dev-toolkit
claudecodexIndependent, reusable development utilities
5 skills
End-to-end development workflow: from ticket to shipped PR with automated task tracking, git management, and team communication
Plugin cortex-workflow from marketplace siroc-cortex in SIROC-Labs/cortex. Commands read from the repo's manifest — 6 days ago.
agent-loop-authorUse when anything has to become work on the agent board — product or stakeholder feedback, review notes, a benchmark table, a UX critique, customer complaints, a bug report, a chat thread, a screenshot, a spec, or a one-line idea — including requests to analyse input, find improvements, plan tasks f
agent-loop-readinessUse when a task is about to be executed by an unattended agent run or written for one — auditing a claimed card from the agent board, drafting a card destined for its queue, judging whether an ambiguity is a stop or a safe default, or at the moment an unattended run is about to ask the operator a qu
agent-loop-review-tickUse when invoked as /agent-loop-review-tick by a scheduler, or when the user asks to review one card from the agent board. Takes exactly one card from the board's in-review column, reviews its PR for completeness, security and simplicity, checks CI and the absence of suppressions, fixes what is smal
agent-loop-setupUse when setting up the agent loop from scratch or repairing it — "set up the agent loop", "/agent-loop-setup", "configure the agent board", "map the agent board columns", "get the agent loop running", or when an unattended run reports that its cache is missing or invalid. Walks the operator through
agent-loop-tickUse when invoked as /agent-loop-tick by a scheduler, or when the user asks to run one task from the agent board. Takes exactly one card from the board's queue, gates it, runs it through start-task in unattended mode, and routes the card to in-review or blocked. Takes only cards that are unassigned o
backend-qaUse when the operator wants to confirm a backend change is adequately tested before it ships — triggers include "QA this branch", "QA this PR", "is this tested enough", "do we have enough tests", "verify test coverage", "confirm the tests pass", "/backend-qa", or any request to audit/gate the unit +
backend-testingUse when writing, reviewing, or improving tests in a backend / API / service project — triggers include "write tests", "add tests", "test this endpoint", "test this service", "improve test coverage", "/backend-testing", or any request to create or fix backend tests. Also triggered when TDD is active
create-prThis skill should be used when the user says "create a PR", "open a pull request", "make a PR", "push and create PR", "open PR for this", "submit a PR", "PR this branch", "let's get this reviewed", or wants to update an existing PR's description or reviewers. Handles the full PR lifecycle: pre-check
create-prdCreates a Product Requirements Document from one or more content sources. Sources can be passed as arguments — task URL, Jira URL, Notion URL, Google Drive URL, Figma URL, Loom URL, any web URL, a local file or folder path, free-text problem statement, or left empty to read the current folder. Use t
create-specProduces a technical specification as a markdown document — the layer above feature implementation that captures architecture, data, contracts, behaviors, and testing strategy at the right abstraction level for a later planner to act on. Inputs can be passed as arguments — a PRD path, a task URL, a
design-reviewUse when the operator wants a design or mockup challenged against requirements — triggers include "challenge this design", "review these designs", "do the designs cover all the use cases / states", "verify the mockups match the spec", "audit the screens", "/design-review". Inputs are tool-agnostic:
documentationUse when a task is done and verified, before shipping, committing the final change or opening a pull request, to bring the project's documentation in line with what the task changed. Also use when the user asks to refresh, update or check the docs for this branch or recent work. Never run it mid-tas
fix-bugHandles bug-fix investigation and testing when start-task routes a Bug category task. Orchestrates root cause investigation (DIAGNOSE_AND_FIX_BUG capability) and a TDD hard gate to prevent recurrence (APPLY_TDD capability), resolved via the runtime-bindings table. Returns to start-task for QA verifi
frontend-testingUse when writing, reviewing, or improving tests in a frontend project — triggers include "write tests", "add tests", "test this component", "improve test coverage", "/frontend-testing", or any request to create or fix frontend tests. Also triggered when TDD is active in a frontend codebase to provid
git-checkThis skill should be used when the user says "check git status", "is my branch clean", "git check", "any uncommitted changes", "check before commit", or when another skill needs to validate git state before proceeding. Validates branch, conflicts, uncommitted changes, untracked files, debug artifact
implement-featureRoutes non-bug implementation work to the right development skill for the current runtime. Detects an available implementation plan, resolves capabilities (CREATE_PLAN, EXECUTE_PLAN, EXECUTE_INLINE) via the runtime-bindings table, and asks the operator when more than one binding applies. Works stand
