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>
3.9 KiB
3.9 KiB
@tpmjs/tools-markdown-lint-basic
Basic markdown linting to check for common issues.
Features
- Checks for trailing whitespace
- Detects multiple consecutive blank lines
- Validates heading hierarchy (no skipping levels)
- Ensures blank lines around headings
- Checks for consistent list marker style
- Detects hard tabs (recommends spaces)
- Validates code block language specification
- Checks link formatting (no bare URLs, no empty links)
Installation
npm install @tpmjs/tools-markdown-lint-basic
Usage
import { markdownLintBasicTool } from '@tpmjs/tools-markdown-lint-basic';
const result = await markdownLintBasicTool.execute({
markdown: `
# Title
## Section 1
#### Subsection (skips h3)
Some text with trailing spaces
Bare URL: https://example.com
`,
});
console.log(result.passed); // false (has errors)
console.log(result.summary);
// {
// errors: 1,
// warnings: 2,
// totalLines: 8,
// rulesChecked: ['no-trailing-spaces', 'no-multiple-blanks', ...]
// }
console.log(result.issues);
// [
// {
// rule: 'heading-increment',
// severity: 'error',
// line: 4,
// message: 'Heading level 4 skips level 3',
// context: '#### Subsection (skips h3)'
// },
// ...
// ]
API
markdownLintBasicTool.execute(input)
Input
markdown(string, required): The markdown content to lint
Output
Returns a LintResult object:
interface LintResult {
issues: LintIssue[];
passed: boolean; // true if no errors (warnings are OK)
summary: {
errors: number;
warnings: number;
totalLines: number;
rulesChecked: string[];
};
}
interface LintIssue {
rule: string; // Rule identifier
severity: 'error' | 'warning';
line: number; // Line number where issue occurs
column?: number; // Optional column number
message: string; // Human-readable message
context?: string; // Code snippet showing the issue
}
Rules
Errors (must fix)
- heading-increment: Headings must not skip levels (e.g., h1 → h3)
- no-hard-tabs: Hard tabs are not allowed (use spaces)
- no-empty-links: Link text cannot be empty
Warnings (should fix)
- no-trailing-spaces: Lines should not have trailing whitespace
- no-multiple-blanks: No more than 2 consecutive blank lines
- blanks-around-headings: Headings should have blank lines before/after
- list-marker-style: Use consistent list markers (-, *, or +)
- fenced-code-language: Code blocks should specify a language
- no-bare-urls: URLs should be formatted as markdown links
Examples
Check for Errors Only
const result = await markdownLintBasicTool.execute({ markdown });
if (!result.passed) {
const errors = result.issues.filter(i => i.severity === 'error');
console.error(`Found ${errors.length} errors:`);
for (const error of errors) {
console.error(`Line ${error.line}: ${error.message}`);
}
}
Format Issue Report
const result = await markdownLintBasicTool.execute({ markdown });
for (const issue of result.issues) {
const icon = issue.severity === 'error' ? '❌' : '⚠️';
console.log(`${icon} Line ${issue.line}: ${issue.message}`);
if (issue.context) {
console.log(` ${issue.context}`);
}
}
Group by Rule
const result = await markdownLintBasicTool.execute({ markdown });
const byRule = new Map<string, LintIssue[]>();
for (const issue of result.issues) {
if (!byRule.has(issue.rule)) {
byRule.set(issue.rule, []);
}
byRule.get(issue.rule)!.push(issue);
}
for (const [rule, issues] of byRule) {
console.log(`${rule}: ${issues.length} issues`);
}
Use Cases
- Pre-commit hooks for documentation
- CI/CD markdown validation
- Documentation quality checks
- Style guide enforcement
- Automated code review
License
MIT