solution-researcherlisted

Orchestrates a simultaneous 7-AI competitive intelligence research round on any software product. Builds a capability-analysis prompt from a template, invokes the orchestrator engine, then invokes the consolidator skill to produce a Consolidated Intelligence Report (CIR). USE THIS SKILL whenever the user asks to research a software product, run competitive intelligence, benchmark a tool, or find out what a platform can do. Trigger when the user provides a product URL, names a specific software product and asks to research/analyze/evaluate it, or says "competitive intelligence", "capabilities report", "benchmark this tool", or "what can X do?". Supports any product domain (DevOps, PM tools, security, etc.) via pluggable domain knowledge files. If a domain file exists, evaluation criteria are appended to the prompt and used during consolidation. DEEP vs. REGULAR mode: If the user includes the keyword 'deep' in their request, use Deep Research modes on all platforms.
alo-exp/multai · ★ 2 · AI & Automation · score 63

Install: claude install-skill alo-exp/multai

# Solution Research Skill This skill orchestrates a full solution research workflow: build prompt, run 7 AIs, consolidate results, enrich domain knowledge, and optionally update the comparison matrix. Follow the phases below in order. --- ## Phase 0 — Extract Inputs Extract from the user's request: - **Primary URL** — the product's main website (required) - **Scope context** — one-line description of what the product does (required) - **Additional URLs** *(optional)* — docs, API reference, changelog, etc. - **GitHub / repository URL** *(optional)* — for open-source products - **Domain** *(optional)* — e.g., `devops-platforms`, `project-management`, `security-tools` - **Research depth** — if the user includes **`deep`**, set `MODE = DEEP`. Otherwise `MODE = REGULAR`. If Primary URL or Scope context is missing, ask the user before proceeding. If the user doesn't specify a domain, try to infer from the scope context. Check if `domains/{domain}.md` exists. --- ## Phase 1 — Build Prompt ### Step 1: Load prompt template Read `skills/solution-researcher/prompt-template.md`. The template contains a fenced code block with the raw prompt. Extract the prompt text from inside the code fence (between ``` markers). ### Step 2: Fill placeholders Replace these placeholders in the extracted prompt: - `[PRIMARY_URL]` → the product's URL - `[SCOPE_CONTEXT]` → one-line product description - `[ADDITIONAL_URLS]` → comma-separated extra URLs (or remove the line if none) - `[GITHUB_URL]`