opensite-ai/opensite-skills / ai-research-workflow
ai-research-workflow
VerifiedDeep research and AI workflow orchestration patterns for Octane. Use when working on brand guide generation, market analysis, competitive analysis, content brief, or any multi-step AI research pipeline. Covers the WorkflowBuilder/WorkflowStep orchestration system, Anthropic dual-model routing (Opus for research, Sonnet for generation), and the ai_tasks persistence pattern.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.7 KB |
| agents/openai.yaml | config | 506 B |
| examples/workflow-brief.example.md | markdown | 904 B |
| references/activation.md | markdown | 1.0 KB |
| scripts/validate_workflow_brief.pyexecutable | script | 874 B |
| templates/workflow-brief.md | markdown | 556 B |
examples/workflow-brief.example.md
View on GitHub# Workflow Brief
## Problem
- Add a competitive analysis workflow for restaurant neighborhood comparisons.
- Own the orchestration in `src/services/orchestration/` and the task lifecycle in `ai_tasks`.
## Inputs and Context
- Request body includes restaurant id, geography, and competitor count.
- Research step uses web search plus internal restaurant data.
- Output must be persisted so the CMS can poll progress.
## Step Plan
1. Gather competitor and geographic context.
2. Run a structured research phase with web search enabled.
3. Generate the final JSON report with Sonnet.
4. Persist completion state and attach artifacts.
## Output Contract
- JSON report with market summary, competitor list, and citations.
- Failure states store retryable vs permanent error details.
## Risks
- Missing citation attribution.
- Inconsistent task-state transitions.
- Unbounded token usage during research.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |