bitbucket-devops
Comprehensive Bitbucket pipeline automation using direct Node.js API calls. Monitor pipeline status, analyze failures, download logs, and trigger builds. Use this skill when the user asks to check pipeline status, find failing pipelines, download logs, trigger builds, or debug pipeline failures. No MCP approval prompts required - uses Bash tool with node commands.
What this skill does
# Bitbucket DevOps Skill
This skill provides comprehensive Bitbucket DevOps automation using direct Node.js API calls via the Bash tool. Built on the [bitbucket-mcp](https://github.com/Apra-Labs/bitbucket-mcp) client library.
**Key Advantage:** Uses direct Node.js calls (auto-approved) instead of MCP tools, eliminating the approval prompts issue from [GitHub Issue #10801](https://github.com/anthropics/claude-code/issues/10801).
## ⚠️ MANDATORY: How to Approach User Requests
**You MUST follow this three-tier fallback strategy for ALL Bitbucket operations. This is REQUIRED, not optional.**
**CRITICAL RULES:**
- **DO NOT create new .js files for Bitbucket API calls**
- **DO NOT use `node -e` for inline Bitbucket API operations**
- **ONLY use the pre-built CLI tools listed below**
- **ALWAYS start with Tier 1, fall back to Tier 2 if needed, use Tier 3 only as last resort**
### Tier 1: High-Level Helper Functions (REQUIRED FIRST STEP)
**You MUST check these helpers FIRST before attempting any other approach.**
These solve common workflows in a single command. If the user's request matches any of these patterns, you MUST use the corresponding helper.
**Location:** `~/.claude/skills/bitbucket-devops/lib/helpers.js`
**Available Commands:**
- `get-latest-failed <workspace> <repo>` - Get most recent failed pipeline
- `get-latest <workspace> <repo>` - Get most recent pipeline (any status)
- `get-by-number <workspace> <repo> <build-number>` - Find pipeline by build number
- `get-failed-steps <workspace> <repo> <pipeline-uuid>` - Get all failed steps
- `download-failed-logs <workspace> <repo> <pipeline-uuid> <build-number>` - Download all failed step logs
- `get-info <workspace> <repo> <pipeline-uuid>` - Get formatted pipeline + steps info
**MUST use for:** "latest failed build", "download logs for pipeline #123", "what failed in this build", "get pipeline by number"
**Usage:**
```bash
node ~/.claude/skills/bitbucket-devops/lib/helpers.js <command> <args>
```
**Example:**
```bash
# User: "What's the latest failing pipeline?"
# You MUST use:
node ~/.claude/skills/bitbucket-devops/lib/helpers.js get-latest-failed "workspace" "repo"
# DO NOT create a new script
# DO NOT use node -e
# DO NOT write custom API calls
```
### Tier 2: Low-Level CLI Commands (IF TIER 1 CANNOT SOLVE)
**ONLY use Tier 2 if NO Tier 1 helper matches the user's request.**
Direct API wrappers for specific operations. You MUST use these for operations not covered by Tier 1 helpers.
**Location:** `~/.claude/skills/bitbucket-devops/bitbucket-mcp/dist/index-cli.js`
**Key Commands** (see [docs/REFERENCE.md](docs/REFERENCE.md) for complete list):
**Pipeline Operations:**
- `list-pipelines <workspace> <repo> [limit]`
- `get-pipeline <workspace> <repo> <pipeline-uuid>`
- `get-pipeline-steps <workspace> <repo> <pipeline-uuid>`
- `get-step-logs <workspace> <repo> <pipeline-uuid> <step-uuid>`
- `run-pipeline <workspace> <repo> <branch> [pipeline-name] [variables-json]`
- `stop-pipeline <workspace> <repo> <pipeline-uuid>`
**Pull Request Operations:**
- `list-prs <workspace> <repo> [state] [limit]`
- `get-pr <workspace> <repo> <pr_id>`
- `approve-pr <workspace> <repo> <pr_id>`
- `merge-pr <workspace> <repo> <pr_id> [message] [strategy]`
- `decline-pr <workspace> <repo> <pr_id> [message]`
**Repository Operations:**
- `get-branching-model <workspace> <repo>`
- `list-repositories <workspace>`
**Usage:**
```bash
node ~/.claude/skills/bitbucket-devops/bitbucket-mcp/dist/index-cli.js <command> <args>
