devflow

Lock the full test inventory before any implementation code is written. Reads spec+plan+AC, writes ALL failing tests in a batch, emits a Test Inventory doc, and gates with user approval.

Post-launch setup for a new feature worktree — detect context, recall memories, and transition to brainstorming.

Post-launch setup for a new feature worktree — detect context, recall memories, and transition to brainstorming.

Use when you have a multi-ticket epic (many related tickets across repos) and want to work as many as possible in parallel without breaking dependencies, or need to know what is unblocked now — ingest the epic and its child tickets, build the dependency graph from both formal links and free-text "Dependencies" notes, compute a parallel wave schedule, then act as a persistent coordinator that spawns a session per workable ticket and re-verifies what unblocked as tickets finish.

Use when you have a multi-ticket epic (many related tickets across repos) and want to work as many as possible in parallel without breaking dependencies, or need to know what is unblocked now — ingest the epic and its child tickets, build the dependency graph from both formal links and free-text "Dependencies" notes, compute a parallel wave schedule, then act as a persistent coordinator that spawns a session per workable ticket and re-verifies what unblocked as tickets finish.

Hand off between phases of the devflow new-feature pipeline. Writes a frozen-state file, marks a chapter, sets the terminal title, gates on a one-click AskUserQuestion, then spawns a new session for the next phase via `mcp__ccd_session__spawn_task` so it shows up in the Claude Desktop sidebar with a deterministic title.

Hand off between phases of the devflow new-feature pipeline. Writes a frozen-state file, marks a chapter, sets the terminal title, gates on a one-click AskUserQuestion, then spawns a new session for the next phase via `mcp__ccd_session__spawn_task` so it shows up in the Claude Desktop sidebar with a deterministic title.

Run the full pre-push review pipeline — code review checks, self-review against CLAUDE.md, and a final report.

Run the full pre-push review pipeline — code review checks, self-review against CLAUDE.md, and a final report.

Use when you have a full spike, PRD, or long design doc and want a tight, scannable SUMMARY of it for a busy reviewer. Condenses the source into a super-short TLDR, one all-in-one diagram, the recommendation, spike goals, still-open options, open questions, open risks, the technical deltas (GraphQL / DB / query), additive migration, external dependencies, and feature-flag strategy, with a link back to the full doc. Clean team style, no emoji or tag overload. For the full spike itself use readable-doc-spike; for the content use write-spike.

Use when you have a full spike, PRD, or long design doc and want a tight, scannable SUMMARY of it for a busy reviewer. Condenses the source into a super-short TLDR, one all-in-one diagram, the recommendation, spike goals, still-open options, open questions, open risks, the technical deltas (GraphQL / DB / query), additive migration, external dependencies, and feature-flag strategy, with a link back to the full doc. Clean team style, no emoji or tag overload. For the full spike itself use readable-doc-spike; for the content use write-spike.

Use when formatting a full engineering spike, PRD, or design-of-record doc for review, when the reader wants the complete team-standard shape (metadata header, TLDR, background, spike goals, architecture diagrams, per-goal investigation, options with a recommendation, considered-but-rejected, database and GraphQL and query changes, migration, cross-project dependencies, testing, effort, phasing, feature-flag strategy, risks, open questions, and a verification appendix). Clean team style, no emoji or tag overload. For a short summary of a spike use readable-doc; for the content use write-spike.

Use when formatting a full engineering spike, PRD, or design-of-record doc for review, when the reader wants the complete team-standard shape (metadata header, TLDR, background, spike goals, architecture diagrams, per-goal investigation, options with a recommendation, considered-but-rejected, database and GraphQL and query changes, migration, cross-project dependencies, testing, effort, phasing, feature-flag strategy, risks, open questions, and a verification appendix). Clean team style, no emoji or tag overload. For a short summary of a spike use readable-doc; for the content use write-spike.

Recall relevant memories from Hindsight before starting a task. Injects past learnings, decisions, and context into the current session.

Recall relevant memories from Hindsight before starting a task. Injects past learnings, decisions, and context into the current session.

Reflect on the current session, extract learnings, and consolidate them into Hindsight for future recall.

Reflect on the current session, extract learnings, and consolidate them into Hindsight for future recall.

Create and render an Excalidraw diagram from a description or codebase analysis — exports to PNG via a pure-node pipeline (no browser/MCP), shows it inline via the Read tool, and embeds it in docs. Use when asked to diagram, visualize, or draw an architecture/flow, or when another skill needs a rendered diagram.

Create and render an Excalidraw diagram from a description or codebase analysis — exports to PNG via a pure-node pipeline (no browser/MCP), shows it inline via the Read tool, and embeds it in docs. Use when asked to diagram, visualize, or draw an architecture/flow, or when another skill needs a rendered diagram.

Create and render an Excalidraw diagram from a description or codebase analysis — exports to PNG via a pure-node pipeline (no browser/MCP), shows it inline via the Read tool, and embeds it in docs. Use when asked to diagram, visualize, or draw an architecture/flow, or when another skill needs a rendered diagram.