narailabs

Use when the user asks about Confluence content or wants to create, update, or delete Confluence pages and comments — CQL search, page retrieval, space metadata, comments, attachments, or any write operation on pages. Supports both read and write surfaces; every action passes the policy gate before any network call is made: read actions succeed by default, write and delete actions escalate by default, privilege actions are hard-denied.

Use when the user asks about Jira data or wants to create, update, or delete Jira content — JQL search, issue details, project metadata, comments, attachments, status transitions, or any write operation on issues and comments. Supports both read and write surfaces; every action passes the policy gate before any network call is made: read actions succeed by default, write and delete actions escalate by default, privilege actions are hard-denied.

Use when the user asks about read-only GCP inventory — Cloud Run services, Cloud SQL instances, Pub/Sub topics, or Cloud Logging entries. Queries are scoped to a single GCP project. Never modifies GCP resources.

Use when the user asks about GitLab data or wants to act on GitLab — project info, code search, issue/MR/release/pipeline inspection, or any write that creates, updates, closes, or deletes an MR, issue, note, or release; merging MRs (admin); and managing CI pipeline runs (retry / cancel / trigger / play_job).

Use this skill whenever the user wants to add a new agent connector to their @narai connectors workspace — wrapping a SaaS API, REST endpoint, GraphQL endpoint, SDK, or CLI tool into the canonical @narai connector shape (CLI + library + Claude Code plugin). Trigger even if the user doesn't say "connector" explicitly: phrases like "I want to query Stripe from Claude", "add Slack to our agents", "wrap our internal orders API", "connect Salesforce", "I have a GraphQL endpoint we need exposed", "make a Linear agent" all warrant this skill. Walks the user through identity, auth, and action-surface questions, then scaffolds the package, plugin layer, and tests by stamping out canonical templates and generating per-connector code. Do NOT use for: modifying existing connectors (just edit the file), wrapping MCP servers (different abstraction), or querying databases (db-agent-connector already covers postgres/mysql/sqlite/mssql/mongodb/dynamodb/oracle).

Use when the user asks about read-only AWS inventory — Lambda functions, RDS databases, S3 buckets, or CloudWatch metrics in an AWS account. Queries are scoped to a single region (except list_buckets, which is account-wide). Never modifies AWS resources.

Use this skill when the user wants to add a custom connector to their project — wrapping a SaaS API, REST endpoint, GraphQL endpoint, SDK, or CLI tool so Claude can call it via `gather()` from `narai-primitives`. Trigger even when the user doesn't say "connector" explicitly: phrases like "I want to query Stripe from Claude", "add Slack to our agents", "wrap our internal orders API", "connect Salesforce", "make a Linear agent" all warrant this skill. Also triggers for: "gate kubectl in prod", "approve before force push", "pull from Linear, summarize, post to Slack", "document this workflow". Scaffolds a minimal local connector at `.connectors/connectors/<name>/` (project scope, default) or `~/.connectors/connectors/<name>/` (user scope) — no `git init`, no `npm publish`, no plugin manifest, no marketplace entry. Do NOT use for: modifying an existing connector (just edit the file), wrapping an MCP server (different abstraction), querying databases (the `db` connector inside narai-primitives already covers postg

Use when the user asks about reading data from a database — SELECT queries, schema introspection, "show me the rows/tables/columns…". Supports PostgreSQL, MySQL, SQLite, SQL Server, MongoDB, DynamoDB, and Oracle via pluggable drivers. Every statement passes the policy gate BEFORE any driver loads or any connection opens: write statements escalate, delete and admin statements return formatted SQL without executing, privilege statements are hard-denied.

Build features and full-stack apps using strict Test-Driven Development with agent teams, anti-cheat verification, and E2E browser testing. Always use this skill when the user wants to: build or implement something with tests, use TDD or test-driven development, implement a feature with "tests first" or "write tests before code", add test coverage to existing code, implement code against a failing test file, execute a multi-task implementation plan, build a full-stack app (backend + frontend), or invoke /tdd. Also use when the user mentions "red-green-refactor", "test-first", wants "no shortcuts" or "no cheating" in tests, asks to "resume" a TDD session, or wants comprehensive QA testing of their app. This skill handles everything from simple utilities to complex full-stack applications with React frontends and Express backends. Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1.

Use when testing a web app end-to-end via Chrome browser. Navigates all screens, discovers interactive elements, verifies functionality, checks console errors and network failures, finds bugs, and automatically launches fix agents inline. Also supports targeted workflow testing and bug fix cycles. Requires Claude in Chrome extension connected.

Retrofit self-improving feedback loops into existing skills or agents. Use when user wants to make a skill or agent learn from its usage and mistakes, improve itself over time, or add adaptive behavior that gets smarter with each run. Supports both skill targets (SKILL.md) and agent targets (CLAUDE.md, AGENTS.md). The feedback loop teaches the skill/agent HOW to work better — not what to work on. Always asks user before committing any changes.