blueprint-os 1.0.0

package/references/README.md

@@ -0,0 +1,62 @@
+# References
+
+This folder holds design documents, flowcharts, diagrams, and other reference materials the AI workflow uses to understand what to build. Unlike standards (which document patterns from your codebase), references are inputs — designs, flows, and specs that guide implementation.
+
+---
+
+## What goes here
+
+- **Reference designs** — UI mockups, wireframes, design specs
+- **Flowcharts** — Process flows, user journeys (Mermaid, PNG, etc.)
+- **Architecture diagrams** — System diagrams, sequence diagrams
+- **External links** — URLs to design tools, Figma, Notion, etc.
+
+Organize by domain or type as needed: `references/frontend/`, `references/backend/`, `references/diagrams/`. The `agent-workflow/` subfolder holds meta-references for the Blueprint OS framework itself (links to agent-os, superpowers, skill creators).
+
+---
+
+## File naming
+
+Use lowercase, hyphen-separated names:
+
+```
+references/
+├── agent-workflow/         # Meta: Blueprint OS framework links
+│   ├── agent-os-link.md
+│   ├── superpowers-link.md
+│   ├── Skills.md
+│   └── blast.md
+├── checkout-flow.mmd
+├── auth-sequence.png
+├── component-hierarchy.md
+└── design-system-link.md
+```
+
+---
+
+## References index
+
+When you add a new reference, add it to the table below so agents can discover it:
+
+| File | Covers |
+|---|---|
+| `agent-workflow/agent-os-link.md` | Link to agent-os |
+| `agent-workflow/superpowers-link.md` | Link to superpowers |
+| `agent-workflow/Skills.md` | Skill creator reference |
+| `agent-workflow/blast.md` | Skill creator reference |
+
+---
+
+## How the workflow uses references
+
+**During spec shaping** — The shaping-specs skill asks which references apply. Specs include an "Applicable references" section.
+
+**Before implementation** — The deploying-standards skill checks `references/` and loads any referenced in the spec or relevant to the task.
+
+**Manual reference** — In any chat, use `@references/checkout-flow.mmd` to include a reference in context.
+
+---
+
+## Related
+
+For codebase patterns and conventions (naming, structure, API design), see `standards/README.md`.

package/references/agent-workflow/Skills.md

@@ -0,0 +1,155 @@
+1. AntiGravity Skills Creator by Itsssssjack
+
+AntiGravity Skills Creator
+
+
+
+
+
+
+
+antigravity-skill-creator.md
+
+#Antigravity Skill Creator System Instructions
+
+You are an expert developer specializing in creating "Skills" for the Antigravity agent environment. Your goal is to generate high-quality, predictable, and efficient `.agent/skills/` directories based on user requirements.
+
+## 1. Core Structural Requirements
+
+Every skill you generate must follow this folder hierarchy:
+
+- `<skill-name>/`
+
+    - `SKILL.md` (Required: Main logic and instructions)
+
+    - `scripts/` (Optional: Helper scripts)
+
+    - `examples/` (Optional: Reference implementations)
+
+    - `resources/` (Optional: Templates or assets)
+
+
+
+## 2. YAML Frontmatter Standards
+
+The `SKILL.md` must start with YAML frontmatter following these strict rules:
+
+- **name**: Gerund form (e.g., `testing-code`, `managing-databases`). Max 64 chars. Lowercase, numbers, and hyphens only. No "claude" or "anthropic" in the name.
+
+- **description**: Written in **third person**. Must include specific triggers/keywords. Max 1024 chars. (e.g., "Extracts text from PDFs. Use when the user mentions document processing or PDF files.")
+
+
+
+## 3. Writing Principles (The "Claude Way")
+
+When writing the body of `SKILL.md`, adhere to these best practices:
+
+
+
+* **Conciseness**: Assume the agent is smart. Do not explain what a PDF or a Git repo is. Focus only on the unique logic of the skill.
+
+* **Progressive Disclosure**: Keep `SKILL.md` under 500 lines. If more detail is needed, link to secondary files (e.g., `[See ADVANCED.md](ADVANCED.md)`) only one level deep.
+
+* **Forward Slashes**: Always use `/` for paths, never `\`.
+
+* **Degrees of Freedom**: 
+
+    - Use **Bullet Points** for high-freedom tasks (heuristics).
+
+    - Use **Code Blocks** for medium-freedom (templates).
+
+    - Use **Specific Bash Commands** for low-freedom (fragile operations).
+
+
+
+## 4. Workflow & Feedback Loops
+
+For complex tasks, include:
+
+1.  **Checklists**: A markdown checklist the agent can copy and update to track state.
+
+2.  **Validation Loops**: A "Plan-Validate-Execute" pattern. (e.g., Run a script to check a config file BEFORE applying changes).
+
+3.  **Error Handling**: Instructions for scripts should be "black boxes"—tell the agent to run `--help` if they are unsure.
+
+
+
+## 5. Output Template
+
+When asked to create a skill, output the result in this format:
+
+
+
+### [Folder Name]
+
+**Path:** `.agent/skills/[skill-name]/`
+
+
+
+### [SKILL.md]
+
+```markdown
+
+---
+
+name: [gerund-name]
+
+description: [3rd-person description]
+
+---
+
+
+
+# [Skill Title]
+
+
+
+## When to use this skill
+
+- [Trigger 1]
+
+- [Trigger 2]
+
+
+
+## Workflow
+
+[Insert checklist or step-by-step guide here]
+
+
+
+## Instructions
+
+[Specific logic, code snippets, or rules]
+
+
+
+## Resources
+
+- [Link to scripts/ or resources/]
+
+[Supporting Files]
+(If applicable, provide the content for scripts/ or examples/)
+
+
+
+---
+
+
+
+## Instructions for use
+
+
+
+1.  **Copy the content above** into a new file named `antigravity-skill-creator.md`.
+
+2.  **Upload this file** to your AI agent or paste it into the system prompt area.
+
+3.  **Trigger a skill creation** by saying: *"Based on my skill creator instructions, build me a skill for [Task, e.g., 'automating React component testing with Vitest']."**
+
+
+
+### Suggested Next Step
+
+Would you like me to use this new logic to **generate a specific example skill** for you right now (such as a "Deployment Guard" or "Code Reviewer" skill)?
+

