dcouple

The Notion bridge for work items — creates a Notion work item mirroring a GitHub issue, uploads artifacts (item.md, refs/, plan.md, wrapup.md) to it, and pulls a work item's artifacts down to ./tmp/<id>/. Used by /create-feature, /create-epic, /create-issue…

Performs a comprehensive PR code review. Reads the linked GitHub issue for context, runs quality checks, and reviews code for bugs, architecture, conventions, and frontend best practices. Posts structured findings as a PR review.

Explain one topic to a smart person who knows nothing about it, as a single HTML page that leads with a picture and earns every word, rendered per the html-explainer standards. Use when the user types /eli5 <topic>, asks for a dead-simple explainer of how…

The house standard for any skill that renders an HTML page for a person to read, covering design tokens, typography, components, diagrams, and quality gates so every generated page shares one calm, graphic-first look. Use when a skill's instructions say to…

Assess where a project actually stands against what its README, plan, or pitch promises, with every claim tested against the artifact itself rather than the docs, reported in chat and as an HTML page per the html-explainer standards. Use when someone asks…

Write a plain-language teaching note after a completed task or project so the user learns from the work, and render it as a rich HTML explainer per the html-explainer standards. Use when the user asks Claude for a learning writeup, after-action explanation,…

Write a plain-language teaching note after a completed task or project so the user learns from the work, and render it as a rich HTML explainer per the html-explainer standards. Use when the user asks Claude for a learning writeup, after-action explanation,…

Commits changes grouped by done-plans, rebases main, builds API and webapp, then creates or updates a PR. Replaces the commit command. Use when you're ready to open or update a pull request.

Investigates bugs through hypothesis-driven root cause analysis. Automatically invoked when the user reports a bug, error, broken behavior, or something not working as expected. Use when something is broken, failing, or behaving unexpectedly.

Investigate a bug or broken behavior through hypothesis-driven root cause analysis and report what is wrong without jumping straight to a fix. Use when something is failing or behaving unexpectedly.

Executes an approved plan with one primary implementation stream by default, using bounded parallel sidecars only when the write scopes are truly disjoint. Supports default Claude execution or an explicit Codex executor option. Automatically reviews the…

Selectively stages and commits only the changes related to the current session, skipping unrelated modifications.

Executes an approved plan directly in Codex with one primary implementation stream by default, bounded sidecars only when write scopes are truly disjoint, and mandatory review gates for completeness and intent fidelity. Use after a plan is approved.

Review completed code changes against a plan, run quality checks, and call out gaps, regressions, or missing integrations. Use when implementation work needs a plan-based review.

Carry out a structured implementation plan carefully and systematically, following existing repo patterns, preserving intent, and running quality checks as work progresses. Use when a plan already exists and the goal is execution.

Review an implementation plan for repo accuracy, fact purity, intent fidelity, reconciliation quality, and completeness. Use when a plan needs a correctness and completeness pass.

Run the full autonomous pipeline against a work item — plan, implement, verify, PR, post-PR review + QA, wrap-up. Takes a work-item reference (issue

Take ad-hoc changes made in-session (outside /do) to a pull request — gate them through Socrates (right approach?) and the PR reviewers (correct?), then commit, push, and open the PR in the repo's standard format. /do handles its own PR prep; this skill is…

Produce one artifact by fanning out N blind candidates, picking the strongest as the base, grafting the best of the losers into it, and verifying the synthesis. Use when a single attempt at a non-trivial artifact — a design, a tricky function, a doc — would…

Interactive back-and-forth to clarify, understand, or figure something out — an idea, an approach, a tradeoff, or a suspected bug. Use when the user wants to think out loud or explore before committing to anything — e.g. "let's discuss X", "help me understand…

Sustained improvement of one named metric toward a target — measure a baseline, then loop one hypothesis at a time, each with a re-measurement and a keep-or-revert verdict. Use for perf, bundle size, lint count, test time, or any number with a repeatable…

Dispatches one Codex (GPT-5.6) sub-agent via `codex exec` — implementer, backend-verifier, plan-reviewer, code-reviewer, code-researcher, or investigator — and returns its report. Used by /do, /discussion, and /create-brief whenever one of these roles runs;…

Refactor-deep role in an automated development pipeline: read-only comprehensive analysis of a large diff — per-layer repo-derived conventions plus a correctness hunt over new code paths, writes a prioritized plan. Use when dispatched after the review loop on…

Refactor-simple role in an automated development pipeline: read-only quality analysis of the branch for small/medium diffs — repo-derived conventions, code smells, writes a plan. Use when dispatched after the review loop.

Creates an implementation plan with thorough codebase and web research. Auto-reviews the plan after creation and iterates with user feedback. Use when planning a new feature or significant change.

Executes an approved plan by breaking work into parallelizable chunks and spawning implementation sub-agents. Automatically reviews the result for completeness. Use after a plan is approved.

Quick gut-check before implementing when the user directly asks you to do something (e.g. "add X", "fix Y", "change Z"). Investigates, proposes a lightweight plan, and implements after approval. Use this instead of /create-plan when the user wants something…