Firetiger
Firetiger is an AI-powered observability platform. Telemetry (traces, logs, metrics)
lands in Apache Iceberg tables you query with SQL, and autonomous agents monitor your services, investigate
issues, and watch deployments.
This skill is a router. Identify what the user wants and invoke the matching specialized skill — each one
is self-contained and carries the gotchas for its task.
How you talk to Firetiger
Two mechanisms, referenced throughout the skills:
- The Firetiger MCP server —
https://api.cloud.firetiger.com/mcp/v1 (OAuth 2.0 bearer; the first tool
call opens a browser to sign in). Tools: get_ingest_credentials, get_deploy_credentials, query,
monitor_pr, create_agent_with_goal, send_agent_message, read_agent_messages, resolve_url,
get_subscription_status/get_checkout_url (billing), onboard_github/onboard_slack/onboard_linear
(OAuth connect), and generic CRUD (schema/list/get/create/update/delete). The collections a
client agent works with: agents + sessions (create/run agents), triggers + scheduled-agent-runs
(automate them), investigations (AI diagnosis sessions), issues (Known Issues, IDs are FT-{n} call
signs), monitoring-plans (deploy monitoring, read/delete), and connections (integrations). Always
schema a collection before create/update. Some tools and collections are gated by deployment config
and API-key policy.
- The
@firetiger GitHub flow — comment @firetiger on a pull request to have Firetiger monitor the
deployment that PR produces.
Key gotcha: if the MCP tools aren't available, the user hasn't connected the Firetiger MCP server yet. The
target skill handles this — it tells the user to connect https://api.cloud.firetiger.com/mcp/v1 and sign in,
then retries.
Routing
| The user wants to… |
Skill |
Trigger phrases |
| Onboard a project end-to-end (detect stack → instrument → connect → agent) |
firetiger-setup |
"set up Firetiger", "onboard this project", "connect my app" |
| Add OpenTelemetry instrumentation (Node/Next.js/Python/Go/Rust) |
firetiger-instrument |
"instrument my app", "add OpenTelemetry", "send traces" |
| Query traces, logs, or metrics with SQL |
firetiger-query |
"find traces", "search logs", "show me errors", "analyze latency" |
| Investigate an incident and track findings |
firetiger-investigate |
"investigate", "diagnose", "what's wrong with", "troubleshoot" |
| Monitor a PR/deployment |
firetiger-monitor-deploy |
"monitor this PR", "watch this deploy", "@firetiger" |
| Create a monitoring agent, or configure agents/triggers |
firetiger-create-agent |
"create an agent", "monitor X automatically", "schedule an agent" |
Execution
- Classify the request into one row above.
- Invoke the corresponding skill with the Skill tool (e.g.
firetiger-query).
- If a request spans categories ("set up Firetiger and monitor my next PR"), handle them sequentially —
usually
firetiger-setup first, then the follow-up.
Resources
1---2name: firetiger3description: Use when the user mentions Firetiger or wants to work with their observability data — setting up Firetiger, instrumenting an app with OpenTelemetry, querying traces/logs/metrics with SQL, investigating an incident, monitoring a PR or deployment, or creating a monitoring agent. Always use this skill when the user says "Firetiger", even for simple asks — it routes to the specialized skill that carries the critical gotchas (Basic-auth ingest, DuckDB SQL over per-service tables, the @firetiger comment flow) that prevent common mistakes.4license: Apache-2.05---67# Firetiger89[Firetiger](https://firetiger.com) is an AI-powered observability platform. Telemetry (traces, logs, metrics)10lands in Apache Iceberg tables you query with SQL, and autonomous agents monitor your services, investigate11issues, and watch deployments.1213This skill is a **router**. Identify what the user wants and invoke the matching specialized skill — each one14is self-contained and carries the gotchas for its task.1516## How you talk to Firetiger1718Two mechanisms, referenced throughout the skills:1920- **The Firetiger MCP server** — `https://api.cloud.firetiger.com/mcp/v1` (OAuth 2.0 bearer; the first tool21 call opens a browser to sign in). Tools: `get_ingest_credentials`, `get_deploy_credentials`, `query`,22 `monitor_pr`, `create_agent_with_goal`, `send_agent_message`, `read_agent_messages`, `resolve_url`,23 `get_subscription_status`/`get_checkout_url` (billing), `onboard_github`/`onboard_slack`/`onboard_linear`24 (OAuth connect), and generic CRUD (`schema`/`list`/`get`/`create`/`update`/`delete`). The collections a25 client agent works with: `agents` + `sessions` (create/run agents), `triggers` + `scheduled-agent-runs`26 (automate them), `investigations` (AI diagnosis sessions), `issues` (Known Issues, IDs are `FT-{n}` call27 signs), `monitoring-plans` (deploy monitoring, read/delete), and `connections` (integrations). Always28 `schema` a collection before `create`/`update`. Some tools and collections are gated by deployment config29 and API-key policy.30- **The `@firetiger` GitHub flow** — comment `@firetiger` on a pull request to have Firetiger monitor the31 deployment that PR produces.3233**Key gotcha:** if the MCP tools aren't available, the user hasn't connected the Firetiger MCP server yet. The34target skill handles this — it tells the user to connect `https://api.cloud.firetiger.com/mcp/v1` and sign in,35then retries.3637## Routing3839| The user wants to… | Skill | Trigger phrases |40|---|---|---|41| Onboard a project end-to-end (detect stack → instrument → connect → agent) | **`firetiger-setup`** | "set up Firetiger", "onboard this project", "connect my app" |42| Add OpenTelemetry instrumentation (Node/Next.js/Python/Go/Rust) | **`firetiger-instrument`** | "instrument my app", "add OpenTelemetry", "send traces" |43| Query traces, logs, or metrics with SQL | **`firetiger-query`** | "find traces", "search logs", "show me errors", "analyze latency" |44| Investigate an incident and track findings | **`firetiger-investigate`** | "investigate", "diagnose", "what's wrong with", "troubleshoot" |45| Monitor a PR/deployment | **`firetiger-monitor-deploy`** | "monitor this PR", "watch this deploy", "@firetiger" |46| Create a monitoring agent, or configure agents/triggers | **`firetiger-create-agent`** | "create an agent", "monitor X automatically", "schedule an agent" |4748## Execution49501. Classify the request into one row above.512. Invoke the corresponding skill with the Skill tool (e.g. `firetiger-query`).523. If a request spans categories ("set up Firetiger and monitor my next PR"), handle them sequentially —53 usually `firetiger-setup` first, then the follow-up.5455## Resources5657- [Firetiger Documentation](https://docs.firetiger.com)58- [OpenTelemetry Documentation](https://opentelemetry.io/docs/)
firetiger-oss