[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78E27FNNFHE9DGC4RFSGD7M":3,"skill-same:01M78E27FNNFHE9DGC4RFSGD7M":45},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":28,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M78E27FNNFHE9DGC4RFSGD7M","databricks",null,"justin-pitt\u002Fpitt-skills","justin-pitt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F112410033?v=4","01M78E1625ASNK5WY5C3ZN55T3","Justin Pitt","01M78E1630ZDV7CZJBEWA7CCZH",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjustin-pitt\u002Fpitt-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fpitt-skills\u002Fskills\u002Fdatabricks\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: databricks\ndescription: Use when working on the databricks-mcp server or running read-only SQL against a Databricks SQL warehouse via the Statement Execution API: list tables, describe a table, or run a guarded SELECT\u002FSHOW\u002FDESCRIBE\u002FWITH query. Trigger on the databricks_ MCP tool prefix, DATABRICKS_* env vars, a SQL warehouse and its default namespace (e.g. main.default), the read-only SQL guard, Databricks App deployment (name must start mcp-), or service-principal OAuth M2M vs PAT auth. This is a data-plane query server, NOT a clusters\u002Fjobs\u002FUnity-Catalog management server.\nlicense: MIT\nuser-invocable: false\n---\n\n# Databricks (databricks-mcp)\n\nRead-only MCP server that runs **SQL against a Databricks SQL warehouse** via the Statement Execution API. FastMCP server name `databricks_mcp`, tool prefix `databricks_`.\n\n**Scope correction:** this is a thin **data-plane query client**, not a management-plane server. There are no clusters, jobs, SQL-warehouse admin, Unity Catalog governance, workspace, DBFS, secrets, or repos tools. It queries whatever warehouse and namespace it is pointed at (default `hive_metastore.default`; example query `SELECT count(*) FROM main.default.events`).\n\n## Server at a glance\n\n- **3 read-only tools, zero writes.** No `DATABRICKS_WRITE_TOOLS_ENABLED` flag exists (by design). If a write tool is ever added, gate it behind an env flag per the template's permission-tier pattern and keep the guard.\n- **Two write-prevention layers:** (1) `list_tables`\u002F`describe_table` only interpolate a regex-validated dotted identifier (`_validate_identifier`, up to `catalog.schema.table`), never free text; (2) `assert_read_only()` in `src\u002Fdatabricks_client.py` guards `run_select`: strips `\u002F*...*\u002F` and `--` comments, rejects stacked statements, requires the first word in `{SELECT, SHOW, DESCRIBE, WITH}`, and rejects `INSERT\u002FUPDATE\u002FDELETE\u002FMERGE\u002FDROP\u002FCREATE\u002FALTER\u002FTRUNCATE\u002FGRANT\u002FREVOKE\u002FCOPY\u002FREPLACE` as whole words. On violation it raises `WriteGuardError` and never touches the warehouse.\n- **Transport:** stdio (engineer, default) or `streamable-http` (alias `http`, for the Databricks App). Health `\u002Fhealth`, metrics `\u002Fmetrics`, MCP endpoint `\u002Fmcp\u002F`.\n\n## Auth model\n\nSingle connector code path with a per-request `AuthProvider` header callable:\n\n- **Local \u002F stdio:** PAT in `DATABRICKS_TOKEN` -> static `Bearer`. Token captured in a closure, never stored as an attribute (kept out of repr\u002Flogs). Local-dev only.\n- **Databricks App (prod):** no PAT. The runtime injects service-principal **OAuth M2M** creds (`DATABRICKS_CLIENT_ID`\u002F`DATABRICKS_CLIENT_SECRET`); `main._resolve_auth` builds `databricks.sdk.core.Config(host=...)` and passes `cfg.authenticate` as the provider, which returns a fresh Bearer per request and refreshes the ~hourly token. Header fetched per request, never cached on the pooled httpx client. (Fixed in commit `7a4b4c9`: the App uses OAuth M2M, not a PAT.)\n- **Claude Code attach:** `scripts\u002Fmcp_app_launcher.ps1` mints a fresh U2M token each spawn via `databricks auth token --profile \u003Cyour-oauth-profile>` and bridges stdio to the App `\u002Fmcp` with `npx mcp-remote`.\n\nAPI surface: **only** the SQL Statement Execution API v2.0 (`POST \u002Fapi\u002F2.0\u002Fsql\u002Fstatements`, `GET \u002Fapi\u002F2.0\u002Fsql\u002Fstatements\u002F{id}`). No Jobs 2.1, Unity Catalog REST, or SCIM. Host shape `https:\u002F\u002Fadb-\u003Cworkspace-id>.\u003Cn>.azuredatabricks.net`.\n\n## Env vars\n\n| Var | Default \u002F example | Purpose |\n|---|---|---|\n| `DATABRICKS_HOST` | `https:\u002F\u002Fadb-\u003Cworkspace-id>.\u003Cn>.azuredatabricks.net` | Workspace URL (not a secret) |\n| `DATABRICKS_TOKEN` | unset in prod | PAT, local-dev only. Never log\u002Fcommit |\n| `DATABRICKS_WAREHOUSE_ID` | `\u003Cwarehouse-id>` | Target SQL warehouse |\n| `DATABRICKS_CATALOG` \u002F `DATABRICKS_SCHEMA` | `hive_metastore` \u002F `default` | Default namespace |\n| `DATABRICKS_APP_PORT` | injected by App | Bind port (takes precedence over `MCP_PORT`) |\n| `DATABRICKS_CLIENT_ID` \u002F `DATABRICKS_CLIENT_SECRET` | injected by App | Service-principal OAuth M2M (consumed by the Databricks SDK) |\n| `MCP_TRANSPORT` \u002F `MCP_PORT` \u002F `MCP_HOST` \u002F `MCP_SERVER_NAME` \u002F `LOG_FORMAT` \u002F `LOG_LEVEL` | stdio \u002F 8080 \u002F 0.0.0.0 \u002F databricks_mcp \u002F text \u002F INFO | Fleet transport + logging |\n\n## Tool inventory\n\nAll read-only (`readOnlyHint:True`). All take `response_format: markdown|json` (default markdown). Input models forbid extra keys and strip whitespace.\n\n| Tool | Purpose | SQL issued | Key params |\n|---|---|---|---|\n| `databricks_list_tables` | List tables in a schema | `SHOW TABLES IN \u003Cschema>` | `schema_name` (default `hive_metastore.default`, validated dotted identifier) |\n| `databricks_describe_table` | Describe a table's columns | `DESCRIBE TABLE \u003Ctable>` | `table` (required, validated dotted identifier) |\n| `databricks_run_select` | Run one arbitrary read-only statement | the statement, post read-only guard | `statement` (1-10000 chars, non-blank) |\n\n## API specifics\n\n- `DatabricksConnector.execute()` posts to `\u002Fapi\u002F2.0\u002Fsql\u002Fstatements` with `{warehouse_id, statement, catalog, schema, wait_timeout:\"25s\", format:\"JSON_ARRAY\"}`, then polls PENDING\u002FRUNNING (default 5 attempts x 2s, httpx timeout 60s). Any non-`SUCCEEDED` terminal state raises `DatabricksError` with the `status.error.message`.\n- Result shape: columns from `manifest.schema.columns[].name`, rows from `result.data_array` (empty list if absent). Returned to tools as `{\"columns\": [...], \"rows\": [[...]]}`.\n- **Poll budget is bounded** (~25s inline wait + ~10s polling). Queries that exceed it raise `DatabricksError` rather than waiting longer. This is a design limit, not a bug: for long queries, narrow the query.\n- Default namespace `hive_metastore.default` is the legacy Hive metastore, not a Unity Catalog catalog. Pass a fully-qualified `catalog.schema.table` to reach elsewhere.\n\n## Deployment\n\nPrimary prod target is a **Databricks App** (`app.yaml` runs `python src\u002Fmain.py` with `MCP_TRANSPORT=streamable-http`, `LOG_FORMAT=json`; the runtime injects `DATABRICKS_APP_PORT` + OAuth M2M creds). Deploy with `databricks apps create mcp-databricks` (the App resource name MUST start with `mcp-` or the AI Playground won't list it), `databricks sync`, `databricks apps deploy`. The caller IP must be on the workspace IP access list or the App returns 403. `app.yaml` + `requirements.txt` (kept in sync with pyproject by hand) drive the App build. Also runnable as stdio (engineer mode) or a Streamable-HTTP container.