Menu
Use when extracting technical context from codebase and vision docs before planning implementation.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when producing product artifacts - epics, user stories, acceptance criteria, or analytics specs.
Use when defining product direction, vision document sections, or roadmap. Triggers on strategic product planning, vision creation, or vision document quality review.
Use when designing UI, choosing colors, typography, spacing, creating visual hierarchy, or making design decisions. Based on Refactoring UI by Wathan & Schoger.
Use when someone needs a plain-language explanation of how an existing feature or edge case behaves in the codebase. Triggers - non-technical stakeholder asks how something works, need code-informed functional explanation, need to understand rules or edge cases without implementation planning.
Use when a developer wants to go from rough idea to working code autonomously. Triggers - imperfect prompt, solo dev wants full pipeline, "just build it", idea to implementation without manual steps.
Use when creating a new agentic workflow skill. Triggers - need new multi-step orchestrated process, want to add workflow to agentic framework, building spec-driven pipeline.
| name | agentic:skill:gather-technical-context |
| description | Use when extracting technical context from codebase and vision docs before planning implementation. |
Extract actionable technical context from tech vision docs, product PRD, and codebase. Do NOT write implementation code.
.claude/_agentic_output/tech/vision/...).claude/_agentic_output/product/prd/{epicNumber}-EPIC-{epicName}/US-{usName}-{usNumber}.md).claude/_agentic_output/task/{epicNumber}-EPIC-{epicName}/US-{usName}-{usNumber}/technical-context.md
Epic ID: EPIC-{epicNumber}
User Story ID: US-{usNumber}
Document: Technical Context
Status: Draft | Ready
Owner: AI Architect (Context)
Last Updated: (ISO timestamp)
Inputs: (list exact paths consumed)
tech_stack: [lowercase identifiers of languages/frameworks/runtimes used]
The tech_stack field is required. List all languages, frameworks, and runtimes relevant to the project as lowercase identifiers. Examples: typescript, react, node, bun, ruby, rails, python, django, go, rust. This field is used by the skill-injection-protocol to determine which language skills to load at runtime.
| # | Section | Content |
|---|---|---|
| 1 | Summary of product intent | Bullet summary referencing AC-* |
| 2 | Relevant tech-vision constraints | List with refs to vision doc path + heading |
| 3 | Codebase touchpoints | Packages/modules/files impacted, patterns to follow, "do not touch" areas |
| 4 | Domain & data implications | Multi-tenancy, PII/secrets, GDPR lifecycle |
| 5 | Non-functional expectations | Observability, performance |
| 6 | Risks & mitigations | Security (OWASP), DX (tests, complexity), Operational (deploy/rollback) |
| 7 | Assumptions | Explicit assumptions plan will rely on |
| 8 | Open questions | Only blockers, keep concise |
| 9 | Notes for Technical Plan | Guidance about pitfalls and focus areas |
| 10 | Sources | External references (if used) |
/sync-issue after writing