Generate strategy documents from completed Primr research. Use when the user wants AI, CX, security, or data strategy deliverables from an existing report.
Scanned 5/27/2026
Install via CLI
openskills install blisspixel/primr---
name: primr-strategy
version: "1.1.0"
description: "Generate strategy documents from completed Primr research. Use when the user wants AI, CX, security, or data strategy deliverables from an existing report."
metadata:
openclaw:
requires:
bins:
- primr-mcp
env:
- XAI_API_KEY
- GEMINI_API_KEY
os:
- linux
- darwin
- win32
mcp_server: primr
tools:
- generate_strategy
- run_qa
resources:
- primr://strategies/available
- primr://output/latest
---
# Primr Strategy Skill
## Conceptual Framework
Strategy generation is a post-research step. The report is the evidence base; the strategy output is a structured interpretation of that evidence, not a substitute for validation.
Use `primr://strategies/available` to discover the current strategy set and requirements instead of relying on static tables.
## Operational Capabilities
### 1. Inspect strategy options
Read `primr://strategies/available` to confirm available strategy IDs, expected effort, and whether a platform is required.
### 2. Generate the requested strategy
Before `generate_strategy`, call `estimate_strategy`, tell the user it incurs real API cost, get explicit approval, and pass `max_estimated_cost_usd` when available. Then call `generate_strategy` with a concrete report path and strategy type.
```text
generate_strategy(report_path="output/exampleco/report.md", strategy_type="customer_experience", max_estimated_cost_usd=0.25)
```
### 3. Validate output quality
Offer `run_qa` on the generated strategy or source report when the user wants review.
## Constraints
- Verify the report exists before generation.
- Ask for `platform` when generating `ai_strategy`.
- Do not promise exact runtime or price from the skill text; Primr behavior can evolve.
## Error Handling
- `report_not_found`: locate the report first or run research.
- `invalid_strategy_type`: read `primr://strategies/available` and retry.
- `missing_platform`: ask for the target platform.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.