\n\n## Fleet conventions (adding a tool)\n\nScaffolded from `mcp-template-build`, conforms to the fleet conformance contract. Same shape as [[microsoft-graph]], [[sonarqube]], [[cribl]].\n\n1. Subclass `BaseModule` (or extend `TablesModule`) in `src\u002Fcustom_components\u002F`; `discover_modules()` instantiates each subclass at startup. Register under `fn.__name__`, which MUST start with `databricks_`.\n2. Input is a single Pydantic `BaseModel` (`ConfigDict(extra=\"forbid\")`, `Field(...)`); set all four annotations. Validate any identifier interpolated into SQL with `_validate_identifier`; never interpolate raw user free-text into a statement.\n3. respx-mocked `tests\u002Ftest_\u003Carea>.py` (mock `conn.execute`); no live warehouse in unit tests.\n4. Pre-push gate: `pytest -v` + `ruff check src tests` + `mypy src` (strict) + `check_pydantic_inputs.py src` + `check_no_print.py src` (stdout is the JSON-RPC channel; log to stderr) + `check_jwt_allowlist.py`.\n\nPython `>=3.12,\u003C4.0`, Poetry for dev (pip + `requirements.txt` for the App\u002FDocker build). Do not run the container conformance Docker gate locally; stdio release is githooks only.\n","# Databricks (databricks-mcp)\n\nRead-only MCP server that runs **SQL against a Databricks SQL warehouse** via the Statement Execution API. FastMCP server name `databricks_mcp`, tool prefix `databricks_`.\n\n**Scope correction:** this is a thin **data-plane query client**, not a management-plane server. There are no clusters, jobs, SQL-warehouse admin, Unity Catalog governance, workspace, DBFS, secrets, or repos tools. It queries whatever warehouse and namespace it is pointed at (default `hive_metastore.default`; example query `SELECT count(*) FROM main.default.events`).\n\n## Server at a glance\n\n- **3 read-only tools, zero writes.** No `DATABRICKS_WRITE_TOOLS_ENABLED` flag exists (by design). If a write tool is ever added, gate it behind an env flag per the template's permission-tier pattern and keep the guard.\n- **Two write-prevention layers:** (1) `list_tables`\u002F`describe_table` only interpolate a regex-validated dotted identifier (`_validate_identifier`, up to `catalog.schema.table`), never free text; (2) `assert_read_only()` in `src\u002Fdatabricks_client.py` guards `run_select`: strips `\u002F*...*\u002F` and `--` comments, rejects stacked statements, requires the first word in `{SELECT, SHOW, DESCRIBE, WITH}`, and rejects `INSERT\u002FUPDATE\u002FDELETE\u002FMERGE\u002FDROP\u002FCREATE\u002FALTER\u002FTRUNCATE\u002FGRANT\u002FREVOKE\u002FCOPY\u002FREPLACE` as whole words. On violation it raises `WriteGuardError` and never touches the warehouse.\n- **Transport:** stdio (engineer, default) or `streamable-http` (alias `http`, for the Databricks App). Health `\u002Fhealth`, metrics `\u002Fmetrics`, MCP endpoint `\u002Fmcp\u002F`.\n\n## Auth model\n\nSingle connector code path with a per-request `AuthProvider` header callable:\n\n- **Local \u002F stdio:** PAT in `DATABRICKS_TOKEN` -> static `Bearer`. Token captured in a closure, never stored as an attribute (kept out of repr\u002Flogs). Local-dev only.\n- **Databricks App (prod):** no PAT. The runtime injects service-principal **OAuth M2M** creds (`DATABRICKS_CLIENT_ID`\u002F`DATABRICKS_CLIENT_SECRET`); `main._resolve_auth` builds `databricks.sdk.core.Config(host=...)` and passes `cfg.authenticate` as the provider, which returns a fresh Bearer per request and refreshes the ~hourly token. Header fetched per request, never cached on the pooled httpx client. (Fixed in commit `7a4b4c9`: the App uses OAuth M2M, not a PAT.)