Coding_Corgi_flow

Create or complete a CorgiSpec planning package and synchronize one GitHub parent issue plus Task Group child issues. Use when proposing a change whose normalized tracking provider is GitHub.

Create or complete a CorgiSpec planning package and optionally synchronize GitLab issues. Use when proposing a new change or finishing an existing change whose normalized tracking provider is GitLab or none.

Execute or resume a CorgiSpec Run Contract v2 one Task Group at a time through the canonical corgispec loop CLI. Use when starting, continuing, fixing, committing, recovering, or finalizing an implementation run; never write loop state or evidence artifacts directly.

Implement exactly one pending Task Group from a CorgiSpec change and optionally synchronize GitLab progress. Use when applying a change whose normalized tracking provider is GitLab or none.

Validate and archive a completed CorgiSpec change, extract durable knowledge, and optionally close GitLab tracking. Use when archiving a change whose normalized tracking provider is GitLab or none.

Compare fresh CorgiSpec planning, implementation, Git, and run evidence and close only implementation gaps through the canonical converge CLI. Use after implementation or review when deciding whether a change is converged, planning needs update, or a new append-only Task Group is required.

Implement exactly one pending Task Group from a CorgiSpec change and synchronize GitHub progress. Use when applying a change whose normalized tracking provider is GitHub.

Validate and archive a completed CorgiSpec change, extract durable knowledge, and close GitHub tracking. Use when archiving a change whose normalized tracking provider is GitHub.

Human QA gate between review and archive — classifies change, routes to QA atoms, assembles evidence report.

Reconcile an existing CorgiSpec planning package after intent, requirements, scenarios, design, or task sequencing changes. Use when the user asks to update or realign an existing change while preserving implementation boundaries, task completion truth, OpenSpec 1.6 artifact paths, and strict readiness.

Human QA gate between review and archive — classifies change, routes to QA atoms, assembles evidence report.

Collect structured review findings for the current Run Contract v2 attempt without a human gate or filesystem writes. Use inside corgispec-loop after verification and return findings for the canonical loop submit command.

Collect structured review findings for the current Run Contract v2 attempt without a human gate or filesystem writes. Use inside corgispec-loop after verification and return findings for the canonical loop submit command.

Assess whether an existing CorgiSpec change is safe to implement by combining deterministic `corgispec ready` checks with a read-only cross-artifact semantic review. Use before apply or loop execution, after planning edits, or whenever proposal, requirements, scenarios, design, and tasks may disagree.

Investigate a CorgiSpec change, its planning context, implementation state, and optional GitLab tracking without modifying anything. Use for read-only exploration when the normalized tracking provider is GitLab or none.

Investigate a CorgiSpec change, its planning context, implementation state, and GitHub tracking without modifying anything. Use for read-only exploration when the normalized tracking provider is GitHub.

Review one completed CorgiSpec Task Group, gather quality evidence, and synchronize a GitHub approval decision. Use when reviewing a change whose normalized tracking provider is GitHub.

Review one completed CorgiSpec Task Group, gather quality evidence, and optionally synchronize a GitLab approval decision. Use when reviewing a change whose normalized tracking provider is GitLab or none.

Verify completed CorgiSpec Task Groups against tests, builds, linting, and returned planning requirements, with optional GitHub or GitLab evidence posting. Use after apply and before human review.

Extract reusable patterns and session summaries from completed changes into wiki long-term memory.

Initialize the 3-layer memory structure (memory/ + wiki/) for cross-session AI continuity in a Corgi project.

API walkthrough — endpoint verification with auth pyramid, CRUD coverage, request/response validation, and edge case probing.

Backend logic walkthrough — traces call chain from real entry points, verifies data integrity across layers

CLI walkthrough — terminal-based verification of commands, flags, exit codes, pipes, and help output.

SBTM-style exploratory testing session — charter-driven, tour-guided, time-boxed human investigation

Smoke test gate — verifies the application launches and critical paths are accessible before deeper QA

UI walkthrough — real user path verification with screenshots, component state checks, keyboard navigation, and cross-browser testing

Answer human questions from Obsidian vault using early-stop retrieval with token budget enforcement.

Use when installing, updating, or verifying this repo's project-local Corgi GitFlow assets in a target project.

Validate memory health across 14 checks — freshness, size caps, broken links, extraction completeness — with severity levels and auto-fix routing.

Migrate existing project knowledge into the memory/wiki structure from docs, archived changes, agent configs, and vault files.

Initialize the 3-layer memory structure (memory/ + wiki/) for cross-session AI continuity in a Corgi project.