菜单
Use when asked to set up pncli, configure a service, initialize a repo, or run pncli commands. Walks through identity, work item tracking, source control, and optional services. For any specific service, read the included <service>.md file.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Analyze pod health in an OpenShift / Kubernetes namespace and surface actionable insights. Queries pods, Warning events, and optionally metrics via pncli — data is pre-chunked before LLM analysis to minimize token usage. Use when asked to check namespace health, investigate pod crashes, diagnose CrashLoopBackOff or OOMKilled, or review cluster resource pressure.
Work through all open review comments and SonarQube issues on the current branch's PR. Auto-fixes linting and SonarQube findings; applies AI judgment to reviewer comments. Shows a summary table, then asks user to commit and push before marking threads resolved. Use when asked to address feedback, resolve PR comments, or respond to change requests.
Review the PR for the current branch. Reads the full diff, existing comments, and referenced source files, then posts categorized inline comments (Blocking / Suggestion / Nit) via pncli. Offers to approve or request changes at the end. Works with Bitbucket and Azure DevOps. Use when asked to review a PR, check the diff, or add code review comments.
Turn a feature description, goal, or problem statement into a structured backlog in Jira or ADO. Explores the codebase with parallel subagents before generating the breakdown; shows the plan to the user for confirmation before creating any work items. Use when asked to plan a feature, break down a problem, or create backlog items from a description.
Scan all security sources (dependency CVEs, SonarQube vulnerabilities, SonarQube hotspots, optionally SDElements threats), triage by severity, then create Jira or ADO tickets — Bug for critical/blocking findings, Task for others, grouped under an Epic when more than 3 tickets are created. Use when asked to do a security review, scan for vulnerabilities, or triage security findings into the backlog.
Open a PR for the current branch on Bitbucket or Azure DevOps. Runs the full pre-PR gate (build, lint, typecheck, tests, code review, docs) using parallel subagents before opening the PR. For GitHub repos, use the repo-scoped /ship skill instead. Use whenever the user says "open a PR", "create a PR", "ship this", "pull request", or "/ship".
| name | pncli |
| description | Use when asked to set up pncli, configure a service, initialize a repo, or run pncli commands. Walks through identity, work item tracking, source control, and optional services. For any specific service, read the included <service>.md file. |
| compatibility | Designed for Claude Code. Requires pncli installed and accessible in PATH. |
| user-invocable | true |
| metadata | {"category":"setup","providers":"both","services":"config"} |
pncli gives AI agents and humans unified CLI access to enterprise tools: Jira, Bitbucket, Confluence, SonarQube, SDElements, Azure DevOps, Jenkins, Artifactory, IBM UrbanCode Deploy, Checkmarx, ServiceNow, Contrast Security IAST, Sonatype IQ Server, and OpenShift / Kubernetes.
Env vars — ephemeral, per-session, override the config file. Set before running pncli:
export PNCLI_<SERVICE>_<KEY>=value
Config file — persistent, stored in ~/.pncli/config.json. Set with:
pncli config set <service>.<key> <value>
Repo-level defaults (project key, target branch) are stored in .pncli.json in the repo root:
pncli config set --repo defaults.<service>.<key> <value>
For detailed setup of any service, read the included file for that service.
| Service | File | Commands unlocked |
|---|---|---|
| Jira | jira.md | Issues, sprints, custom fields |
| Bitbucket | bitbucket.md | Repos, PRs, diffs |
| GitHub | github.md | PRs, reviews, comments, checks |
| Azure DevOps | ado.md | Work items, repos, PRs, pipelines |
| Confluence | confluence.md | Pages, spaces |
| JWT | jwt.md | Decode JWT tokens |
| SonarQube | sonarqube.md | Code quality issues |
| SDElements | sde.md | Threat model tasks |
| Checkmarx | checkmarx.md | SAST findings |
| IBM UrbanCode Deploy | udeploy.md | Component versions, deployments |
| Jenkins | jenkins.md | Builds, job status |
| Artifactory | artifactory.md | Packages, repos |
| ServiceNow | servicenow.md | Change requests, incidents |
| Contrast IAST | contrast.md | Runtime vulnerability findings |
| Sonatype IQ | sonatypeiq.md | Dependency policy enforcement |
| OpenShift / Kubernetes | openshift.md | Pod health, events, logs, metrics |
| Skills Marketplace | marketplace.md | Install org-internal skills |
Step 1 — Identity
Ask: email address and username/user ID. Then:
pncli config set user.email <email>
pncli config set user.userId <username>
Step 2 — Work item tracking
Ask: "Does this org use Jira or Azure DevOps for work items?" See jira.md or ado.md.
Step 3 — Source control
Ask: "Does this org use GitHub, Bitbucket, or Azure DevOps for PRs?" See github.md, bitbucket.md, or ado.md.
Step 4 — Optional services
Ask about each optional service the user may need. Read the relevant .md file for config keys and commands. Skip services they don't use.
Step 5 — Repo-level defaults
pncli config set --repo defaults.jira.project <key>
pncli config set --repo defaults.bitbucket.targetBranch <branch>
Step 6 — Test connectivity
pncli config test
Review results. If any service shows ok: false, help troubleshoot the URL or credentials.
pncli config show