Git & VCS
Git operations, commit helpers, branch management
hackage-release
by colonelpanic8
Use when user asks to release, publish, or bump version of a Haskell package to Hackage
structure-first-review
by perhapsspy
Generate a short, playful AI-style review and guide posting directly to the structure-first GitHub Discussions page
wechat-publisher
by NeverSight
"一键发布 Markdown 到微信公众号草稿箱。基于 wenyan-cli，支持多主题、代码高亮、图片自动上传。"
codex
by NeverSight
Hand off a task to Codex CLI for autonomous execution. Use when a task would benefit from a capable subagent to implement, fix, investigate, or review code. Codex has full codebase access and can make changes.
codex
by NeverSight
Hand off a task to Codex CLI for autonomous execution. Use when a task would benefit from a capable subagent to implement, fix, investigate, or review code. Codex has full codebase access and can make changes.
git-best-practices
by NeverSight
Git workflow patterns for commits, branching, PRs, and history management across heterogeneous repositories. Use when creating commits, managing branches, opening pull requests, or rewriting history. Do not use for non-git implementation tasks or repo-specific release policy decisions without repository documentation.
nix-best-practices
by NeverSight
Nix patterns for flakes, overlays, unfree handling, and binary overlays. Use when working with flake.nix or shell.nix.
schematic
by blader
Reverse engineer a detailed product and technical specification document from a git branch's implementation. Use when: (1) a branch has shipped or is in-progress and needs documentation, (2) you need to understand what a branch does at product and architecture level, (3) onboarding to someone else's feature branch, (4) creating PR descriptions or design docs after the fact, (5) user asks to "analyze this branch", "write a spec from the code", or "document what this branch does". Produces a structured markdown spec covering problem statement, product requirements, architecture, technical design, file inventories, testing strategy, rollout plan, and risks.
robotframework-results
by manykarim
Parse Robot Framework output.xml results into JSON summaries, detailed suite/test breakdowns, tag and criticality stats, execution errors, failed test messages, keyword-level errors, and timing. Use when asked to read/merge output.xml, compute pass/fail counts, tag stats, criticality, error messages, elapsed time, slowest tests/keywords, or combine/merge multiple outputs via rebot.
drive-new-project
by p-wegner
Drive a freshly-created project hands-off to a finished multi-ticket epic — the playbook for "use the board to build a new app / implement a 10+ ticket epic" tickets. Encodes the completion CONTRACT (keep the meta-ticket In Progress until the epic is N/N Done, then drive the meta itself to Done — not parked in Review), a preflight prerequisites check, fan-out epic seeding, autodrive enablement, and a REQUIRED resident watch that recovers stalls instead of abandoning them. Use when a ticket asks you to register/scaffold a new project and take it to completion via the board.
merge-reconciler
by p-wegner
Land a whole BATCH of stranded/mergeable-but-conflicting workspaces onto the base branch in the most efficient way. You are handed the full batch as injected JSON ({{strandedBatch}}), analyze the whole set first (clean-independent / file-overlap clusters / migration collisions / dependencies), then land everything via the board's SAFE primitives — never manual git in the main checkout. Resolve each overlapping cluster's union ONCE in an integration worktree instead of N re-conflicting rebases. Report what landed and what was escalated.
test-coverage
by Montimage
Expand unit test coverage by targeting untested branches and edge cases. Use when users ask to "increase test coverage", "add more tests", "expand unit tests", "cover edge cases", "improve test coverage", or want to identify and fill gaps in existing test suites. Adapts to project's testing framework.
board-monitor
by p-wegner
System-level board health — conflict scan, server/frontend health check. Board operations (relaunch/merge/nudge/auto-start) are handled by the app's built-in monitor (Settings → Workflow → Board Monitoring). Run Sections 0-3 every cycle; only do Section 4 if the app monitor is OFF.
kanban-workflow
by p-wegner
Guide for using the agentic-kanban MCP tools to reflect implementation progress on the board. Use when starting work on an issue, moving through implementation steps, reviewing completed work, or closing out a task.
code-review
by Montimage
Perform code reviews following best practices from Code Smells and The Pragmatic Programmer. Use when asked to "review this code", "check for code smells", "review my PR", "audit the codebase", or need quality feedback on code changes. Supports both full codebase audits and focused PR/diff reviews. Outputs structured markdown reports grouped by severity.
publish
by p-wegner
Publish a new version of the agentic-kanban npm package — build, bump, pack check, publish, commit, push
release
by p-wegner
Pre-release verification + gated GitHub + npm release for agentic-kanban. Runs all checks, summarizes changes, drafts release notes, then PAUSES for explicit user confirmation before pushing the git tag, the GitHub release, and the npm publish.
endpoint-docs
by p-wegner
Create, maintain, and query a concise Markdown catalog of the REST API (docs/api/endpoints.md) — method, path, request shape, response, semantic — with a frontmatter SHA so staleness is detected via git diff. Use when asked "what endpoints exist", "is there an API for X", "where is endpoint Y used", "document the API", or after adding/changing Hono routes.
scope-guard
by p-wegner
Pre-commit check for scope creep — diff working changes vs the task, flag unrelated files, run the project's fast checks, then commit. Stack-agnostic (reads the project's stack profile, not hard-coded to the TS monorepo).
learning-step
by p-wegner
Analyze agent session data (kanban sessions, JSONL transcripts, or inline context), detect friction points, and produce targeted improvements to documentation, hooks, skills, or code.
board-tuning-lab
by p-wegner
R&D harness for tuning the kanban BOARD (its agents, monitor, and workflow) along a chosen DIMENSION by building an increasingly complex disposable fixture project, driving it through the board, measuring where the workflow breaks, filing the gaps as dev-board tickets, and fixing them end-to-end. Dimension-parameterized — docker/multi-repo, observability, token-efficiency, ticket-sizing, and more added over time. Use for "run the board-tuning lab", "tune the board for <dimension>", "dogfood/stress the board's <X> support", "build a fixture and find gaps in <X>", "exercise the board on docker / multi-repo / observability / token efficiency / ticket sizing", or "improve how the board handles <X>".
sentinel
by p-wegner
The board-orchestrator WATCH role. Check the out-of-process board-monitor loop (the "Conductor") once and report a concise one-line status — loop health, board state, profile≠mock, and the current Strategy-Bullseye targets/weights it's steering by; alert with detail and recover ONLY when something needs attention. Use for "check the board monitor", "is the Conductor healthy?", or as a recurring watch scheduled with ScheduleWakeup. Distinct from the board-monitor skill (that's the system-health checklist a monitor CYCLE runs; this is what the human-side supervisor checks between cycles).
code-review-thorough
by p-wegner
In-depth AI code review using a more capable model — catches subtle bugs and architecture issues
db-doctor
by p-wegner
Diagnose & repair kanban.db migration/lock/WAL issues in place — never deletes, truncates, or resets the DB