\n- **Claude Code attach:** `scripts\u002Fmcp_app_launcher.ps1` mints a fresh U2M token each spawn via `databricks auth token --profile \u003Cyour-oauth-profile>` and bridges stdio to the App `\u002Fmcp` with `npx mcp-remote`.\n\nAPI surface: **only** the SQL Statement Execution API v2.0 (`POST \u002Fapi\u002F2.0\u002Fsql\u002Fstatements`, `GET \u002Fapi\u002F2.0\u002Fsql\u002Fstatements\u002F{id}`). No Jobs 2.1, Unity Catalog REST, or SCIM. Host shape `https:\u002F\u002Fadb-\u003Cworkspace-id>.\u003Cn>.azuredatabricks.net`.\n\n## Env vars\n\n| Var | Default \u002F example | Purpose |\n|---|---|---|\n| `DATABRICKS_HOST` | `https:\u002F\u002Fadb-\u003Cworkspace-id>.\u003Cn>.azuredatabricks.net` | Workspace URL (not a secret) |\n| `DATABRICKS_TOKEN` | unset in prod | PAT, local-dev only. Never log\u002Fcommit |\n| `DATABRICKS_WAREHOUSE_ID` | `\u003Cwarehouse-id>` | Target SQL warehouse |\n| `DATABRICKS_CATALOG` \u002F `DATABRICKS_SCHEMA` | `hive_metastore` \u002F `default` | Default namespace |\n| `DATABRICKS_APP_PORT` | injected by App | Bind port (takes precedence over `MCP_PORT`) |\n| `DATABRICKS_CLIENT_ID` \u002F `DATABRICKS_CLIENT_SECRET` | injected by App | Service-principal OAuth M2M (consumed by the Databricks SDK) |\n| `MCP_TRANSPORT` \u002F `MCP_PORT` \u002F `MCP_HOST` \u002F `MCP_SERVER_NAME` \u002F `LOG_FORMAT` \u002F `LOG_LEVEL` | stdio \u002F 8080 \u002F 0.0.0.0 \u002F databricks_mcp \u002F text \u002F INFO | Fleet transport + logging |\n\n## Tool inventory\n\nAll read-only (`readOnlyHint:True`). All take `response_format: markdown|json` (default markdown). Input models forbid extra keys and strip whitespace.\n\n| Tool | Purpose | SQL issued | Key params |\n|---|---|---|---|\n| `databricks_list_tables` | List tables in a schema | `SHOW TABLES IN \u003Cschema>` | `schema_name` (default `hive_metastore.default`, validated dotted identifier) |\n| `databricks_describe_table` | Describe a table's columns | `DESCRIBE TABLE \u003Ctable>` | `table` (required, validated dotted identifier) |\n| `databricks_run_select` | Run one arbitrary read-only statement | the statement, post read-only guard | `statement` (1-10000 chars, non-blank) |\n\n## API specifics\n\n- `DatabricksConnector.execute()` posts to `\u002Fapi\u002F2.0\u002Fsql\u002Fstatements` with `{warehouse_id, statement, catalog, schema, wait_timeout:\"25s\", format:\"JSON_ARRAY\"}`, then polls PENDING\u002FRUNNING (default 5 attempts x 2s, httpx timeout 60s). Any non-`SUCCEEDED` terminal state raises `DatabricksError` with the `status.error.message`.\n- Result shape: columns from `manifest.schema.columns[].name`, rows from `result.data_array` (empty list if absent). Returned to tools as `{\"columns\": [...], \"rows\": [[...]]}`.\n- **Poll budget is bounded** (~25s inline wait + ~10s polling). Queries that exceed it raise `DatabricksError` rather than waiting longer. This is a design limit, not a bug: for long queries, narrow the query.\n- Default namespace `hive_metastore.default` is the legacy Hive metastore, not a Unity Catalog catalog. Pass a fully-qualified `catalog.schema.table` to reach elsewhere.\n\n## Deployment\n\nPrimary prod target is a **Databricks App** (`app.yaml` runs `python src\u002Fmain.py` with `MCP_TRANSPORT=streamable-http`, `LOG_FORMAT=json`; the runtime injects `DATABRICKS_APP_PORT` + OAuth M2M creds). Deploy with `databricks apps create mcp-databricks` (the App resource name MUST start with `mcp-` or the AI Playground won't list it), `databricks sync`, `databricks apps deploy`. The caller IP must be on the workspace IP access list or the App returns 403. `app.yaml` + `requirements.txt` (kept in sync with pyproject by hand) drive the App build. Also runnable as stdio (engineer mode) or a Streamable-HTTP container.