Skill Claude CodeCodex
Use when defining a feature - name what is in scope, out of scope, and assumed, and handle mid-flight expansion without corrupting in-progress tasks.
Local-first agent platform: board + role agents + agent CLI runs (Claude Code, Cursor, Antigravity, OpenCode) or local and API models (Ollama, LM Studio), all on your own Mac
This repository also configures its own agents. See what tasktrooper tells them →
Skill Claude CodeCodex
Use when defining a feature - name what is in scope, out of scope, and assumed, and handle mid-flight expansion without corrupting in-progress tasks.
Skill Claude CodeCodex
Use when updating the stakeholder - report in outcome language (what changed for users, what's next, what decision is needed), translate technical detail, and surface risks early.
Skill Claude CodeCodex
Use when a stakeholder sends a request - route it to backlog tasks, an analiz task, or a focused question, decide ask-vs-assume with a Definition of Ready, and ask only what a wrong guess would actually cost.
Skill Claude CodeCodex
Use when a task changes any screen, form, dialog, menu or control - Lighthouse/axe scan of the changed screens, a keyboard walk, and the thresholds that fail a task.
Skill Claude CodeCodex
Use when a task adds or changes an HTTP endpoint, its request/response shape, status codes, auth or error format - the request matrix, curl templates and what counts as a contract break.
Skill Claude CodeCodex
Wire the automation test project into the repository's own pipeline so every task must pass the suite before it can leave QA.
Skill Claude CodeCodex
Use when the task touches a backend API, database or worker - booting it from the task branch, driving real requests and verifying side effects (DB rows, outbound calls, logs) as evidence.
Skill Claude CodeCodex
Use when building cases for any input, form, endpoint or state change - boundary values, invalid and hostile data, authz and concurrency cases with a worked example.
Skill Claude CodeCodex
Use when any case fails or you reject a criterion - what goes in the reviewcriterion note, the failed case and the numbered needrevision comment, with severity.
Skill Claude CodeCodex
Maintain a dedicated automation test project per repository - separate from the product's unit tests - with API, worker, and UI suites written scenario-first.
Skill Claude CodeCodex
Use when the task changes anything a user sees in a web app - booting it, driving flows with the browser tools, the four-width check, console/network/keyboard checks and the visual checklist.
Skill Claude CodeCodex
Use when the task touches a mobile app - the device flow with the mobile tools, confirming the installed build is the task's, and what to report when no device is attached.
Skill Claude CodeCodex
Use when a criterion mentions speed or limits, or the change touches a list, query, endpoint or page that could get slower - timing loops, the N-vs-10N data check and Lighthouse on a production build.
Skill Claude CodeCodex
Use before any reviewcriterion approval or column move - the evidence each verdict needs, how to treat skipped, blocked and intermittent cases, and which exit a blocker takes.
Skill Claude CodeCodex
Use after the targeted cases pass - choosing the adjacent behaviour this change can break from the PR's files and the component's links, and the per-repository smoke set.
Skill Claude CodeCodex
Use when the task came back to QA after needrevision - what to re-run, what may carry over, and how to keep old passes from approving new code.
Skill Claude CodeCodex
Use at the start of every QA round - recording the case matrix with recordtestcases (categories, criterion links, rejected cases) before touching the app, then executing all of it.
Skill Claude CodeCodex
Use when a case needs data, a user/role, or a third-party dependency - seeding through the product first, test credentials, namespacing on shared environments, and stubbing an external HTTP service by hand.
Skill Claude CodeCodex
Use when a test needs a database - spin up a dedicated, disposable test database (Testcontainers) seeded with known data, never a shared or production database.
Skill Claude CodeCodex
Use when a test would otherwise call a real external dependency - replace it with WireMock or an equivalent stub so runs are deterministic, offline, and control the responses.
Skill Claude CodeCodex
Use before booting anything - choosing local (starttaskpreview or a workspace boot), the task's preview or stage, confirming the build is the PR head, and what to do when nothing can run.
Skill Claude CodeCodex
Use while deriving cases - Given/When/Then and the techniques (partitions, boundaries, decision tables, state transitions) that find the cases the criteria do not state.
Skill Claude CodeCodex
Use when the task has a background job, queue consumer, scheduler or webhook - firing the real trigger, polling for the side effect, and the retry, idempotency and poison-message cases.
Skill Claude CodeCodex
Use when a batch (desktop or mobile) release reaches awaitingverdict or was rolled back - read-only checks that the published artifact really exists and is served, and the exact yank step for a bad tag.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: