Creator · avivsinai
Last updated · Sep 6, 2026
Bitbucket CLI for Data Center and Cloud. Use when users need to manage repositories, pull requests, branches, issues, webhooks, or pipelines in Bitbucket. Triggers include "bitbucket", "bkt", "pull request", "PR", "repo list", "branch create", "Bitbucket Data Center", "Bitbucket
Sandbox only
Install targets
Codex install prompt
Install the "bkt" agent skill from https://github.com/avivsinai/bitbucket-cli/tree/master/.agents/skills/bkt. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Bitbucket CLI for Data Center and Cloud. Use when users need to manage repositories, pull requests, branches, issues, webhooks, or pipelines in Bitbucket. Triggers include "bitbucket", "bkt", "pull request", "PR", "repo list", "branch create", "Bitbucket Data Center", "Bitbucket Cloud", "keyring timeout". After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"avivsinai-bkt","task":"Install bkt","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.
Scenario
GitHub automation
I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.
Agent fit
Claude Code + OpenAI Agents + Browser agents
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add avivsinai/bitbucket-cli --skill bkt
Maintenance
fresh
3d since push
Risk
Needs review
Dependency or permission surface needs review
GitHub quality
200
70/100 Quality · 72/100 Trust
Coverage tags
Review notes
Dependency or permission surface needs review · Permission surface may require sandboxing
Agent adoption scorecard
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
200 GitHub stars
Repo activity
200 stars, 44 forks
Maintenance
3d since push
License
MIT
Install
npx skills add avivsinai/bitbucket-cli --skill bkt
Install safety
Agent-readable metadata
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
Suited agents
Install decision
Trust and risk
Outcome loop
Install command
npx skills add avivsinai/bitbucket-cli --skill bktDo not use when
Agent safety v2
This skill should not be selected by an agent without explicit human security review.
Do not auto-install. Inspect the source, dependencies, and permission surface first.
high
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Skill may drive a browser or interact with web pages.
medium
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Skill may read or write project files, documents, generated artifacts, or local workspace state.
Agent resolve plan
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20bkt%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20bkt%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/avivsinai-bkt/install
Agent should check
Copy prompt
Task: Use bkt in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20bkt%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/avivsinai-bkt/install
Install command: npx skills add avivsinai/bitbucket-cli --skill bkt
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/avivsinai-bkt/install
LLM text format
/api/skills/avivsinai-bkt/install?format=text
Find alternatives
/api/skills/search?q=bkt&limit=3
Agent prompt
Use bkt for this task. Review https://www.openagentskill.com/api/skills/avivsinai-bkt/install, then install with: npx skills add avivsinai/bitbucket-cli --skill bktRegistry metadata
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/avivsinai-bkt
LLM text
/api/registry/manifest/avivsinai-bkt?format=text
Install alias
/api/registry/install/avivsinai-bkt
Recommend
/api/registry/recommend?task=Use%20bkt%20in%20an%20agent%20workflow&limit=3
Agent fit
GitHub automation
Use-case tags
Platforms
Claude Code, OpenAI Agents, Browser agents
Audit report
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Prototype with this skill first; keep a fallback candidate ready.
Role in stack
Fallback candidate
Primary fit
GitHub automation
Trust label
Prototype first
Install path
Command ready
Use when
Evidence
review first
Implementation path
Trust profile
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
INFO200 GitHub stars
Stars/forks activity
CHECK200 stars, 44 forks; issue activity unavailable in current metadata
Recent maintenance
PASS3d since push
License clarity
PASSMIT
Good signals
Review before install
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Manage repositories
I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.
Build and ship code
I need a coding agent that can understand a repository, edit code, and review pull requests.
Operate web apps
I need my agent to control a browser, fill forms, and verify web app workflows.
Workflow fit
Inspect, patch, and verify code
A workflow for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Operate and verify web apps
A workflow for agents that navigate products, fill forms, take screenshots, and verify real user flows across web applications.
Turn skills into distribution
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Alternative shortlist
Similar skills that may fit this task.