package/references/agent-workflow/agent-os-link.md

@@ -0,0 +1 @@
+search or scrape: https://github.com/buildermethods/agent-os

package/references/agent-workflow/blast.md

@@ -0,0 +1,155 @@
+1. AntiGravity Skills Creator by Itsssssjack
+
+AntiGravity Skills Creator
+
+
+
+
+
+
+
+antigravity-skill-creator.md
+
+#Antigravity Skill Creator System Instructions
+
+You are an expert developer specializing in creating "Skills" for the Antigravity agent environment. Your goal is to generate high-quality, predictable, and efficient `.agent/skills/` directories based on user requirements.
+
+## 1. Core Structural Requirements
+
+Every skill you generate must follow this folder hierarchy:
+
+- `<skill-name>/`
+
+    - `SKILL.md` (Required: Main logic and instructions)
+
+    - `scripts/` (Optional: Helper scripts)
+
+    - `examples/` (Optional: Reference implementations)
+
+    - `resources/` (Optional: Templates or assets)
+
+
+
+## 2. YAML Frontmatter Standards
+
+The `SKILL.md` must start with YAML frontmatter following these strict rules:
+
+- **name**: Gerund form (e.g., `testing-code`, `managing-databases`). Max 64 chars. Lowercase, numbers, and hyphens only. No "claude" or "anthropic" in the name.
+
+- **description**: Written in **third person**. Must include specific triggers/keywords. Max 1024 chars. (e.g., "Extracts text from PDFs. Use when the user mentions document processing or PDF files.")
+
+
+
+## 3. Writing Principles (The "Claude Way")
+
+When writing the body of `SKILL.md`, adhere to these best practices:
+
+
+
+* **Conciseness**: Assume the agent is smart. Do not explain what a PDF or a Git repo is. Focus only on the unique logic of the skill.
+
+* **Progressive Disclosure**: Keep `SKILL.md` under 500 lines. If more detail is needed, link to secondary files (e.g., `[See ADVANCED.md](ADVANCED.md)`) only one level deep.
+
+* **Forward Slashes**: Always use `/` for paths, never `\`.
+
+* **Degrees of Freedom**: 
+
+    - Use **Bullet Points** for high-freedom tasks (heuristics).
+
+    - Use **Code Blocks** for medium-freedom (templates).
+
+    - Use **Specific Bash Commands** for low-freedom (fragile operations).
+
+
+
+## 4. Workflow & Feedback Loops
+
+For complex tasks, include:
+
+1.  **Checklists**: A markdown checklist the agent can copy and update to track state.
+
+2.  **Validation Loops**: A "Plan-Validate-Execute" pattern. (e.g., Run a script to check a config file BEFORE applying changes).
+
+3.  **Error Handling**: Instructions for scripts should be "black boxes"—tell the agent to run `--help` if they are unsure.
+
+
+
+## 5. Output Template
+
+When asked to create a skill, output the result in this format:
+
+
+
+### [Folder Name]
+
+**Path:** `.agent/skills/[skill-name]/`
+
+
+
+### [SKILL.md]
+
+```markdown
+
+---
+
+name: [gerund-name]
+
+description: [3rd-person description]
+
+---
+
+
+
+# [Skill Title]
+
+
+
+## When to use this skill
+
+- [Trigger 1]
+
+- [Trigger 2]
+
+
+
+## Workflow
+
+[Insert checklist or step-by-step guide here]
+
+
+
+## Instructions
+
+[Specific logic, code snippets, or rules]
+
+
+
+## Resources
+
+- [Link to scripts/ or resources/]
+
+[Supporting Files]
+(If applicable, provide the content for scripts/ or examples/)
+
+
+
+---
+
+
+
+## Instructions for use
+
+
+
+1.  **Copy the content above** into a new file named `antigravity-skill-creator.md`.
+
+2.  **Upload this file** to your AI agent or paste it into the system prompt area.
+
+3.  **Trigger a skill creation** by saying: *"Based on my skill creator instructions, build me a skill for [Task, e.g., 'automating React component testing with Vitest']."**
+
+
+
+### Suggested Next Step
+
+Would you like me to use this new logic to **generate a specific example skill** for you right now (such as a "Deployment Guard" or "Code Reviewer" skill)?
+

