mcpField
S
sdd-context-intake

sdd-context-intake

github.com/alejandro-cedeno-10Development0129 installsUpdated 17w ago
Repository

About sdd-context-intake

sdd-context-intake organizes source material into a structured brief for Spec-Driven Development. It is intended for requests grounded in tickets, documents, notes, files, or URLs, and highlights unresolved decisions without treating assumptions as facts.

Key features

  1. 01Collects supplied and referenced sources
  2. 02Delegates reading of large or multi-source material
  3. 03Organizes briefs into fixed sections
  4. 04Separates source facts from inferences
  5. 05Surfaces implementation-changing unknowns

Use cases

  1. 01Extracting goals from tickets or design docs
  2. 02Synthesizing requirements from named files or URLs
  3. 03Preparing a brief for clarification and feature workflows

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/alejandro-cedeno-10/agentic-sdd-kit --skill sdd-context-intake

After installing, type/sdd-context-intakein Claude Code to confirm it loaded.

Details

From the project README

Context intake for Spec-Driven Development

The user rarely starts with a clean one-line goal — they have a ticket, a doc, a thread, some files. This skill turns that raw material into the structured brief the SDD flow needs, WITHOUT guessing past what the sources actually say.

When to use

  • The user pastes a ticket / requirements / design doc / notes and says "do this".
  • The user names files, paths, or URLs as the source of truth.
  • Before sdd-clarify and before launching sdd-feature-flow, when the goal is buried in material rather than stated.

Procedure

  1. Collect every source the user gave, verbatim: pasted text, plus anything referenced — Read the named files, WebFetch the URLs, pull the ticket via its MCP/CLI if available. Do NOT stop at the pasted blurb if it points elsewhere.
  2. Delegate the reading when it's large or multi-source. Spawn a read-only agent (the Explore or general-purpose agent) to ingest the sources and return a compact digest — this keeps the bulky material out of the main context. For a single short paste, read inline.
  3. Synthesize a brief with exactly these sections, grounded ONLY in the sources (mark anything you inferred):
    • Goal — one or two lines: what to build and why (the "what/why", not the "how").
    • In scope / Out of scope — bullet lists drawn from the sources.
    • Constraints — data model, contracts, integrations, naming, limits the sources state.
    • Load-bearing unknowns — decisions the sources do NOT settle that would change code, contract, or template structure. These become the questions for sdd-clarify.
    • Sources — the files/URLs/tickets you actually read.
  4. Hand off. Feed the unknowns to sdd-clarify (ask the user), then pass the resolved brief as the goal (and any confirmed params) to the sdd-feature-flow workflow.

Rules

  • Ground everything in the sources. If the source doesn't say it, it's an unknown, not an assumption — surface it, don't invent it. (This is the same discipline the harness's clarity gate enforces later; catching it here is cheaper.)
  • Never begin writing a spec or code from this skill — its only output is the brief.
  • Keep the digest tight; the point is to compress source material into decisions and unknowns.

Comments

Markdown supported