looply

Use to list, inspect or manage linked looply sessions from chat. Shows session details and resume commands.

Use to open a new session tab for a feature. Registers the session in session-links.json and provides the resume command for the new tab.

Use to review architecture and design independently. Identifies structural improvements, validates against existing ADRs, and verifies compliance with codebase design principles.

Use to execute structured code review like GitHub and CodeRabbit. Reviews code changes, classifies findings by severity and generates actionable suggestions. Formal delivery gate with approval checklist.

Use to prepare and validate a software release. Includes security, performance, monitoring, rollback and operability checklist. Final delivery gate before production deploy.

Use when a delivery story already exists and needs technical design, implementation, review and release preparation. Do not use before discovery and planning are complete.

Use for discovery work that turns a feature idea into a PRD. Do not use for story breakdown or implementation.

Use to diagnose problems in the app using looply artifacts (stories, specs, code graph, knowledge graph) as primary source, with deep dive into the codebase as fallback when artifacts are insufficient.

Use to classify bugs and issues by severity using looply artifacts as primary source. Recommends whether the problem requires formal investigation or immediate action.

Use to verify and sync context files (context-index, project-context, session-context, code-context) against the real codebase state.

Use to verify safety of git operations during active looply workflows. Blocks destructive commands and suggests safe alternatives.

Use to create new looply skills interactively. Generates SKILL.md cross-host, agents yamls, command help file and updates indices. Do not use for editing existing skills.

Use when the user asks what looply can do, how to start a workflow, which workflow to use, or how to continue a feature in Codex.

Use to discover available looply skills and workflows. Forces skill-aware discovery before any code action. Load this skill first when the user intent is unclear or when tool selection would benefit from structured workflow guidance.

Use to resume a persisted feature workflow from its saved state and always question the user about what to do next before taking any action. Cross-host support for Codex and Claude Code.

Use to perform a deep critique and improvement of the current workflow step artifact (PRD, stories, tech spec, ADR, etc.) with a terminal approval form.

Use to show the next recommended step for a persisted feature workflow without restarting the whole flow.

Use to resume a persisted feature workflow from its saved state, especially when multiple sessions exist.

Use to inspect the persisted state of a feature workflow and decide the next recommended step.

Use when the main problem is cloud topology, async-first communication, governance posture or workload cost direction before delivery.

Use when the main problem is shared platform baseline, guardrails, pipelines, identity or observability foundation rather than a single workload feature.

Use when a PRD already exists and needs to be broken into delivery stories. Do not use for raw idea discovery or implementation.

Use to create a disposable prototype and validate design decisions before implementation. Integrates as optional gate in planning or early delivery.