kdlbs/kandev

release

Kandev release and version-channel conventions — unified Stable SemVer plus deterministic npm-only Nightlies. Use when cutting a release, changing channels, debugging artifacts, or answering version-channel questions.

原文语言：英语

code-review

Review changed code for quality, security, and architecture compliance. Use only when the user explicitly requests local review or a PR finding requires it.

原文语言：英语

commit

Stage and commit changes using Conventional Commits. Use when there are dirty/staged files to commit, the user says "commit", or before pushing a PR.

原文语言：英语

context-engineering

Curate the right project context before coding or debugging. Use when starting a new session, switching areas of the codebase, output quality is drifting, a task spans backend/frontend/docs, or external instructions need to be reconciled with Kandev…

原文语言：英语

debug

Diagnose Kandev bugs, running-instance issues, UI/browser failures, and runtime behavior. Use when the user reports unexpected behavior, asks to investigate, asks to add logs/instrumentation, or when a fix needs root-cause evidence before implementing. Triage…

原文语言：英语

e2e

Write and run web E2E tests (Playwright) using TDD — locations, patterns, commands, and debugging.

原文语言：英语

fix

Diagnose a bug, update its behavioral spec, create reviewable fix plan and task files, then hand off for explicit implementation with TDD.

原文语言：英语

harness-improvement

Improve Kandev's AI harness from session learnings or explicit requests. Use when the user asks to record learnings, update or create skills, agents, subagents, commands, AGENTS.md/CLAUDE.md guidance, or adapt harness files across Claude, Codex, Cursor, or…

原文语言：英语

plan

Create a committed implementation plan from a feature spec. Explores the codebase, designs the approach, and produces docs/plans/<feature>/plan.md plus individual task files. Use after writing a spec and before implementing.

原文语言：英语

playwright-cli

Automate browser interactions, test web pages and work with Playwright tests.

原文语言：英语

pr-fixup

Wait for CI and automated reviews on a PR, fix valid failures and comments in the primary conversation, verify, and push.

原文语言：英语

pr

Create a PR from a committed and pushed branch after task-defined checks pass. Ready PRs continue to fixup in the primary conversation.

原文语言：英语

push

Push a committed branch whose task-defined checks passed. With --fixup, continue with CI and review handling in the primary conversation.

原文语言：英语

runtime-feature-flags

Add, roll out, promote, graduate, or remove Kandev runtime feature flags and release toggles across the backend and frontend. Use whenever a task mentions a feature flag, release toggle, staged rollout, kill switch, or graduating a flag.

原文语言：英语

tdd

Implement changes using Test-Driven Development (Red-Green-Refactor). Use for bug fixes, new features, or any code change that should have test coverage.

原文语言：英语

using-agent-skills

Discover and choose the right Kandev agent skill for a task. Use when starting a session, when the user asks which skill applies, when work spans multiple phases, or when existing skill references need to be mapped to this repo's actual skills.

原文语言：英语

create-kandev-plugin

Create, modify, debug, test, package, or publish a Kandev runtime plugin in its dedicated repository. Use only when the requested work targets a Kandev plugin implementation or its release and marketplace lifecycle, including fixing a bug in an existing…

原文语言：英语

mobile-parity

Ensures Kandev UI work uses native mobile interaction patterns instead of compressed desktop adaptations while preserving desktop/mobile capability parity, responsive behavior, and mobile Playwright E2E coverage. Use when implementing, planning, reviewing, or…

原文语言：英语

planner-orchestration

Enforce Kandev's single-session, user-controlled model workflow for feature, fix, debug, review, verification, and delivery work.

原文语言：英语

spec-driven-development

Single-session Kandev feature workflow: clarify intent, create durable specs, plans, and task files, then hand off for user-directed model selection before implementation and verification.

原文语言：英语

spec

Write a feature spec — the "what & why" of a Kandev product feature, before coding. Use for a product feature, or from `/fix` to amend/create the concise behavioral repair spec required before implementation. Do not use for incident postmortems,…

原文语言：英语

docs-maintainer

Keep public Kandev docs current when code or behavior changes affect CLI commands, config keys, install/deploy flows, workflows, executors, APIs, screenshots, or user-facing terminology. Use this before finishing any change with public documentation impact,…

原文语言：英语

acp-debug

Debug an ACP agent CLI by spawning it, speaking raw JSON-RPC, and capturing every frame to a JSONL file. Use when the user asks to probe an agent's capabilities, compare agents, test a prompt against an agent, inspect raw ACP wire frames, or investigate why…

原文语言：英语

verify

Run a broad local verification audit only when the user explicitly requests it or PR/CI remediation requires it.

原文语言：英语

qa

Verify a feature works after implementation. Actively try to break it — edge cases, error paths, integration wiring, and real usage flows.

原文语言：英语

simplify

Simplify recently changed code — inline one-off abstractions, remove speculative code, reduce nesting, replace cleverness with clarity. Use only on explicit request or PR-review remediation.

原文语言：英语

add-integration

Add a new third-party integration (Jira/Linear-style) — per-workspace credentials, 90s auth-health poller, settings page, link/import buttons. Use when scaffolding a new external service integration.

原文语言：英语

kandev-escalation

Escalate to a human when required information, access, credentials, or a product decision blocks completion and no reasonable default is available.

原文语言：英语

kandev-projects

List and create Office projects, then place new tasks in the correct project when organizing workspace work by repository.

原文语言：英语

kandev-protocol

Follow the core Office agent protocol on wakeup, including parsing KANDEV_* context, checking blockers, commenting progress, updating status, and using the CLI safely.

原文语言：英语

kandev-task-ops

Operate Office tasks when you need to list workspace tasks, read a conversation, or post an agent-authored comment.

原文语言：英语

interview-me

Clarify what the user actually wants before specs, plans, or code. Use when an ask is underspecified, when the user says "interview me", "grill me", "stress-test my thinking", or when you would otherwise fill in important product/architecture assumptions…

原文语言：英语

product-demo-seeding

Seed coherent, disposable Kandev demo scenarios for screenshots, product films, landing-page media, and reproducible UI captures. Use when media needs believable tasks, workflows, agents, executors, integrations, plans, sessions, diffs, reviews, or…

原文语言：英语

product-video-capture

Record, camera-process, encode, stage, and validate polished Kandev product films, landing-page loops, screenshots, and alternate framing from isolated demo data. Use when the user asks for product videos, GIF-like feature demos, cursor-follow camera motion,…

原文语言：英语

record

Keep durable architecture decisions and product specs in sync with the work happening in the conversation. AUTO-INVOKE when a request establishes or changes a long-lived architectural boundary, public contract, data ownership rule, operational invariant, or…

原文语言：英语

kandev-approvals

Clear the CEO approval queue when hire requests, budget grants, or other sensitive Office mutations are waiting for approve or reject decisions.

原文语言：英语

kandev-config-sync

Synchronize Office workspace configuration with the .kandev folder when exporting reviewable config, importing committed config, seeding a workspace, or reviewing a config diff.

原文语言：英语

kandev-routines

Create, inspect, pause, resume, or delete recurring Office routines when work should run on a cron schedule or webhook trigger.

原文语言：英语

kandev-team-admin

Manage the Office roster when delegating work, hiring agents, changing budgets or concurrency, retiring agents, or checking spend before approvals.

原文语言：英语

memory

Read, write, and summarize persistent Office memory when durable behavioral guidance or project knowledge should survive across agent sessions.

原文语言：英语