\n\n## Fleet conventions (adding a tool)\n\nScaffolded from `mcp-template-build`, conforms to the fleet conformance contract. Same shape as [[microsoft-graph]], [[sonarqube]], [[cribl]].\n\n1. Subclass `BaseModule` (or extend `TablesModule`) in `src\u002Fcustom_components\u002F`; `discover_modules()` instantiates each subclass at startup. Register under `fn.__name__`, which MUST start with `databricks_`.\n2. Input is a single Pydantic `BaseModel` (`ConfigDict(extra=\"forbid\")`, `Field(...)`); set all four annotations. Validate any identifier interpolated into SQL with `_validate_identifier`; never interpolate raw user free-text into a statement.\n3. respx-mocked `tests\u002Ftest_\u003Carea>.py` (mock `conn.execute`); no live warehouse in unit tests.\n4. Pre-push gate: `pytest -v` + `ruff check src tests` + `mypy src` (strict) + `check_pydantic_inputs.py src` + `check_no_print.py src` (stdout is the JSON-RPC channel; log to stderr) + `check_jwt_allowlist.py`.\n\nPython `>=3.12,\u003C4.0`, Poetry for dev (pip + `requirements.txt` for the App\u002FDocker build). Do not run the container conformance Docker gate locally; stdio release is githooks only.\n",{},"main","9f1f296b9b682f7dbd6a45516cec063c022fd01b","plugins\u002Fpitt-skills\u002Fskills\u002Fdatabricks","https:\u002F\u002Fgithub.com\u002Fjustin-pitt\u002Fpitt-skills","https:\u002F\u002Fgithub.com\u002Fjustin-pitt","https:\u002F\u002Fexecbound.ai","Security engineer building ExecBound, a deterministic policy layer for AI-agent actions","2026-11-04 01:00:27",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add justin-pitt\u002Fpitt-skills --skill databricks",{"tool":37,"command":38},"bunx","bunx skills add justin-pitt\u002Fpitt-skills --skill databricks",{"tool":40,"command":41},"pnpm","pnpm dlx skills add justin-pitt\u002Fpitt-skills --skill databricks","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjustin-pitt\u002Fpitt-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fpitt-skills\u002Fskills\u002Fdatabricks\u002FSKILL.md",true,[],[46,54,61,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":50,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":18},"01M78E5NQS1QSV0EEE2TWVXQ0X","vibesec","This skill helps Claude write secure web applications. Use this when working on any web application or when a user requests a scan or audit to ensure security best practices are followed.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjustin-pitt\u002Fpitt-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fpitt-skills\u002Fskills\u002Fvibesec\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":50,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"01M78E5DNJTX8NEQKVX8RTXYM2","ui-ux-guide","Modern, clean UI\u002FUX guidance + review skill. Use when you need actionable UX\u002FUI recommendations, design principles, or a design review checklist for new features or existing systems (web\u002Fapp). Focus on CRAP (Contrast\u002FRepetition\u002FAlignment\u002FProximity) plus task-first UX, information architecture, feedback & system status, consistency, affordances, error prevention\u002Frecovery, and cognitive load. Enforce a modern minimal style (clean, spacious, typography-led), reduce unnecessary copy, forbid emoji as icons, and recommend intuitive refined icons from a consistent icon set.","https:\u002F\u002Fgithub.com\u002Fjustin-pitt\u002Fpitt-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fpitt-skills\u002Fskills\u002Fui-ux-guide\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M78E5BQCKGV89JJ394VAP3QF","tufin","https:\u002F\u002Fgithub.com\u002Fjustin-pitt\u002Fpitt-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fpitt-skills\u002Fskills\u002Ftufin\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M78E52863FJJS5WX88WW93SY","tines","Tines