roost

In the author's own words, from each skill's SKILL.md.

• automate-tests

  Automate the tests linked to a story or slice. Read each test's scenarios, find which already have automation, write the missing automation at the right layer, run it, and only when every scenario passes mark the test automated. Use when a developer agent is asked to "automate the tests for PROJ-X", "figure out why these tests aren't automated", or to finish the e2e work for a slice.

  skills/automate-tests/SKILL.md on GitHub (opens in a new tab)

• automate-xray-tests

  The old name of automate-tests, kept so it still works. Use automate-tests.

  skills/automate-xray-tests/SKILL.md on GitHub (opens in a new tab)

• bug-bash

  Fix a list of bugs from the tracker in this repo, one branch each, test-first, with each fix placed by its parent (on the epic's GitHub stack for a bug in an unreleased epic, or its own PR from main for a standalone bug), moving each ticket through In Progress and Ready for Release. When a fix needs another repo, hand it off with pasteable comments instead of touching it. Use when the user gives…

  skills/bug-bash/SKILL.md on GitHub (opens in a new tab)

• build-epic

  Build an epic from its tech lead prompt to release QA, through the user's repo sessions (one per repo in the team's roost config). If the stories have no kickoff comments yet, it first sends the epic's tech lead prompt to the lead repo's session, brings the plan to the user for approval, and has the kickoffs posted. Then it runs run-slice for each story in order, slice-handoff between stories, th…

  skills/build-epic/SKILL.md on GitHub (opens in a new tab)

• close-out-epic

  Close out an epic before it's released, so that its open-ticket count means something. Lists every open ticket under the epic and proposes, for each, fix before release, move to the epic's follow-up epic, or make standalone, then waits for the user's decisions. Moves the deferred tickets out of the epic with a link back, rewrites each one's description so it still makes sense outside the epic, po…

  skills/close-out-epic/SKILL.md on GitHub (opens in a new tab)

• create-xray-test

  File Cucumber scenarios you already have into Jira as Xray Test issues, or update the scenarios on an existing Xray Test, through the browser. Sets the parent epic, Components and the link to the story, and checks what was saved. Doesn't write or check scenarios; use live-verified-bdd to write them for a feature that already runs, or shape-epic for a new epic.

  skills/create-xray-test/SKILL.md on GitHub (opens in a new tab)

• cross-repo-handoff

  Write a prompt that another repo's agent can run cold, for work this repo needs but must not do itself (for example the API change a UI fix depends on, or the UI change an API fix needs). Posts it as a comment on the ticket or returns it for pasting. Use when the user asks for "a prompt for the API agent", "a prompt for the UI agent", "what should I share back", or when a fix needs changes in the…

  skills/cross-repo-handoff/SKILL.md on GitHub (opens in a new tab)

• live-verified-bdd

  Write or revise Cucumber scenarios for a feature that already runs, then walk each one in the live app with Playwright and correct it to match what the app does. Use to write test scenarios, or to check that existing scenarios still match the app. Doesn't file anything in the tracker; hand the result to create-xray-test. For a new epic that isn't built yet, use shape-epic.

  skills/live-verified-bdd/SKILL.md on GitHub (opens in a new tab)

• pair-runbook

  Run a rollout runbook together with the user, one step at a time. Claude gives the next command and what to expect; the user checks it, runs it and pastes the output; Claude checks the output, fills in the stage's record in the run's working copy, updates the stage's sub-task, and moves on. Claude never runs a command against staging, production, outside services or a shared database itself. Stop…

  skills/pair-runbook/SKILL.md on GitHub (opens in a new tab)

• release-notes

  Draft customer-facing release notes for an epic that has shipped, ready to paste, one note per feature it shipped (usually one). Dates each note by when customers could first use the feature (the production deploy, release or merge that first carried its last change, shown in an evidence table), never by the tracker's resolution date; writes only what the slices built, listing anything cut; holds…

  skills/release-notes/SKILL.md on GitHub (opens in a new tab)

• release-qa

  QA an epic before release on the local environment. Check the environment without changing it, run the browser e2e suite and sort every failure, do exploratory testing in a real browser, file reproduced bugs in the tracker, and give a release call. Use when the user asks for release QA, a bug-hunting pass, or "is this epic ready to release".

  skills/release-qa/SKILL.md on GitHub (opens in a new tab)

• review-epic

  Review a whole epic's code before it's released, in every repo it touches, against main. Each repo's session runs /code-review at high effort on everything the epic's stack changes, and the lead repo's session also runs /security-review, looking for what slice-by-slice reviews miss (how the slices interact, fixes layered on fixes, code that was never reviewed). Findings come back to one checkpoin…

  skills/review-epic/SKILL.md on GitHub (opens in a new tab)

