skills

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

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 (publish) and /do (pull before work, upload after). Use when a work item needs to be published to, updated in, or fetched from Notion.

Create Excalidraw diagram JSON files and PR visual overviews that make visual arguments. Use when the user wants to visualize workflows, architectures, concepts, pull request changes, before/after behavior, or a shareable explainer image for reviewers.

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-issue whenever one of these roles runs; not normally invoked by the user directly. Use when a pipeline stage needs its Codex sub-agent dispatched, resumed for a fix round, or re-run.

Captures a discussed multi-phase workstream as an Epic Spec work item ready for /do. For a single-outcome change use /create-feature instead.

Captures a discussed feature as a lean Feature Ticket work item ready for /do. For multi-phase workstreams use /create-epic instead.

Captures a defect as a Bug Report work item ready for /do, running the investigator first if the root cause isn't already established.

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 Y", "why is Z happening", "what should we do about W". Produces clarity plus a dated decision log, not deliverables; work items are created afterward with /create-feature, /create-epic, or /create-issue.

Runs a postmortem after /do finished and the human reviewed the PR, when the result fell short of intent. Use when the user says a /do run missed the mark, the PR needed rework, the delivered feature didn't match the ticket, or asks "why did /do get this wrong" — or when any workflow skill (/discussion, /create-*) produced the wrong outcome. Root-causes the gap in our system and proposes one concrete improvement.

Backend-verifier role in an automated development pipeline: proves backend verification criteria by running the mapped tests, scripts, and commands with quoted evidence. Use when dispatched to verify implemented work.

Code-researcher role in an automated development pipeline: explores the codebase and returns current-state facts with precise file:line references. Use when dispatched to answer a question about what exists in the repo.

Code-reviewer role in an automated development pipeline: reviews the diff for correctness and security with file:line evidence. Use when dispatched to review an implementation.

Implementer role in an automated development pipeline: executes an Implementation Plan (plan.md), writing the diff while keeping the plan file true. Use when dispatched to implement a plan or apply review fixes.

Investigator role in an automated development pipeline: reproduces a reported defect and isolates its root cause with evidence. Use when dispatched to diagnose a bug before it's written up.

Plan-reviewer role in an automated development pipeline: audits an Implementation Plan for gaps, repo accuracy, and fidelity to the work item. Use when dispatched to review a plan.

Creates a reconciled implementation plan by combining a structured plan draft with a normalized intent brief and a PRP-style research dossier, then auto-reviews the final plan. Use when planning a new feature or significant change.

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 result for completeness and intent fidelity. Use after a plan is approved.

Recommend what to work on next across a Pane workspace and GitHub activity. Use when the user asks what they should work on next, what to prioritize, what is blocked, what needs review, what PRs should be merged, what issues matter, or wants a triage of active/recent repos, panes, PRs, issues, checks, reviews, and recent work.

Orchestrate RunPane issue-to-PR workstreams across discussion, planning, implementation, review, PR testing, and CLI dogfooding without stealing user focus. Use when the user asks Claude Code to fan out GitHub issues, manage multiple Pane workstreams, or run the Pane discussion-plan-implement-review loop.

Recommend what to work on next across a Pane workspace and GitHub activity. Use when the user asks what they should work on next, what to prioritize, what is blocked, what needs review, what PRs should be merged, what issues matter, or wants a triage of active/recent repos, panes, PRs, issues, checks, reviews, and recent work.

Orchestrate RunPane issue-to-PR workstreams across discussion, plan, implementation, review, PR testing, and CLI dogfooding without stealing user focus. Use when the user asks Codex to fan out GitHub issues, manage multiple Pane workstreams, or run the Pane discussion-plan-implement-review loop.

Summarize recent Pane workspace activity from active panes, archived panes, branches, pull requests, and agent logs. Use when the user asks what they worked on, what they finished, what shipped, what is still active, or asks for a recap over a time window such as today, yesterday, last 24 hours, this week, recently, or open-ended "what have I been working on?"

Run first-pass automated manual testing for PRs that are reviewed or nearly ready to merge. Use when the user asks Claude to test a PR/branch/worktree, validate product flows, exercise browser or CLI workflows, map changed UI journeys with screenshots, verify analytics/webhooks/payments/email/SMS behavior through connected tools, or produce manual QA notes before human testing.

Run first-pass automated manual testing for PRs that are reviewed or nearly ready to merge. Use when the user asks Codex to test a PR/branch/worktree, validate product flows, exercise browser or CLI workflows, map changed UI journeys with screenshots, verify analytics/webhooks/payments/email/SMS behavior through connected tools, or produce manual QA notes before human testing.

(foundational) Audit and rewrite website copy for voice consistency, readability, and first-timer comprehension.

(execution) Create new SEO content: blog posts, landing pages, comparison pages based on the content strategy.

(support) Discover connected analytics sources, pull data, write .seo/data/ snapshots, and visualize results with deltas vs prior pulls.

(proactive) Pull analytics from PostHog, GSC, and Ahrefs. Correlate data and produce an actionable SEO briefing.

(foundational) Research, draft, reader-hat, edit, read-aloud process for any customer-facing deliverable.

(foundational) Add E-E-A-T signals: explainer pages, glossary, author attribution, structured data, OG images, and SEO metadata.

(greenfield) Crawl your site, find competitors, map the search landscape, and build the starting point for all SEO work.

(proactive) Turn an SEO briefing into a prioritized content plan: what to create, update, and index.

(support) Archive and organize .seo/ data into a dated wiki structure for historical tracking.

Capture conversation context and explicit human intent into one or more high-level GitHub tickets. Use when the user asks Claude to create a ticket, issue, GitHub equivalent of a planning intent brief, delegation ticket, backlog item, or asks to turn the current discussion into ticket(s), especially when the work should be framed by intent, scope, acceptance criteria, inputs needed, and non-exhaustive starting points.

Capture conversation context and explicit human intent into one or more high-level GitHub tickets. Use when the user asks to create a ticket, issue, GitHub equivalent of a planning intent brief, delegation ticket, backlog item, or asks to turn the current discussion into ticket(s), especially when the work should be framed by intent, scope, acceptance criteria, inputs needed, and non-exhaustive starting points.

Write a plain-language teaching note after a completed task or project so the user learns from the work. Use when the user asks Claude for a learning writeup, after-action explanation, personal teacher note, or breakdown of what happened and why, especially at the end of a unit of work, after PR testing/manual testing, or before merge.

Write a plain-language teaching note after a completed task or project so the user learns from the work. Use at the end of a unit of work, after PR testing/manual testing, before merge, or whenever the user asks for a learning writeup, after-action explanation, personal teacher note, or breakdown of what happened and why.

Orchestrate business work from a captured task through context, discussion, spec, artifact, review, and release — each stage in fresh context via filesystem handoff.

Create the business artifact from an approved spec, then coordinate claim/evidence ledger creation, artifact review, anti-sycophancy review, and human gate.

Have a business-goal discussion using the context base without drafting the deliverable.