is a no-code automation and orchestration platform commonly used as a SOAR replacement, IT automation engine, and workflow builder. Use this skill whenever the user mentions Tines, Tines stories, actions, the AI Agent action, Story copilot, Webhook actions, HTTP Request actions, Event Transform, Send to Story, Resources, Pages, Cases, Records, credentials, Connect Flows, formulas, pills (`\u003C\u003Cslug.body.field>>` syntax), the Tines API, the Tines Terraform provider, tenants, change control, self-hosted Tines, Helm charts for Tines, Tines Tunnel, Command-over-HTTP, Tines on Azure or AWS, Tines credits and the AI credit pool, the Workbench, MCP server templates exposed by Tines, or any automation or workflow build inside Tines. Also trigger when the user asks about migrating from Cortex XSOAR \u002F XSIAM or other SOAR platforms to Tines, designing playbook or story patterns, integrating security tools through Tines, building forms with Pages, running case management in Tines, or is debugging a Tines workflow, even if they don't name a specific Tines concept.","https:\u002F\u002Fgithub.com\u002Fjustin-pitt\u002Fpitt-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fpitt-skills\u002Fskills\u002Ftines\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M78E4VKT2QKNF2KRVFHH5ZFT","tines-3b","Tines 3B is a separate product from Tines (Stories), not an upgrade path. Workflows are git repositories, steps are containerized code directories that pipe stdin to stdout, and an AI agent builds them from prompts. Use this skill whenever the user mentions Tines 3B, 3B spaces, 3B workflows, steps, config.toml, route_auth, route_type, webpage routes, volumes and \u002Fstorage, Tines units (TUs), connectors and the credential proxy, 3B skills, watchtower, autofix, autotune, solo runs, 3B branches or push-live, the 3B REST API or MCP endpoint, GitSync, tunnels and networks, or docs.3b.tines.com. Also trigger when comparing 3B against Tines Stories, deciding which of the two a use case belongs in, or migrating between them. For classic Tines (stories, actions, pills, formulas, Cases, Records, Pages), use the `tines` skill instead.","https:\u002F\u002Fgithub.com\u002Fjustin-pitt\u002Fpitt-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fpitt-skills\u002Fskills\u002Ftines-3b\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M78E4K8ZYVEGAN4PQ1ZFY5DT","threatconnect","ThreatConnect TIP and Polarity overlay expert. Use for any task involving ThreatConnect or Polarity: REST API calls (v2\u002Fv3), authentication (Token\u002FHMAC), TQL queries, Indicators, Groups, Cases, Workflow, Tags, Security Labels, Associations, ThreatAssess scoring, CAL configuration, indicator deprecation, exclusion lists, TAXII feeds (inbound\u002Foutbound), feed metrics, dashboards, Query Cards, Threat Graph, ATT&CK Visualizer, Risk Quantifier, Polarity integrations (Core, IOC Submission, Intel Search, CAL, XSOAR), Polarity custom development (Node.js), Polarity server administration, Playbooks, Components, Workflow Playbooks, App Builder, TcEx, indicator distribution to SIEM\u002FSOAR (XSIAM, Sentinel, Splunk, Elastic, Tines, Torq, BlinkOps), HTTP errors, HMAC signature failures, indicator formatting (ASN, CIDR, Host, URL, Registry Key), or troubleshooting. Trigger even without explicit ThreatConnect\u002FPolarity mention if the task involves threat intelligence platform operations.","https:\u002F\u002Fgithub.com\u002Fjustin-pitt\u002Fpitt-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fpitt-skills\u002Fskills\u002Fthreatconnect\u002FSKILL.md",[],[]]