```
**You MAY chain multiple Tier 2 commands** - see [docs/PATTERNS.md](docs/PATTERNS.md) for examples.
### Tier 3: Direct Bitbucket API Calls (ONLY IF TIER 1 AND 2 FAIL)
**ONLY use Tier 3 if BOTH Tier 1 AND Tier 2 cannot solve the request. This should be RARE.**
Before using Tier 3, you MUST:
1. Verify no Tier 1 helper exists
2. Verify no Tier 2 CLI command exists
3. Verify no combination of Tier 1 + Tier 2 can solve it
**Documentation:** `~/.claude/skills/bitbucket-devops/bitbucket-mcp/docs/`
- `api-overview.md` - Authentication, base URLs, rate limits
- `pipelines-api.md` - Complete pipeline API reference
- `repositories-api.md` - Repository operations
- `pull-requests-api.md` - PR operations (future)
---
## REQUIRED Decision Process
**Before performing ANY Bitbucket operation, you MUST:**
1. **Check Tier 1 helpers** - Review the 6 helpers above. Does one solve this?
- **YES** → Use it immediately with `node ~/.claude/skills/bitbucket-devops/lib/helpers.js <command>`
- **NO** → Continue to step 2
2. **Check Tier 2 CLI** - Review the CLI commands above. Can one or more solve this?
- **YES** → Use them with `node ~/.claude/skills/bitbucket-devops/bitbucket-mcp/dist/index-cli.js <command>`
- **NO** → Continue to step 3
3. **Check Tier 3 docs** - Read API docs. Is there a direct API call needed?
- **YES** → Read docs, use curl with credentials
- **NO** → Ask user for clarification
**NEVER skip this process. NEVER create new .js files. ALWAYS use pre-built tools.**
---
## Known Limitations
### Pipeline Artifacts Cannot Be Downloaded via API
**IMPORTANT:** Bitbucket Cloud does NOT provide an API to download pipeline artifacts.
**If a user asks to download build artifacts:**
1. Inform them that artifact download via API is not possible
2. Direct them to the Bitbucket web UI:
- Repository → Pipelines → Build # → Step → Artifacts section → Download button
3. Note: Artifacts expire automatically after 14 days
**Tip:** For programmatic artifact access, consider uploading to S3/Azure Blob Storage during your pipeline.
**DO NOT:** Search for undocumented endpoints - this has been thoroughly researched and no API exists.
---
## The DevOps REPL Advantage
Traditional pipeline debugging is slow: push code → wait → fail → investigate logs → fix → repeat (hours per cycle).
This skill enables a **REPL-like experience for DevOps**: Claude observes pipelines in real-time, analyzes failures instantly, suggests precise fixes, and iterates with you until builds pass - reducing debugging cycles from hours to minutes.
**The Loop:**
1. **Read**: Monitor pipeline execution and capture failures
2. **Eval**: AI analyzes logs and identifies root cause
3. **Print**: Claude presents findings and suggests fixes
4. **Loop**: Apply fix, trigger build, repeat until green ✅
This transforms DevOps from slow batch processing into interactive, conversational development.
---
## Prerequisites
This skill uses the Bash tool (auto-approved in Claude Code) to run Node.js commands. Required:
- Node.js (v18+)
- Git (for submodule management)
**Note:** No MCP server required - bitbucket-mcp is used as a library via git submodule.
---
## Configuration
The skill directory is located at: `~/.claude/skills/bitbucket-devops/`
Credentials are loaded with priority (first found wins):
1. **Project level**: `./credentials.json` or `./.bitbucket-credentials` (current working directory)
2. **User level**: `~/.bitbucket-credentials` (home directory)
3. **Skill level**: `~/.claude/skills/bitbucket-devops/credentials.json`
### Credential Format
**IMPORTANT: Different credentials for different operations**
```json
{
"url": "https://api.bitbucket.org/2.0",
"workspace": "your-workspace-name",
"user_email": "[email protected]",
"username": "your-workspace-name",
"password": "your-bitbucket-app-password"
}
```
**Field explanations:**
- `user_email`: Your Bitbucket account email (for API authentication) - MUST contain `@`
- `username`: Your Bitbucket workspace slug (for git operations) - MUST NOT contain `@`
- `password`: App password from https://bitbucket.org/account/settings/app-passwords/
- Required permissions: Repositories: Read, Pipelines: Read
See [docs/GIT_OPERATIONS.md](docs/GIT_OPERATIONS.md) for details on credential requirements.
---
## Quick Start: Essential Patterns
### Pattern 0: Always Detect Workspace and Repository First
**Before any pipeline operation**, determRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.