to-spec

Synthesizes conversation context into a structured spec and publishes it to the project issue tracker.

6|2|Updated May 6, 2026
One-click install
npx skills add https://github.com/sek788432/Stock-Back-Test-System --skill to-spec-sek788432
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: to-spec
Source: https://github.com/sek788432/Stock-Back-Test-System/tree/main/.agents/skills/to-spec
Command: npx skills add https://github.com/sek788432/Stock-Back-Test-System --skill to-spec-sek788432

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a long design conversation into a formal spec (PRD) is tedious and error-prone. This Skill converts the current conversation and codebase understanding directly into a structured spec document, without re-interviewing the user, and publishes it to the project's issue tracker. ## Core Features & Use Cases - Conversation-to-Spec Synthesis: Generates a complete spec from existing discussion context, including problem statement, solution, user stories, implementation decisions, testing decisions, and out-of-scope items. - Issue Tracker Publishing: Discovers the issue tracker from repository remotes or authenticated connectors and publishes the spec, with graceful local fallback when publishing is unavailable. - Test Seam Planning: Identifies existing or proposed testing seams in the codebase, preferring the highest-level seam and minimizing new ones. - Use Case: After discussing a new backtesting feature with an AI agent, invoke this Skill to produce a ready-for-agent spec issue on the project tracker without writing the document by hand. ## Quick Start Ask the agent to turn the current conversation into a spec and publish it to the project issue tracker.

Frequently Asked Questions about to-spec

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn a conversation into a product spec?▼

Invoke the Skill after discussing the feature with the agent. It synthesizes the existing conversation and codebase context into a spec with problem statement, user stories, implementation decisions, and testing decisions, without asking new interview questions.

How does the spec get published to an issue tracker?▼

The Skill discovers the tracker from repository remotes, user-provided links, or an authenticated connector, CLI, API, or browser. It publishes only after user authorization and verifies labels like ready-for-agent before applying them.

What happens if publishing to the issue tracker fails?▼

The Skill produces the complete spec locally or in the response and reports the publishing blocker. The generated work is never discarded when an authenticated publishing mechanism is unavailable.

Does the spec include file paths or code snippets?▼

No, implementation decisions avoid specific file paths and code snippets because they become outdated quickly. An exception exists for prototype snippets that encode decisions like state machines or schemas more precisely than prose.

When should I not use conversation-to-spec synthesis?▼

Avoid it when key decisions are still missing and would materially change the spec, since the Skill does not interview the user. Resolve those decisions in conversation first, then generate the spec.