Aggregate Markdown folders into cohesive knowledge bases with automated table of contents generation, cross-link validation and rewriting, heading normalization, and multi-format export (HTML, PDF, DOCX, EPUB).
Open the source and read safety notes before installing.
Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.
Decision playbook
Signals are comparatively strong, but you should still validate source, privacy posture, and package provenance for your environment.
0
96
—
No baseline selected
No major trust-signal divergence detected in the current selection.
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Source provenance statusRequired
Marked as first-party.
Metadata reviewed
Registry metadata indicates a reviewed listing.
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Trust level risk gateRequired
Trust level does not block evaluation.
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Package verification flag
Package marked verified.
Checksum metadata
SHA-256 hash is present.
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Baseline comparison available
No baseline peer selected yet.
Diverging trust signals identified
No major trust-signal divergence found.
Setup at a glance
Copy-ready — paste the snippet to get started.
Adoption plan
Current risk score 0/100. Use staged verification before broader rollout.
Validate source and review signals before any execution.
Confirm source provenanceRequired
Source URL/provenance metadata is present.
Confirm metadata review state
Listing has review metadata.
Verify install payload
Install/config payload exists and can be inspected.
Confirm safety, privacy, and package integrity signals.
Review safety notesRequired
Safety notes are present.
Review privacy notesRequired
Privacy notes are present.
Verify package integrity metadata
Package verification/checksum metadata is available.
Adopt in controlled steps based on the selected plan.
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Evidence readiness
Required evidence gates are covered (6/6 signals complete).
Source repository/provenance is listed.
Required in this preset
Review metadata is present.
Required in this preset
Safety notes are present.
Required in this preset
Privacy notes are present.
Optional in this preset
Package integrity metadata is present.
Optional in this preset
Install payload is available.
Required in this preset
Required evidence gates are covered for this preset.
Decision timeline
6/6 steps complete with no blocking gaps for this preset.
triage
Source/provenance metadata is available.
triage
Review metadata is available.
verify
Safety notes are available.
verify
Privacy notes are available.
verify
Package integrity metadata is available.
rollout
Install payload is available.
No required blockers for this timeline preset.
Prerequisite readiness
6 prerequisites to line up before setup.
Safety & privacy surface
1 safety and 2 privacy notes across 3 risk areas. Review closely: credentials & tokens, third-party handling.
| Platform | Support | Install path |
|---|---|---|
| claude-code | Native | .claude/skills/<skill-name>/SKILL.md |
| codex | Native | .agents/skills/<skill-name>/SKILL.md |
| windsurf | Native | .windsurf/skills/<skill-name>/SKILL.md |
| gemini | Native | .gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md |
| cursor | Adapter | .cursor/rules/<skill-name>.mdc |
| cli | Manual | AGENTS.md or tool-specific context file |
import { readFileSync, readdirSync } from 'node:fs';
import { join } from 'node:path';
import { unified } from 'unified';
import remarkParse from 'remark-parse';
import remarkStringify from 'remark-stringify';
import remarkToc from 'remark-toc';
import remarkSlug from 'remark-slug';
const dir = './notes';
const files = readdirSync(dir).filter(f => f.endsWith('.md'));
for (const file of files) {
const input = readFileSync(join(dir, file), 'utf8');
const tree = unified()
.use(remarkParse)
.use(remarkSlug)
.use(remarkToc, { tight: true })
.use(remarkStringify)
.processSync(input);
console.log(String(tree));
}Claude can organize, process, and transform Markdown documentation into cohesive knowledge bases. Generate table of contents, fix broken links, convert formats, create static sites, and export to PDF or HTML.
SKILL.md.SKILL.md content as reusable workflow instructions..gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md where supported..cursor/rules/*.mdc adapter for project rules.Required:
What Claude handles:
Prompt: "Generate a table of contents from all these Markdown files. Include links to each section."
Claude will:
Prompt: "Check all internal links in these Markdown files and fix any broken ones. Report what was fixed."
Claude will:
Prompt: "Convert all these Markdown docs to a single PDF with:
Claude will:
Prompt: "Generate a static HTML site from these docs:
Claude will:
"Create documentation site:
1. Parse all .md files in docs/
2. Generate sidebar navigation
3. Create search index
4. Add syntax highlighting for code blocks
5. Export as static HTML site
Use clean, professional styling."
"Consolidate scattered notes:
1. Combine all Markdown files into sections
2. Generate master TOC
3. Normalize heading levels (start all at H1)
4. Fix relative links between files
5. Create single comprehensive document
Export as both Markdown and PDF."
"Generate professional README.md:
1. Extract project info from package.json
2. Add badges (build status, version, license)
3. Create sections: About, Installation, Usage, Contributing
4. Add table of contents with anchor links
5. Include code examples from docs/"
"Export documentation in multiple formats:
1. HTML (with navigation and search)
2. PDF (with TOC and page numbers)
3. EPUB (for e-readers)
4. DOCX (for Word)
Maintain consistent styling across all formats."
Issue: Broken links after reorganizing files Solution: "Scan all links and update paths based on new file structure"
Issue: TOC not rendering correctly Solution: Ensure consistent heading hierarchy (H1 → H2 → H3, no skipping)
Issue: Images not showing in PDF export Solution: "Use absolute paths for images" or "Embed images inline as base64"
Issue: Code blocks losing formatting Solution: "Preserve code block syntax highlighting in export" and specify language
Issue: Special characters breaking exports Solution: "Escape special characters" or "Use UTF-8 encoding throughout"
Issue: Large files causing memory issues Solution: "Process files in batches" or "Split into smaller sections first"
Show that Markdown Knowledge Base Composer Skill is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/skills/markdown-knowledge-base-composer)Markdown Knowledge Base Composer Skill side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
2 trust signals differ across this comparison (Package trust, Source provenance).
| Field | Aggregate Markdown folders into cohesive knowledge bases with automated table of contents generation, cross-link validation and rewriting, heading normalization, and multi-format export (HTML, PDF, DOCX, EPUB). Open dossier | ARIS is a Markdown-only skill workflow pack for autonomous ML research agents, with idea discovery, experiment planning, auto-review loops, paper writing, rebuttal, resubmission, slides, posters, Research Wiki, and cross-model reviewer workflows for Claude Code, Codex, OpenClaw, Cursor, and other agent hosts. Open dossier | MIT-licensed BrowserAct Agent Skill pack for installing and operating the `browser-act` browser automation CLI from Claude Code, Codex, OpenClaw, Cursor, OpenCode, Windsurf, Gemini CLI, and other skills-compatible agents. Open dossier | Build JavaScript and TypeScript apps with Bun, an all-in-one toolchain that replaces Node.js, npm, a bundler, and a test runner with one fast binary that executes TypeScript directly. Open dossier |
|---|---|---|---|---|
| Next steps | ||||
| Trust | ||||
| Review status | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed |
| Package trustDiffers | Package verified2025-10-15 | Package not verified | Package not verified | Package verified2025-10-23 |
| Source provenanceDiffers | Source-backed | Source-backed | Source-backed | No submission link |
| Submitter | — | — | — | — |
| Install risk | Review first | Review first | Review first | Low risk |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Brand | — | — | — | |
| Category | skills | skills | skills | skills |
| Source | First-party | Source-backed | Source-backed | First-party |
| Author | JSONbored | wanshuiyin | BrowserAct | JSONbored |
| Added | 2025-10-15 | 2026-06-18 | 2026-06-18 | 2025-10-23 |
| Platforms | ||||
| Harness | ||||
| Source repo | — | — | — | — |
| Safety notes | ✓Installs npm packages (remark, unified) and runs scripts that read your Markdown files and write composed/transformed output to disk, overwriting files at the target path; review before running on an existing knowledge base. | ✓ARIS skills can guide agents through code changes, experiment planning, experiment execution, paper drafting, rebuttal drafting, and cross-model review loops; treat those workflows as high-impact research automation rather than passive documentation. The `research-pipeline` skill supports auto-proceed modes and reviewer loops. Keep expensive runs, repository mutations, cloud/GPU jobs, and paper-submission decisions behind explicit human approval. Cross-model review through Codex MCP, Claude-review, Gemini-review, or similar reviewer adapters is a quality-control signal, not scientific proof or peer review. Generated claims, citations, tables, plots, ablations, rebuttals, and paper text need source checks, experiment audits, citation audits, and human scientific review before being relied on or submitted. Review all copied skills, scripts, MCP server configuration, and reviewer routing before installing them into a sensitive repository or giving them shell, file, web, cloud, or GPU access. | ✓BrowserAct can open pages, click, type, upload files, inspect state, capture screenshots, read page text, handle dialogs, export cookies, capture network requests, and operate logged-in browser sessions. Use BrowserAct only on sites, accounts, and data sources where the user has authorization. Do not use it to evade access controls, violate site terms, scrape disallowed data, or bypass rate limits. The entry skill declares confirmation gates for browser creation, deletion, local Chrome profile import, proxy/security changes, logins, form submissions, file uploads, and other sensitive operations; preserve those gates in agent workflows. `solve-captcha` may send the challenge image to BrowserAct's verification-assistance service according to the skill metadata; do not use it with sensitive or unauthorized pages. `remote-assist` can generate a live handoff URL for a human to take over. Treat that URL as access to the active browser session. Skill Forge can generate reusable automation skills from explored sites. Review generated scripts, selectors, network assumptions, output schemas, and site authorization before reusing them at scale. | ✓Installing Bun globally (`npm install -g bun`) adds a runtime to your system; install from the official npm package or bun.sh and keep it updated. Bun runs JavaScript/TypeScript with full system access like Node.js; review code before executing it, especially untrusted scripts. |
| Privacy notes | ✓Inputs can include source files, prompts, logs, account metadata, repository details, and operational context that may be sent to the configured AI model. Redact secrets, customer data, private URLs, credentials, and proprietary implementation details before sharing prompts, reports, or generated artifacts. | ✓Research automation can expose unpublished hypotheses, paper drafts, peer-review text, datasets, logs, source code, experiment traces, model outputs, reviewer comments, account names, and GPU or cloud configuration to the selected model providers and MCP tools. Cross-model review loops may send the same research artifact to multiple providers or local/remote reviewer services depending on configuration. Research Wiki, traces, generated reports, paper artifacts, and run logs can persist confidential results or private review material on disk. Do not share confidential reviews, unreleased findings, private datasets, credentials, proprietary code, or submission-sensitive artifacts with external services unless the research and account policies allow it. | ✓BrowserAct workflows can expose page content, screenshots, URLs, credentials typed into forms, cookies, browser profiles, uploaded files, downloaded files, network requests, HAR data, session names, browser descriptions, and logs. The BrowserAct skill metadata states that cookies, login sessions, page content, credentials, and browser profile data stay local, except the CAPTCHA challenge image when `solve-captcha` is invoked. Chrome-direct and profile import workflows can connect agents to existing local browser state. Treat those modes as account access, not a blank test browser. Log reports, feedback, Discord support, generated Skill Forge packages, and shared screenshots can leak private browsing or account context if submitted without review. Managed proxy, stealth browser, and API-key features create additional BrowserAct service dependencies beyond local CLI execution. | ✓Bun apps you build can read local files, environment variables, and make network calls like any Node.js app; keep secrets in environment variables and review what your code sends externally. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | — | — | — | — |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Markdown research-agent skills for idea discovery, experiment automation, paper writing, rebuttal, and cross-model review loops.
BrowserAct entry skill for agent-safe browser automation, indexed page interaction, session isolation, remote assist, and reusable Skill Forge flows.
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.