bkt
Operate Bitbucket Cloud or Data Center repositories, pull requests, branches, pipelines, permissions, and webhooks with bkt. Use when a request names Bitbucket or bkt; confirm the platform before platform-specific commands.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-11
- Stars
- ★ 1.6k
- Forks
- 474
01 前言 Front Matter
- name
- bkt
- version
- 0.38.1
- metadata
- { "compatibility": "claude-code, codex-cli", "short-description": "Bitbucket CLI for repos, PRs, branches" }
- description
- Operate Bitbucket Cloud or Data Center repositories, pull requests, branches, pipelines, permissions, and webhooks with bkt. Use when a request names Bitbucket or bkt; confirm the platform before platform-specific commands.
03 SKILL.md 正文
Bitbucket CLI (bkt)
Use bkt for Bitbucket Cloud and Data Center operations. Prefer structured
--json, --yaml, --jq, or --template output for automation.
Start with the requested operation
Run bkt --version only when installation or compatibility is uncertain. Run
bkt auth status when the command needs authentication or the active platform
and context are unknown. Do not make setup a prerequisite for an already
configured read-only request.
Cloud and Data Center have different feature sets. Determine the platform from the active context or ask when it cannot be inferred. Do not suggest a Cloud-only command for Data Center, or the reverse.
Read setup and common workflows when installing, authenticating, creating a context, or learning the main command patterns. For config-free CI or containers, read headless authentication.
Route to the command reference
Read only the reference for the requested command group:
- pull requests, repositories, branches, commits, or statuses
- pipelines or variables
- Bitbucket Cloud Issues no longer exist (Atlassian removed them in August 2026); route issue tracking to Jira.
- Data Center administration, projects, or permissions
- authentication, contexts, webhooks, extensions, MCP, skills, or raw API
Mutation and credential boundaries
- Listing, viewing, status, and checks are read-only. Create, edit, approve, merge, delete, rerun, or permission changes modify Bitbucket; perform them only when the user requested that change.
- Never place tokens, OAuth secrets, or passwords in commands that could enter logs or committed files. Use the CLI's supported credential flow or environment variables described in the auth references.
- Every bkt build carries its Cloud browser-OAuth consumer, so
bkt auth login --kind cloud --webneeds no setup. - Before a merge or other consequential write, inspect the exact target, repository, and current checks. Report the resulting URL or identifier.
References
<!-- auto-generated by cmd/docgen — do not edit below this line -->
- admin — Administrative operations for Bitbucket (DC)
- auth — Manage Bitbucket authentication credentials
- branch — Inspect and manage branches
- commit — Work with commits
- context — Manage Bitbucket CLI contexts
- extension — Manage bkt CLI extensions
- mcp — Model Context Protocol server for agents
- perms — Manage Bitbucket permissions (DC)
- pipeline — Run and inspect Bitbucket Cloud pipelines (Cloud)
- pr — Manage pull requests
- project — Work with Bitbucket projects (DC)
- repo — Work with Bitbucket repositories
- skill — Install and manage agent skills
- status — Inspect commit and pull request statuses
- variable — Manage pipeline variables (Cloud)
- webhook — Manage Bitbucket webhooks
- other — api
<!-- end auto-generated -->
04 同仓库更多 Skills
migrate-to-e2e
Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for /migrate-to-e2e, "migrate our tests to e2e", "port these Maestro flows", "move our TesterArmy tests", or when a project has an e2e config and an older suite still running.
e2e
Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.
create-verification-skill
Generate a project-local verify-<app> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for /create-verification-skill, "make a verification skill for this repo", or when a project has no scripted way to prove UI behavior.
deja-search
deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.
deja-reflect
End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.
revid
Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.