tpmjs/packages/tools/official/runbook-draft/README.md
Ajax Davis 5d2096fb5d feat: add 100+ official TPMJS tools
Implements a comprehensive suite of AI SDK v6 tools across multiple categories:

- Research (5): page-brief, compare-pages, source-credibility, claim-checklist, timeline-from-text
- Web (10): fetch-text, links-catalog, extract-meta, extract-json-ld, redirect-trace, sitemap-read, rss-read, table-extract, robots-policy, url-normalize
- Data (15): csv-parse, csv-stringify, json-repair, json-schema-validate, yaml-parse, yaml-stringify, text-chunk, normalize-whitespace, dedupe-by-key, pivot, rows-filter, rows-sort, rows-group-aggregate, rows-join, schema-infer
- Doc (12): toc-generate, glossary-build, faq-from-text, executive-brief, decision-record-adr, prd-outline, acceptance-criteria, style-rewrite
- Eng (12): diff-text-unified, env-var-docs-generate, dependency-audit-lite, conventional-commit-suggest, markdown-lint-basic, test-case-generate, stacktrace-parse, release-notes, changelog-entry, release-checklist
- Security (7): redact-secrets, secret-scan-text, url-risk-heuristic, csp-compose, hardening-checklist-web, access-control-matrix, data-classification-heuristic
- Stats (9): effect-size-suite, bootstrap-ci, permutation-test, multiple-testing-adjust, linear-regression-ols, logistic-regression, time-series-decompose-lite, anomaly-detect-mad
- Ops (7): slo-draft, runbook-draft, postmortem-draft, postmortem-action-extractor, error-log-triage, coverage-tracker, monitoring-gap-analysis
- Agent (15): prompt-to-workflow-skeleton, workflow-validate-io, workflow-explain, workflow-cost-estimate, tool-call-accuracy-score, eval-fixture-build, guardrail-policy-draft, workflow-auto-repair, tool-selection-plan, novelty-score-workflow, workflow-variant-generate, config-normalize, recipe-*
- Utility (8): base64-encode, base64-decode, hash-text, regex-extract, template-render, date-parse, json-path-query, url-parse
- HTML (3): html-sanitize, html-to-markdown, markdown-to-html

All tools follow AI SDK v6 pattern with tool() and jsonSchema<T>().

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-31 22:55:56 +10:00

2 KiB

@tpmjs/tools-runbook-draft

Draft operational runbooks from procedure steps with commands and verification.

Installation

npm install @tpmjs/tools-runbook-draft

Usage

import { runbookDraftTool } from '@tpmjs/tools-runbook-draft';

const result = await runbookDraftTool.execute({
  title: 'Database Migration Runbook',
  steps: [
    {
      action: 'Backup the database',
      command: 'pg_dump mydb > backup.sql',
      verification: 'Check that backup.sql exists and has content',
    },
    {
      action: 'Stop the application',
      command: 'systemctl stop myapp',
      verification: 'Run systemctl status myapp to confirm stopped',
    },
    {
      action: 'Run migrations',
      command: 'npm run migrate',
      verification: 'Check migration logs for errors',
    },
    {
      action: 'Start the application',
      command: 'systemctl start myapp',
      verification: 'Run systemctl status myapp to confirm running',
    },
  ],
});

console.log(result.runbook);
// Markdown-formatted runbook with all steps
console.log(`Steps: ${result.stepCount}`);
console.log(`Has commands: ${result.hasCommands}`);

Features

  • Generates structured markdown runbooks
  • Supports optional command examples in code blocks
  • Includes verification steps for each action
  • Automatically adds prerequisites section when commands are present
  • Timestamps generation for version tracking

Input

RunbookDraftInput

  • title (string, required): Title of the runbook
  • steps (array, required): Array of procedure steps

RunbookStep

  • action (string, required): Description of the action to perform
  • command (string, optional): Command to execute
  • verification (string, optional): Verification step to confirm success

Output

RunbookDraft

  • runbook (string): Markdown-formatted runbook document
  • stepCount (number): Number of steps in the runbook
  • hasCommands (boolean): Whether any steps include commands

License

MIT