repo-sme

Included with Lifetime

$97 forever

This skill should be used when the user asks to "ask the SME", "check the repo for", "query the SME", "consult the expert", "how does the API work", "look up in the SME", "what does this library do", "how does [library] handle", "repo architecture", "how does the repo work", "create an issue", "file an issue", "what branch has", or when TypeScript errors reference external types from a registered repo. Also use when the user asks about patterns, conventions, or architecture of a registered repository, or wants to compare branches.

Backend & APIs

What this skill does


# Repository SME (Subject Matter Expert)

Query locally-cloned GitHub repositories for grounded, citation-backed answers about APIs, architecture, patterns, and conventions. Supports branch switching, cross-branch analysis, and GitHub issue creation.

**Do NOT announce registered repos at session start.** Only act when a relevant question arises.

## When to Spawn the SME Agent

Proactively spawn `repo-sme-expert` via the Agent tool when **any** of these conditions are met:

1. User asks about types, methods, events, or interfaces of an external library
2. TypeScript compiler errors reference types from an external package
3. User imports match a registered repo name (e.g., `import { ... } from 'obsidian'`)
4. User asks "how does X work?" where X is a registered library's API or architecture
5. User asks about patterns, conventions, or structure of a registered repository
6. User asks to create/file a GitHub issue against a registered repo
7. User asks about a specific branch of a registered repo

**Before spawning:** read `~/.claude/repo-sme/registry.json` to confirm a matching repo is registered.

## Registry Format

```json
{
  "repos": [
    {
      "name": "obsidian-api",
      "url": "https://github.com/obsidianmd/obsidian-api",
      "localPath": "/home/user/.claude/repo-sme/repos/obsidianmd/obsidian-api",
      "addedAt": "2026-02-28T10:00:00.000Z",
      "lastPulledAt": "2026-02-28T10:00:00.000Z",
      "currentBranch": "main",
      "defaultBranch": "main"
    }
  ]
}
```

## How to Spawn the SME Agent

```
Use the Agent tool:
  subagent_type: "repo-sme:repo-sme-expert"
  prompt: |
    Repository: <repoName>
    Path: <localPath>
    URL: <url>
    Branch: <currentBranch>
    Question: <user's question>
```

Always pass `localPath`, `repoName`, and `url`. Include `branch` when the user asks about a specific branch.

## Matching Library Names to Registered Repos

| Signal | Example | Action |
|--------|---------|--------|
| Import statement | `import { TFile } from 'obsidian'` | Check if `obsidian` or `obsidian-api` is registered |
| User question | "how does app.vault.read() work?" | Match `obsidian` → spawn SME |
| TS error | `error TS2305: Module 'obsidian' has no exported member 'X'` | Check registered repos for obsidian |
| Architecture question | "how does the plugin lifecycle work?" | Match to registered repo → spawn SME |
| Issue request | "file an issue about missing types" | Match to registered repo → spawn SME with issue context |
| Branch query | "what's on the develop branch?" | Match to registered repo → spawn SME with branch param |
| Explicit request | "ask the SME about TFile" | Spawn directly |

## Commands Reference

| Command | Description |
|---------|-------------|
| `/repo-sme add <url>` | Clone and register a GitHub repo |
| `/repo-sme list` | Show all registered repos with branch info |
| `/repo-sme remove <name>` | Remove a repo from the registry |
| `/repo-sme ask <name> <question>` | Query a specific repo directly |
| `/repo-sme branches <name>` | List all branches for a repo |
| `/repo-sme checkout <name> <branch>` | Switch a repo to a different branch |

Never guess at API behavior — always use the SME for external library questions when a matching repo is registered.

Files: 1

Size: 3.8 KB

Complexity: 17/100

Category: Backend & APIs

Source: https://github.com/nthplusio/functional-claude/tree/main/plugins/repo-sme/skills/repo-sme

Related in Backend & APIs

jfrog

Included

Interact 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.

Backend & APIsscripts

cupynumeric-migration-readiness

Included

Pre-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.

Backend & APIsscripts

alibabacloud-data-agent-skill

Included

Invoke 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".

Backend & APIsscripts

token-optimizer

Included

Reduce 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.

Backend & APIsscripts

resend-cli

Included

Use 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.

Backend & APIsscripts

alibabacloud-odps-maxframe-coding

Included

Use 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.

Backend & APIsscripts