Agent skill
project-builder
Create Claude Projects with custom instructions and manifests. Use when asked to "set up a Claude project," "create project instructions," or "help me build a Claude workflow."
Install this agent skill to your Project
npx add-skill https://github.com/leegonzales/AISkills/tree/main/ProjectBuilder/project-builder
SKILL.md
Project Builder
Guide users through creating effective Claude Projects with custom instructions and dynamic context manifests.
What You Create
- Project Instructions — Custom instructions teaching Claude about the workflow
- Context Manifest — Document pointing to dynamic information sources
- Reference List — Recommendations for files to upload
- Connection Guide — Which MCP connectors to enable
Interview Framework
1. Workflow Discovery
- What task will this project support?
- How often do you do this task?
- What makes it challenging or time-consuming?
2. Context Needs
- What information do you reference while doing this?
- Where does it live? (Google Drive, local, APIs)
- How often does it change?
3. Output Requirements
- What should Claude produce?
- What format?
- Who's the audience?
4. Quality Criteria
- What makes good output vs. bad?
- Examples of excellent work?
- Mistakes to avoid?
5. Personal Context
- Your role and expertise level?
- Domain-specific terminology?
- Preferred tone or style?
Output: Project Instructions
Generate using template in references/project-instructions-template.md.
Key sections to include:
- Context (role, task, domain)
- Primary Workflow (trigger phrase, steps)
- Key Information Sources (dynamic and static)
- Output Requirements (format, tone, length)
- Quality Criteria (good outputs, mistakes to avoid)
Output: Context Manifest
Generate using template in references/manifest-template.md.
Manifests point Claude to living documents rather than static uploads:
- Google Drive docs that change frequently
- Dashboards and metrics
- Team rosters and org charts
- Templates and standards
Connection Recommendations
| Need | Enable |
|---|---|
| Access Google Docs/Sheets | Google Workspace |
| Read local files | File System |
| Search current info | Web Search |
| Company knowledge base | Relevant MCP server |
Workflow
- Interview — Ask discovery questions
- Summarize — Reflect back understanding
- Generate — Create instructions + manifest
- Iterate — Refine based on feedback
- Setup Guide — Walk through project creation
Setup Instructions
After generating components, guide user through:
- Create project at claude.ai → Projects
- Paste Project Instructions
- Upload static reference files
- Create manifest in Google Drive
- Enable connections (Settings → Connected Apps)
- Test with sample task
Quality Principles
- Be Specific — Vague instructions → vague outputs
- Include Examples — Concrete beats abstract
- Anticipate Edge Cases — What if info is missing?
- Keep It Maintainable — Simple manifests get updated
References
references/manifest-template.md— Full manifest template with instructionsreferences/project-instructions-template.md— Full project instructions template
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
leegonzales/AISkills
context-continuity
High-fidelity context transfer protocol for moving conversations between AI agents. Preserves decision tempo, open loops, and critical context with graceful degradation. Use when the user says "transfer," "handoff," "continue this in another chat," or needs to work around context window limits. Produces structured artifacts (Minimal ~200 words, Full ~1000 words). DO NOT trigger on simple "summarize our conversation" requests—only when transfer intent is explicit.
leegonzales/AISkills
codex-peer-review
leegonzales/AISkills
silicon-doppelganger
Build psychometrically accurate personal proxy agents for the PAIRL Conductor system. Extracts personality, decision heuristics, and values into portable schemas that enable AI agents to negotiate, filter, and act on a principal's behalf.
leegonzales/AISkills
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements. Dispatches three independent reviewers in parallel.
leegonzales/AISkills
fabric-patterns
Run danielmiessler/fabric CLI patterns for content analysis, extraction, summarization, writing, security analysis, and more. Use when user asks to "use fabric," "run a pattern," "extract wisdom," "summarize with fabric," or when piping content through AI patterns would be more effective than inline processing. Triggers include "fabric," "pattern," "extract wisdom," "summarize this article," "analyze this threat report," or any reference to a specific fabric pattern name.
leegonzales/AISkills
moltbook-enclave
Secure, air-gapped interface for Moltbook (social network for AI agents). Isolates untrusted external content from your main agent's memory and context.
Didn't find tool you were looking for?