• roost-config

  Load the team's roost config (which tracker, which repos and sessions, the local stack's commands, branching rules, deploy and design details) and the adapter notes for its tracker and test tool. Every other roost skill uses this first, before it reads or changes anything. Use it directly when the user asks "what does roost know about our setup?" or "which config is roost using?".

  skills/roost-config/SKILL.md on GitHub (opens in a new tab)

• run-bug

  Fix one or more bugs (or follow-up tasks) from the tracker by driving the user's repo sessions over cross-session messages, the way run-slice drives a story. Triages each bug first, assigns it to the user and starts it, sends it to the session that owns the code, and tells that session where the fix goes, on the epic's stack when the bug belongs to an unreleased epic or from main as its own PR wh…

  skills/run-bug/SKILL.md on GitHub (opens in a new tab)

• run-slice

  Orchestrate one slice (story) from kickoff to done by driving the user's repo sessions (one Claude session per repo in the team's roost config, for example an API session and a UI session) over cross-session messages. Sends each repo's kickoff prompt from the tracker in order, has the stack's owner start the local stack, then loops through test verification, code review, fixes and exploratory tes…

  skills/run-slice/SKILL.md on GitHub (opens in a new tab)

• setup

  Set up roost for a team. Links an existing team config, or makes a new one by asking about the team's tracker (Jira or GitHub Issues), tests, repos and how each reaches production, local stack, branching and deploy rules, and release notes (where they're published, and the team's voice), leaving out what the team doesn't have, then checks it. Use when a roost skill says there's no config, or the…

  skills/setup/SKILL.md on GitHub (opens in a new tab)

• shape-epic

  Shape a product idea into a fully-defined, buildable epic. Composable phases from problem statement through epic definition, design (a UI prototype, an architecture PR, or both), slice planning, test creation, build guide, and a tech lead handoff prompt attached to the epic. Can enter at any phase depending on what already exists. Use when user wants to go from idea to implementation-ready epic.

  skills/shape-epic/SKILL.md on GitHub (opens in a new tab)

• slice-handoff

  Close out a finished slice of an epic before the next one starts. Sorts everything the slice left open (follow-up tickets, deferred bugs, unautomated scenarios) into the next slice, before release, or later; keeps one Carry-over comment on the epic; runs every test in the epic so far, so a later slice can't quietly break an earlier one, and makes the tracker match; rewrites the next slice's kicko…

  skills/slice-handoff/SKILL.md on GitHub (opens in a new tab)

• stacked-prs

  Work with GitHub stacked pull requests (gh stack) in the team's repos. Put a branch on the right stack, commit, push and open its PR with the "Stacked on" banner, fix a merge conflict on the one branch that has it, and walk a stack bottom to top. Use whenever the user says "on the stack", "add it to the stack", "open a PR on the stack", "fix the conflict", or pastes GitHub's stacked-PR conflict s…

  skills/stacked-prs/SKILL.md on GitHub (opens in a new tab)

• triage-ticket

  Decide whether a ticket (often a code-review or security finding) is accurate and needs fixing. Check each claim against the code, explain the real risk or failure scenario, and recommend fix or not. If the user says fix, fix it test-first with one commit per item. Use when the user asks to "review PROJ-X and help me determine whether we need to address it" or "is this accurate".

  skills/triage-ticket/SKILL.md on GitHub (opens in a new tab)

• verify-slice-tests

  After a slice's changes are pushed, prove which of its story's tests are automated and passing, mark those automated, and propose splits for tests with scenarios that aren't automated, waiting for the user's answer. Reports one table and fixes nothing. Use when the user asks which tests for a story are automated, to "verify the tests for PROJ-X", or to mark a slice's tests automated. To write mis…

  skills/verify-slice-tests/SKILL.md on GitHub (opens in a new tab)

• write-runbook

  Write or rewrite an operational runbook in roost's recordable, gated format, with literal commands for each environment, a run record, pass/fail gates and a rollback, and keep it one to one with the rollout ticket's sub-tasks (one sub-task per stage, same number and name, checked both ways). Use when the user asks for a runbook, a rollout or migration procedure, or says an existing runbook doesn'…

  skills/write-runbook/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 181k stars · 6 skills
• marketingskillsby coreyhaines31 Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering. 57.5k stars · 30 skills
• elephant-goldfish-modelby google Open-source skills for designing and reviewing software with AI agents 6.6k stars · 7 skills
• skillsby NVIDIA Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA,… 3.8k stars · 30 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 412k stars · 5 skills
• taste-skillby Leonxlnx Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages 106k stars · 1 skill