Talaria
Docs

Agent skills overview

Talaria plugin skills closed loop — how they map to MCP tools and existing playbooks.

agentsskillsmcpplaybook

The Talaria plugin for Cursor and Grok Bot includes five closed-loop skills that guide agents from initial connection through fix verification. These skills wrap the hosted MCP tools and reference the detailed playbooks in this docs repo.

Plugin: github.com/newtalaria/talaria-agent-plugin
Listing: cursor.directory/plugins/talaria

Closed-loop workflow

text
talaria-get-started → talaria-instrument → talaria-observe-performance → talaria-triage-issue → talaria-verify-fix

Each skill focuses on one phase, hands off to the next when appropriate, and constrains writes to prevent silent project creation or status changes.

Skills → playbooks map

Skill Purpose Core tools Existing playbook
talaria-get-started Connect MCP, confirm org/project, first smoke read get_connection, get_projects, docs_*, search_errors Orientation only — no dedicated playbook
talaria-instrument SDK install, create project/key, send test event setup_project, send_test_event, search_events, docs_get Add Talaria with an agent
talaria-observe-performance Health, traces, spans, queries, sessions, monitors get_project_stats, search_traces, list_suspect_spans, list_database_queries Read-only stats — extends playbook tools
talaria-triage-issue Investigate one issue: pack → trace/replay → optional GitHub get_error, get_trace, get_replay, get_suspect_commits, create_github_issue, update_issue_status Triage issues with an agent
talaria-verify-fix After release: verdict + optional status update verify_fix, list_releases, get_release, wait_for_event, update_issue_status Extends triage with release verification — see verify_fix tool in MCP

Where agents get these skills

From the Talaria plugin

Install the Talaria plugin in Cursor Marketplace or Grok Bot (handle talaria once approved). The plugin includes:

  • mcp.json pointing at https://api.newtalaria.com/mcp
  • Five skill SKILL.md files in skills/ with YAML frontmatter

Agents that load the plugin automatically discover and apply these skills when relevant.

From Markdown playbooks via docs_get

Agents that do not have the plugin installed can still follow the same workflows by reading the playbooks via MCP docs_get:

  • Install: docs_get path guides/add-talaria-with-an-agent
  • Triage: docs_get path guides/triage-issues-with-an-agent
  • Configuration: docs_get path getting-started/configuration
  • SDK reference: docs_get path sdk/<id>/README (e.g. sdk/flutter/README)

The playbooks are the detailed how-to; the skills are workflow guardrails that enforce read-only smoke, ask before create, and hand off appropriately.

Tool scopes

Scope Includes
mcp:read get_connection, get_projects, get_project, search_errors, get_error, search_events, get_event, search_traces, get_trace, get_replay, get_suspect_commits, get_source_context, get_source_map, list_suspect_spans, list_database_queries, search_sessions, get_project_stats, feature flag reads, list_releases, get_release, wait_for_event, verify_fix
mcp:write All read tools plus update_project_settings, create_project, send_test_event, update_issue_status, add_issue_comment, create_github_issue, link_github_issue, unlink_github_issue, feature flag writes
mcp:keys All write tools plus create_api_key, setup_project

Install scopes are mcp:read mcp:write mcp:keys. Skills ask before using write tools.

Skill usage examples

First-time setup

User: "Add Talaria to this Flutter project"

  1. talaria-get-started → authenticate, confirm org
  2. talaria-instrument → detect Flutter, docs_get SDK hub, setup_project with confirmed: true, wire talaria_flutter, send_test_event, search_events with environment: development
  3. Hand off to talaria-observe-performance or talaria-triage-issue when ready

Production investigation

User: "What's failing in production?" or paste a Talaria issue URL

  1. talaria-get-started → confirm connection (may skip if already connected)
  2. talaria-triage-issue → get_error with issueId, read pack (latest instance, breadcrumbs, release, suspects), optional get_trace / get_replay, state hypothesis, optional GitHub create/link

Post-release verification

User: "Did version 2.1.0 fix issue NORTH-4F2?"

  1. talaria-verify-fix → list_releases, get_release, verify_fix with issueId + release, report verdict (verified, regressed, pending_adoption, etc.), optional update_issue_status to resolved after user approval

Skills vs playbooks

Source Best for Provides
Skills (plugin) Agents with plugin support (Cursor, Grok Bot) Workflow guardrails, read-only checks, ask-before-write, hand-offs
Playbooks (docs_get) Any agent via MCP docs_* tools Detailed how-to, SDK snippets, conversation scripts, must-not rules

Skills reference playbooks when needed (docs_get path guides/add-talaria-with-an-agent). Playbooks are the canonical source of truth for SDK wiring; skills enforce the workflow.