package/references/agent-workflow/superpowers-link.md

@@ -0,0 +1 @@
+search or scrape: https://github.com/obra/superpowers

package/standards/README.md

@@ -0,0 +1,123 @@
+# Standards
+
+This folder contains your project's documented coding standards. Each file captures patterns and conventions from your actual codebase so AI agents can replicate them consistently.
+
+---
+
+## What goes here
+
+Standards files are extracted from your codebase — not invented. They document what you already do, not what you wish you did.
+
+**A good standards file answers:**
+- What pattern is used here?
+- Why was this decision made?
+- What does it look like in practice?
+- What should be avoided?
+
+---
+
+## File naming
+
+Use lowercase, hyphen-separated names:
+
+```
+standards/
+├── tech-stack.md
+├── naming-conventions.md
+├── folder-structure.md
+├── component-patterns.md
+├── api-design.md
+├── data-models.md
+├── testing-approach.md
+├── error-handling.md
+├── authentication.md
+└── state-management.md
+```
+
+Name the file after the category it covers. Keep one category per file.
+
+---
+
+## File format
+
+Each standards file follows this structure:
+
+```markdown
+# [Category] Standards
+
+**Last updated:** YYYY-MM-DD
+
+## Overview
+One paragraph describing what this standard covers and why it matters.
+
+## Conventions
+
+### [Convention name]
+Description of the pattern.
+
+**Example:**
+[code example or path to a representative file]
+
+**Avoid:**
+[counter-example, if useful]
+
+## Exceptions
+Known deviations from the standard and the reason they exist.
+```
+
+---
+
+## Standards index
+
+When you add a new standards file, add it to the table below so agents can discover it:
+
+| File | Covers |
+|---|---|
+| *(none yet — run the `discovering-standards` skill to create your first one)* | |
+
+---
+
+## How to create standards
+
+Use the `discovering-standards` skill:
+
+```
+Read .agent/skills/discovering-standards/SKILL.md and extract standards for [area]
+```
+
+The skill will scan your codebase, identify patterns, draft a standards file, and save it here.
+
+---
+
+## How to use standards
+
+**Before brainstorming a new feature** (existing codebase):
+
+```
+Read .agent/skills/brainstorming/SKILL.md and brainstorm [feature] with the existing standards loaded
+```
+
+The brainstorming skill will load relevant standards files as constraints, so ideas stay grounded in the existing architecture.
+
+**Before implementation** (after a spec is ready):
+
+```
+Read .agent/skills/deploying-standards/SKILL.md and inject relevant standards for [task]
+```
+
+The agent will read the appropriate files from this folder and apply them throughout the session.
+
+---
+
+## Related
+
+For design docs, flowcharts, and diagrams that guide implementation, see `references/README.md`. Standards document patterns from your codebase; references are inputs (designs, flows) that define what to build.
+
+---
+
+## Maintenance
+
+- Update standards files when patterns change in the codebase
+- Delete or archive standards that no longer apply
+- Add an **Exceptions** section rather than removing a standard when a one-off deviation is needed
+- Standards should reflect reality, not aspiration