$npx -y skills add PaulRBerg/agent-skills --skill find-toolUse to find, compare, and recommend current tools, packages, libraries, CLIs, VSCode extensions, agent skills, databases, or infrastructure options for a development task.
| 1 | # Find Tool |
| 2 | |
| 3 | Recommend the current option that best fits the user's actual constraints, backed by fresh primary evidence. |
| 4 | |
| 5 | ## Workflow |
| 6 | |
| 7 | 1. Infer the ecosystem, existing stack, must-haves, switching cost, and decision criteria from the request and |
| 8 | repository. Ask only when an unknown would materially change the recommendation. |
| 9 | 2. Check whether the standard library, platform, or an already-installed tool is sufficient before adding a dependency. |
| 10 | 3. Search current authoritative sources. Read [references/find-tool.md](references/find-tool.md) only for the relevant |
| 11 | ecosystem's source routing, fallback criteria, install conventions, and red flags. |
| 12 | 4. Compare the viable options against the user's criteria. Use adoption, maintenance, security, documentation, |
| 13 | performance, operational cost, and ecosystem fit only where they affect this decision; do not force fixed weights or |
| 14 | a fixed number of candidates. |
| 15 | 5. Recommend one option when the evidence supports it. State the decisive tradeoff, material red flags, and the closest |
| 16 | alternative. Say when the evidence is too close or no external tool is justified. |
| 17 | |
| 18 | ## Defaults |
| 19 | |
| 20 | - With no repository evidence, default to JavaScript/TypeScript and Node.js tooling. |
| 21 | - Prefer standard-library or platform primitives when adequate. |
| 22 | - For JavaScript installs, prefer the repository's package manager and otherwise `ni`; for macOS CLIs, prefer an |
| 23 | official or well-maintained Homebrew formula. |
| 24 | - Prefer registries, official docs, repositories, changelogs, and security advisories over secondary comparisons. For |
| 25 | agent skills, search registries and GitHub because no single index is complete. |
| 26 | |
| 27 | ## Completion |
| 28 | |
| 29 | The answer is complete when the recommendation is traceable to current sources, the deciding criteria are explicit, |
| 30 | installation guidance matches the user's environment, and uncertainties or disqualifying risks are visible. Use a table |
| 31 | only when repeated fields make the comparison easier to scan. |
| 32 | |
| 33 | Lead with `### 🏆 Pick: <tool>` and the decisive reason. Follow with `### 📦 Install` and the exact command, a compact |
| 34 | criteria/evidence table only when fields repeat, `### 🥈 Closest alternative` only for a credible material runner-up, |
| 35 | and `### ⚠️ Caveats` only when material. Use symbols in comparison cells only with text; never manufacture scores. Keep |
| 36 | URL targets exact and use descriptive Markdown links for human output. Keep install commands, versions, security |
| 37 | advisories, and installer-risk wording exact and undecorated. |