log-taskUse when the user wants to create a new task in the task manager from the current conversation — before or after doing the work. Triggers: "log this as a task", "create a ticket for this", "capture this as a task", "I want to track this", "let's create a ticket for what we just found", "add this to
milestone-breakdownProduces a milestone-based roadmap of work as a folder of artifacts — a top-level breakdown.md (one rich block per milestone, ready to push as milestone descriptions) plus one M{N}-milestone-spec.md per milestone (a self-contained technical spec scoped to that milestone, designed to be uploaded as a
mobile-qaUse when the operator asks to investigate a specific question or problem in a running mobile application — triggers include "/mobile-qa", "QA this app", "test this on mobile", or any specific question about a mobile app's behavior. Requires a running app on an iOS simulator or Android emulator and m
mobile-testingUse when writing, reviewing, or improving tests in a mobile project — triggers include "write tests", "add tests", "test this ViewModel", "test this Presenter", "test this use case", "/mobile-testing", or any request to create or fix mobile tests. Also triggered when TDD is active in a mobile codeba
pre-ship-checkThis skill should be used when the user says "am I ready to ship", "pre-flight check", "check before PR", "ready to merge", "pre-ship check", "can I ship this", "is this ready", or "run checks". Validates that code is in a shippable state: enforces the QA verification gate (blocks bugs without verif
product-one-pagerUse when the user wants a product one-pager, brief, or short feature spec — drafting one from raw material (idea notes, a feature request, meeting/Slack notes, research snippets), or reviewing and strengthening an existing one (Markdown file or pasted text). Not for long-form PRDs, technical specs (
refine-tasksTurns Refinement-status tasks into one-shotters. Given any input that resolves to a deterministic set of tasks (task URLs, a milestone/grouping in a project, a project URL, or a user-described filter), reads the codebase, resolves ambiguities, composes a detailed implementation plan per task, attach
ship-itThis skill should be used when development is complete and the work needs to be shipped: the user says "ship it", "we're done", "ready to ship", "done with this feature", "let's wrap up", "mark as in review", "create the PR", "link this to the task manager", "create a PR and update the task", or "pu
start-taskThis skill should be used when the user provides a task URL and wants to begin working on it — "start task", "work on this", "pick up this ticket", "let's start on [task-id]", "jump on this", "begin this task", or pastes a task URL with intent to start development. Orchestrates the full lifecycle: v
submit-breakdownPushes a task breakdown to the task manager by faithfully replicating the breakdown markdown into tasks. Use this skill whenever the user wants to submit, push, upload, publish, or create tasks from a task-breakdown file — "submit this breakdown", "upload this task-breakdown file", "push these tasks
task-breakdownSubdivides one coherent scope into implementation tasks. Produces a folder bundle — `breakdown.md` (T-blocks only) plus one per-task `T{N}-<slug>-implementation-plan.md` attachment — ready for `submit-breakdown` to push to the task manager, with planned tasks landing `Unassigned`. Drives the intervi
task-manager-asanaAsana implementation of the task-manager interface. Maps neutral task operations (create/read/update tasks, statuses, fields, comments, attachments, boards) onto the Asana REST API. Invoked by the task-manager seam when the project's provider is Asana; not called directly by workflow skills.
task-manager-jiraJira implementation of the task-manager interface. Maps neutral task operations (create/read/update tasks, statuses, fields, comments, attachments, boards) onto Jira via the `acli` CLI (+ Atlassian MCP fallback). Invoked by the task-manager seam when the project's provider is Jira; not called direct
task-managerNeutral interface to the project's task manager (Asana, Jira, etc.). Other skills perform all task operations through this seam — create/read/update tasks, statuses, fields, comments, and attachments — without naming a specific provider. Use whenever a workflow needs to read or write a task, ticket,
web-qaUse when the operator asks to investigate a specific question or problem in a running web application — triggers include "QA this", "why is X broken", "test this flow", "/qa", "/web-qa", or any specific question about a web app's behavior. Requires a running web app (local or remote) and Chrome DevT
work-summaryThis skill should be used when the user says "summarize my work", "what did I do", "session recap", "standup notes", "handoff", "write a summary", "what changed", "wrap up summary", "give me a recap", or "work report". Produces a concise, reusable work summary that other skills (ship-it, create-pr,
Independent, reusable development utilities
5 skills
mobile-mcp server for cortex-workflow mobile QA (mobile-qa). Enable per project.
1 MCP server
Chrome DevTools MCP server for cortex-workflow web QA (web-qa). Enable per project.
1 MCP server
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.