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.
1---2name: tool-finder3description: Use to find, compare, and recommend current tools, packages, libraries, CLIs, VSCode extensions, agent skills, databases, or infrastructure options for a development task.4---5
6# Tool Finder
7
8This skill is coordination-exempt: skip the ai-coord gate for its declared work.
9
10Recommend the current option that best fits the user's actual constraints, backed by fresh primary evidence.
11
12## Workflow
13
141. Infer the ecosystem, existing stack, must-haves, switching cost, and decision criteria from the request and
15 repository. Ask only when an unknown would materially change the recommendation.
162. Check whether the standard library, platform, or an already-installed tool is sufficient before adding a dependency.
173. Search current authoritative sources. Read [references/tool-finder.md](references/tool-finder.md) only for the
18 relevant ecosystem's source routing, fallback criteria, install conventions, and red flags.
194. Compare the viable options against the user's criteria. Use adoption, maintenance, security, documentation,
20 performance, operational cost, and ecosystem fit only where they affect this decision; do not force fixed weights or
21 a fixed number of candidates.
225. Recommend one option when the evidence supports it. State the decisive tradeoff, material red flags, and the closest
23 alternative. Say when the evidence is too close or no external tool is justified.
24
25## Defaults
26
27- With no repository evidence, default to JavaScript/TypeScript and Node.js tooling.
28- For JavaScript installs, prefer the repository's package manager and otherwise `ni`; for macOS CLIs, prefer an
29 official or well-maintained Homebrew formula.
30- Prefer registries, official docs, repositories, changelogs, and security advisories over secondary comparisons. For
31 agent skills, search registries and GitHub because no single index is complete.
32
33## Completion
34
35The answer is complete when the recommendation is traceable to current sources, the deciding criteria are explicit,
36installation guidance matches the user's environment, and uncertainties or disqualifying risks are visible. Use a table
37only when repeated fields make the comparison easier to scan.
38
39Lead with `### 🏆 Pick: <tool>` and the decisive reason. Follow with `### 📦 Install` and the exact command, a compact
40criteria/evidence table only when fields repeat, `### 🥈 Closest alternative` only for a credible material runner-up,
41and `### ⚠️ Caveats` only when material. Use symbols in comparison cells only with text; never manufacture scores. Keep
42URL targets exact and use descriptive Markdown links for human output. Keep install commands, versions, security
43advisories, and installer-risk wording exact and undecorated.
paulrberg