MRSF Document Review
Turns Markdown feedback into anchored, resolvable review comments (a real YAML sidecar) instead of a flat comment list.
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 15, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · d566c10
Ran the real @mrsf/cli (same engine the MCP tools wrap) against a throwaway doc: produced a genuine validated YAML sidecar with UUIDs, severity/type tags, and fuzzy-reanchor metadata, versus a baseline flat-text review list - concretely more useful for multi-round or CI-driven review, but nothing works until the separate @mrsf/mcp server is installed and registered as an MCP server first.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 4/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What MRSF Document Review does
Reviews Markdown documents by adding structured, line-anchored comments through the MRSF (Sidemark) MCP server, tagging each with type/severity and storing them in a .review.yaml sidecar that survives document edits via re-anchoring. Triggers when asked to review, comment on, or give feedback on a Markdown file; requires the separate @mrsf/mcp server to be installed and registered before the tools exist.
How to install MRSF Document Review
git clone https://github.com/wictorwilen/MRSF
mkdir -p ~/.claude/skills
cp -r MRSF/examples/mrsf-review ~/.claude/skills/mrsf-review
npm install -g @mrsf/mcp # required MCP server, not bundled in the skill folder
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger MRSF Document Review
-
/mrsf-reviewTurns Markdown feedback into anchored, resolvable review comments (a real YAML sidecar) instead of a flat comment list.
It also activates on plain-language prompts like these:
-
Review this markdown doc and leave anchored comments I can resolve -
Give feedback on this deployment doc with severity-tagged comments -
Comment on this spec so the notes survive future edits to the file
Frequently asked questions
- Is the MRSF Document Review skill free?
- Yes. The skill itself is free from wictorwilen/MRSF. SkillProof publishes the install command and an independent test verdict at no cost.
- Does MRSF Document Review work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Works with setup. Ran the real @mrsf/cli (same engine the MCP tools wrap) against a throwaway doc: produced a genuine validated YAML sidecar with UUIDs, severity/type tags, and fuzzy-reanchor metadata, versus a baseline flat-text review list - concretely more useful for multi-round or CI-driven review, but nothing works until the separate @mrsf/mcp server is installed and registered as an MCP server first.
- What is the MRSF Document Review SkillProof Score?
- 8.8/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install MRSF Document Review?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use MRSF Document Review with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.