Apache ECharts is a powerful, interactive charting and data visualization library for browser
Bring data to life with SVG, Canvas and HTML. :bar_chart::chart_with_upwards_trend::tada:
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
Apache Superset is a Data Visualization and Data Exploration Platform
--- name: bkt version: 0.32.1 description: Bitbucket CLI for Data Center and Cloud. Use when users need to manage repositories, pull requests, branches, issues, webhooks, or pipelines in Bitbucket. Triggers include "bitbucket", "bkt", "pull request", "PR", "repo list", "branch create", "Bitbucket Data Center", "Bitbucket Cloud", "keyring timeout". metadata: short-description: Bitbucket CLI for repos, PRs, branches compatibility: claude-code, codex-cli ---
# Bitbucket CLI (bkt)
`bkt` is a unified CLI for **Bitbucket Data Center** and **Bitbucket Cloud**. It mirrors `gh` ergonomics and provides structured JSON/YAML output for automation.
## Before You Start
**1. Verify installation** — always check before running any `bkt` command:
```bash bkt --version ```
If not installed:
| Platform | Command | |----------|---------| | macOS/Linux | `brew install avivsinai/tap/bitbucket-cli` | | Windows | `scoop bucket add avivsinai https://github.com/avivsinai/scoop-bucket && scoop install bitbucket-cli` | | Go | `go install github.com/avivsinai/bitbucket-cli/cmd/bkt@latest` | | Binary | Download from [GitHub Releases](https://github.com/avivsinai/bitbucket-cli/releases) |
**2. Check authentication** — most commands require an active session:
```bash bkt auth status ```
**Bitbucket Cloud Token Requirements:** - Create an "API token with scopes" (not a general API token) - Select **Bitbucket** as the application - Required scope: **Account: Read** (`read:user:bitbucket`) - Additional scopes as needed: Repositories, Pull requests, Issues
For config-free use in containers and CI pipelines, see [headless authentication](rules/headless.md).
If not authenticated, log in:
```bash # Data Center (PAT-based) bkt auth login https://bitbucket.example.com --username alice --token <PAT>
# Bitbucket Cloud — OAuth (official binaries open browser out of the box) bkt auth login https://bitbucket.org --kind cloud --web
# Bitbucket Cloud — API token (--web-token opens Atlassian's token creation page) bkt auth login https://bitbucket.org --kind cloud --web-token ```
For source and Nix builds, set `BKT_OAUTH_CLIENT_ID` and `BKT_OAUTH_CLIENT_SECRET` env vars before running `--web`.
**3. Set up a context** — contexts bind a host to a project/workspace and optional default repo, so you don't repeat flags on every command:
```bash # Data Center bkt context create dc-prod --host bitbucket.example.com --project ABC --set-active
# Cloud bkt context create cloud-team --host bitbucket.org --workspace myteam --set-active ```
## Platform Awareness
Some commands are **Data Center only** or **Cloud only** — check the command reference for `*(DC)*` and `*(Cloud)*` badges. Key splits:
| Feature | Data Center | Cloud | |---------|:-----------:|:-----:| | Pull requests | yes | yes | | Repositories | yes | yes | | Branches (list) | yes | yes | | Branches (create/delete/protect) | yes | — | | Issues | — | yes | | Pipelines | — | yes | | Permissions | yes | — | | Webhooks | yes | yes | | Auto-merge, tasks, reactions | yes | — | | Variables | — | yes | | Skill search | — | yes |
When a user's context is DC, do not suggest Cloud-only commands (and vice versa). If the platform is unknown, ask or check with `bkt auth status`.
## Common Workflows
### Create a PR from the current branch
```bash bkt pr create --title "feat: add caching" --target main ```
Source branch, title, and target default to sensible values from git state. Add `--draft` for work-in-progress, `--reviewer alice` to request review.
