work.

Recommend the current option that best fits the user's actual constraints, backed by fresh primary evidence.

## Workflow

1. Infer the ecosystem, existing stack, must-haves, switching cost, and decision criteria from the request and
   repository. Ask only when an unknown would materially change the recommendation.
2. Check whether the standard library, platform, or an already-installed tool is sufficient before adding a dependency.
3. Search current authoritative sources. Read [references/tool-finder.md](references/tool-finder.md) only for the
   relevant ecosystem's source routing, fallback criteria, install conventions, and red flags.
4. Compare the viable options against the user's criteria. Use adoption, maintenance, security, documentation,
   performance, operational cost, and ecosystem fit only where they affect this decision; do not force fixed weights or
   a fixed number of candidates.
5. Recommend one option when the evidence supports it. State the decisive tradeoff, material red flags, and the closest
   alternative. Say when the evidence is too close or no external tool is justified.

## Defaults

- With no repository evidence, default to JavaScript/TypeScript and Node.js tooling.
- For JavaScript installs, prefer the repository's package manager and otherwise `ni`; for macOS CLIs, prefer an
  official or well-maintained Homebrew formula.
- Prefer registries, official docs, repositories, changelogs, and security advisories over secondary comparisons. For
  agent skills, search registries and GitHub because no single index is complete.

## Completion

The answer is complete when the recommendation is traceable to current sources, the deciding criteria are explicit,
installation guidance matches the user's environment, and uncertainties or disqualifying risks are visible. Use a table
only when repeated fields make the comparison easier to scan.

Lead with `### 🏆 Pick: <tool>` and the decisive reason. Follow with `### 📦 Install` and the exact command, a compact
criteria/evidence table only when fields repeat, `### 🥈 Closest alternative` only for a credible material runner-up,
and `### ⚠️ Caveats` only when material. Use symbols in comparison cells only with text; never manufacture scores. Keep
URL targets exact and use descriptive Markdown links for human output. Keep install commands, versions, security
advisories, and installer-risk wording exact and undecorated.