mcpField
T
tech-advisor

tech-advisor

github.com/cyranobProductivity1062 installsUpdated 3w ago
Repository

About tech-advisor

A technology-advisory skill for people choosing or evaluating technology for a specific use case. It separates maturity assessments from product comparisons and requires current evidence from web search and page fetches.

Key features

  1. 01Maturity assessment or product comparison modes
  2. 02Evidence gathering through web search and fetch
  3. 03Current-version and source verification
  4. 04Recommendations that include costs and tradeoffs

Use cases

  1. 01Assess whether a technology is ready to adopt
  2. 02Compare products for a defined use case
  3. 03Prepare an evidence-backed technology recommendation

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/cyranob/web-forager --skill tech-advisor

After installing, type/tech-advisorin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

maturity-assessment.md
product-comparison.md
source-access.md

Details

From the project README

Tech Advisor

Make a current, evidence-backed technology recommendation for a specific user or team.

Choose one mode

  • Maturity assessment: one technology is being considered for adoption. Read maturity-assessment.md completely, then follow it.
  • Product comparison: two or more products, or a product category, must be chosen for a concrete use case. Read product-comparison.md completely, then follow it.

Use maturity assessment for “is this ready?” and product comparison for “which should I choose?” If intent does not settle the mode, ask one focused question.

Tools and evidence

Before using tools, read source-access.md completely.

Use available web search and URL-fetch tools. Prefer callable names ending in duckduckgo_search and web_fetch; client-added prefixes vary, so inspect the tools in the session. Without session tools, run the packaged CLI in an isolated environment:

uvx --python '>=3.10,<3.14' web-forager search "your query" --max-results 8 --output-format json
uvx --python '>=3.10,<3.14' web-forager fetch "https://example.com" --format markdown

If uvx cannot run packaged search, use ddgs without touching the current project environment:

uv run --no-project --python '>=3.10,<3.14' --with 'ddgs>=9.5.2' python - <<'PY'
from ddgs import DDGS
results = DDGS().text(query="your query", max_results=8)
for r in results:
    print(r["title"], r["href"], r["body"])
PY

If packaged fetch fails, use Jina Reader:

curl -s "https://r.jina.ai/https://example.com"

The workflow requires both search and fetch. If either capability is unavailable, state what is missing instead of recommending from stale knowledge.

Technology changes quickly. Use [current year] in queries, verify the exact current model or version, and prefer recent first-party specifications plus current independent evidence. Label estimates and inference.

Shared quality bar

  • Read every source used for a material comparison or recommendation.
  • Match evidence to the user's region, constraints, and use case.
  • Include total cost and meaningful tradeoffs, not only headline specifications.
  • Cite material claims near the text they support.
  • Take a position when the evidence supports one; state what would change it.

Comments

Markdown supported