### Review cycle
```bash bkt pr checks 42 --wait # Wait for CI to pass bkt pr approve 42 # Approve bkt pr merge 42 # Merge (closes source branch by default) ```
### Checkout a colleague's PR locally
```bash bkt pr checkout 42 # Creates pr/42 branch ```
### Structured output for scripting
All commands support `--json`, `--yaml`, `--jq`, and `--template`:
```bash bkt pr list --mine --json | jq '.pull_requests[].title' ```
### Raw API escape hatch
For endpoints without a dedicated command:
```bash bkt api /rest/api/1.0/projects --param limit=100 --json ```
### Search for Agent Skills in Bitbucket Cloud
```bash bkt skill search "code review" bkt skill search "review repo:agent-skills" --workspace myteam --json ```
Search is workspace-scoped and returns only `SKILL.md` files. It is not available for Bitbucket Data Center because Data Center has no public workspace code-search API. Atlassian has announced that the [Cloud code-search REST endpoint](https://developer.atlassian.com/cloud/bitbucket/rest/api-group-other-operations/#api-workspaces-workspace-search-code-get) will be deprecated on November 1, 2026.
## Global Flags
Every command accepts these inherited flags:
| Flag | Short | Purpose | |------|-------|---------| | `--context` | `-c` | Use a specific named context | | `--json` | | JSON output | | `--yaml` | | YAML output | | `--jq` | | Apply a jq expression (requires `--json`) | | `--template` | | Render with Go template |
## References
- [headless / env vars](rules/headless.md) — Config-free CI/container auth (BKT_TOKEN, BKT_HOST) and full env var reference
<!-- auto-generated by cmd/docgen — do not edit below this line -->
- [admin](rules/admin.md) — Administrative operations for Bitbucket *(DC)* - [auth](rules/auth.md) — Manage Bitbucket authentication credentials - [branch](rules/branch.md) — Inspect and manage branches - [commit](rules/commit.md) — Work with commits - [context](rules/context.md) — Manage Bitbucket CLI contexts - [extension](rules/extension.md) — Manage bkt CLI extensions - [issue](rules/issue.md) — Work with Bitbucket Cloud issues *(Cloud)* - [mcp](rules/mcp.md) — Model Context Protocol server for agents - [perms](rules/perms.md) — Manage Bitbucket permissions *(DC)* - [pipeline](rules/pipeline.md) — Run and inspect Bitbucket Cloud pipelines *(Cloud)* - [pr](rules/pr.md) — Manage pull requests - [project](rules/project.md) — Work with Bitbucket projects *(DC)* - [repo](rules/repo.md) — Work with Bitbucket repositories - [skill](rules/skill.md) — Install and manage agent skills - [status](rules/status.md) — Inspect commit and pull request statuses - [variable](rules/variable.md) — Manage pipeline variables *(Cloud)* - [webhook](rules/webhook.md) — Manage Bitbucket webhooks - [other](rules/other.md) — api
<!-- end auto-generated -->
Source provenance
Decision snapshot
recent repository activity
Audit
Install and adoption review
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Free and open source. Review the report before installing into production agents.
Growth loop
Scenario-led draft for bkt, ready for a manual X post.
bkt: Bitbucket CLI for Data Center and Cloud. Use when users need to manage repositories, pull req... 200 stars https://www.openagentskill.com/skills/avivsinai-bkt?ref=x
Listing + install path for bkt: https://www.openagentskill.com/skills/avivsinai-bkt?ref=x Install: npx skills add avivsinai/bitbucket-cli --skill bkt
Listing source
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
This Registry indexed listing is attributed to avivsinai but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/avivsinai-bkt?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/avivsinai-bkt?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[](https://www.openagentskill.com/skills/avivsinai-bkt/audit)
[](https://www.openagentskill.com/skills/avivsinai-bkt?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)avivsinai
@avivsinai
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Sandbox only
Echarts
Apache ECharts is a powerful, interactive charting and data visualization library for browser
67.2K StarsD3
Bring data to life with SVG, Canvas and HTML. :bar_chart::chart_with_upwards_trend::tada:
113.1K StarsScientific Agent Skills
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
33.5K StarsSuperset
Apache Superset is a Data Visualization and Data Exploration Platform
74.7K StarsPermission surface
secrets or environment access, shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Strong README/SKILL.md context
Risk summary
Install readiness