← All creators

kdlbs

Organization

AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.

36 indexed · 0 Featured · 304 stars · avg score 83
Prolific

Categories

Indexed Skills (36)

Code & Development Solid

debug-instance

Debug a running kandev development instance. Use when the user reports a bug, unexpected behavior, or asks to investigate an issue while kandev is running via `make dev`. Fetches backend logs, analyzes errors, and optionally inspects the UI via an existing Playwright browser session.

304 Updated today
kdlbs
AI & Automation Solid

mobile-parity

Ensures UI feature work ships with desktop and mobile parity, responsive behavior, and mobile Playwright E2E coverage. Use when implementing, planning, reviewing, or testing any new feature, page, component, workflow, form, dialog, sidebar, navigation, dashboard, or visual UI change; if work touches frontend or user-facing UI, this skill must run even when user mentions only desktop or says "new feature".

304 Updated today
kdlbs
AI & Automation Solid

playwright-cli

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

304 Updated today
kdlbs
AI & Automation Solid

kandev-escalation

How to create a human-actionable decision task when you are blocked

304 Updated today
kdlbs
AI & Automation Solid

kandev-protocol

How to interact with the kandev orchestrator via the CLI

304 Updated today
kdlbs
Code & Development Listed

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 an agent fails to initialize.

304 Updated today
kdlbs
AI & Automation Listed

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.

304 Updated today
kdlbs
Code & Development Listed

code-review

Review changed code for quality, security, and architecture compliance. Use after implementing features or before opening PRs.

304 Updated today
kdlbs
Code & Development Listed

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.

304 Updated today
kdlbs
Code & Development Listed

debug-logs

Add temporary debug logs (console.log / structured Warn) to investigate issues. Use whenever the user wants to add logs, log statements, console.logs, trace, instrument, or print runtime behaviour to debug a frontend or backend issue. Triggers include "add debug logs", "add some logs", "log this", "trace this", "instrument", "investigate why", "print", "console.log around". Debug logs must be stripped before creating a PR.

304 Updated today
kdlbs
Code & Development Listed

e2e

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

304 Updated today
kdlbs
Code & Development Listed

feature

Guided feature development — brainstorm, explore codebase, design architecture, implement with TDD, and review. Use for new features or significant changes.

304 Updated today
kdlbs
AI & Automation Listed

fix

Fix bugs and issues — reproduce, find root cause, minimal fix with regression test. Use when something is broken.

304 Updated today
kdlbs
AI & Automation Listed

plan

Create an implementation plan (plan.md) from a feature spec. Explores the codebase, designs the approach, and produces a structured plan with backend, frontend, tests, and E2E sections. Use after writing a spec and before implementing.

304 Updated today
kdlbs
AI & Automation Listed

pr-fixup

Wait for CI checks and automated reviews (CodeRabbit, Greptile, Claude, cubic) on a PR, fix failures and address comments, then push.

304 Updated today
kdlbs
Code & Development Listed

pr

Commit, push, and create a PR. Default is ready-for-review with auto-fixup. Use --draft to skip review/fixup.

304 Updated today
kdlbs
AI & Automation Listed

pull-upstream

Pull latest changes from the public kandev repo, rebase onto them, and fix any conflicts or issues.

304 Updated today
kdlbs
AI & Automation Listed

qa

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

304 Updated today
kdlbs
AI & Automation Listed

simplify

Simplify recently changed code — inline one-off abstractions, remove speculative code, reduce nesting, replace cleverness with clarity. Run after implementing a feature.

304 Updated today
kdlbs
Code & Development Listed

spec

Write a feature spec — the "what & why" of a kandev product feature, before coding. Use ONLY for a product-feature surface (user-visible capability the app supports). Do NOT use for bug fixes, incident postmortems, refactors that preserve behavior, or infra-only work — those get ADRs (if a new convention emerged) and/or regression tests, not specs. Use when the user says "let's spec X" or starts a new product feature.

304 Updated today
kdlbs
AI & Automation Listed

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.

304 Updated today
kdlbs
AI & Automation Listed

kandev-agent-edit

Edit or remove existing agents — rename, adjust budget, retire

304 Updated today
kdlbs
Code & Development Listed

kandev-approvals

List pending approvals and decide them (approve or reject)

304 Updated today
kdlbs
AI & Automation Listed

kandev-budget

Check workspace and per-agent spend before expensive operations

304 Updated today
kdlbs
AI & Automation Listed

kandev-config-export

Export the office workspace config to the .kandev/ folder for version control

304 Updated today
kdlbs
AI & Automation Listed

kandev-config-import

Apply config changes from the .kandev/ folder back into the office DB

304 Updated today
kdlbs
AI & Automation Listed

kandev-hiring

Hire new agents via agentctl, gated by the workspace approval policy

304 Updated today
kdlbs
AI & Automation Listed

kandev-routines

Schedule recurring work via cron and webhook triggers

304 Updated today
kdlbs
AI & Automation Listed

kandev-tasks

List, move, archive, and message tasks via agentctl

304 Updated today
kdlbs
AI & Automation Listed

kandev-team

List and inspect agents in the workspace before delegating or hiring

304 Updated today
kdlbs
AI & Automation Listed

memory

Read and write persistent memory entries via agentctl

304 Updated today
kdlbs
AI & Automation Listed

kandev-task-comment

Post a comment on any task as the current agent

304 Updated today
kdlbs
AI & Automation Listed

clean-branches

Delete local branches whose remote has been deleted ([gone]), including their worktrees. Use for branch cleanup after merging PRs.

304 Updated today
kdlbs
Code & Development Listed

push

Commit and push to the current branch. Use --fixup to also wait for CI/CodeRabbit and fix issues.

304 Updated today
kdlbs
Code & Development Listed

release

Kandev release & versioning conventions — single SemVer across npm, Homebrew, GitHub release. Use when cutting a release, debugging release artifacts, or answering questions about version channels.

304 Updated today
kdlbs
Code & Development Listed

verify

Run format, typecheck, test, and lint across the monorepo. Use after implementing changes.

304 Updated today
kdlbs

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.