Automated summary
Launches a TUI to review a markdown file with line-by-line commenting capabilities.
Strengths
- Interactive line-by-line navigation with j/k keys
- Multiple comment types: Blocker, Concern, Question, Suggestion, Praise, Acknowledge
- Syntax highlighting for code blocks
- Export comments to markdown or clipboard
Limitations
- Only works with markdown files
- Requires a TUI-compatible terminal environment
- Depends on the external lgtm package and bun
When you need a structured, interactive review of a markdown document such as a design doc or plan.
When reviewing non-markdown files or when a non-interactive review is sufficient.
Security analysis
SafeThe skill runs a TUI tool via bun/bunx on a user-specified markdown file, with no destructive commands, external data exfiltration, or obfuscation. It uses tmux and third-party packages but only for intended interactive review, and does not execute arbitrary shell commands from the file content.
No concerns found
How this analysis is madeExamples
Review the plan in plan.md using lgtm.I want to review the document @CLAUDE.md line by line.Use lgtm to review the piped content.name: lgtm description: Launch lgtm TUI to review a markdown file with line-by-line commenting argument-hint: <file-path> [--stdin] allowed-tools: Bash(bun run *), Bash(bunx *), Bash(tmux *), Read
Launch lgtm to review the specified markdown file or piped content.
Usage
/lgtm path/to/plan.md # Opens TUI for review (auto-spawns in tmux pane) /lgtm @CLAUDE.md # @ prefix is stripped automatically /lgtm --stdin # Review content piped from stdin
What it does
Opens an interactive TUI for reviewing markdown documents with:
- Line-by-line navigation (j/k)
- Comment types: Blocker, Concern, Question, Suggestion, Praise, Acknowledge
- Syntax highlighting for code blocks
- Export to markdown (E) or clipboard (y)
- Summary view (v)
Instructions
When this skill is invoked, follow these steps:
- Parse arguments: Extract the file path from
$ARGUMENTS. If it starts with@, strip that prefix. Ignore--tmuxif present (it's automatic). - Resolve path: Convert the file path to an absolute path if it isn't already.
- Read the file: Use the Read tool to load the full file content into context. This is essential so you can correlate the user's line-level comments with actual file content.
- Create export path: Generate
/tmp/lgtm-export-{basename-without-extension}.md - Run the TUI: Check if
${CLAUDE_PLUGIN_ROOT}/node_modulesexists to determine the run command. The--export-on-quitflag automatically enables tmux mode and waits for the user to quit.- If
${CLAUDE_PLUGIN_ROOT}/node_modulesexists (local dev):bun run ${CLAUDE_PLUGIN_ROOT}/src/cli.ts "<resolved-file-path>" --export-on-quit "<export-path>" - If
node_modulesdoes not exist (marketplace install):bunx @hapticdata/lgtm "<resolved-file-path>" --export-on-quit "<export-path>"
- If
- Read the export: After the command returns (user has quit the TUI), use the Read tool to read the export file.
- Respond in review mode: This is a collaborative review workflow. After reading the export:
- Correlate each comment with the corresponding line(s) from the original file content you read in step 3.
- Summarize the user's feedback, grouping by comment type (Blockers, Concerns, Questions, Suggestions, Praise).
- Proactively address blockers and concerns first — propose concrete code or content changes to resolve them.
- Answer any questions the user raised.
- Acknowledge suggestions and praise.
- Offer to iterate on the file by applying the proposed changes.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/interactive-markdown-review-with-lgtm-tui-mm5t8alf/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/interactive-markdown-review-with-lgtm-tui-mm5t8alf' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/interactive-markdown-review-with-lgtm-tui-mm5t8alf/download' --output '.skill-downloads/interactive-markdown-review-with-lgtm-tui-mm5t8alf/SKILL.md.part' && mv '.skill-downloads/interactive-markdown-review-with-lgtm-tui-mm5t8alf/SKILL.md.part' '.skill-downloads/interactive-markdown-review-with-lgtm-tui-mm5t8alf/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Bash(bun run *), Bash(bunx *), Bash(tmux *), Read
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/interactive-markdown-review-with-lgtm-tui-mm5t8alf/SKILL.md' && test -s '.skill-downloads/interactive-markdown-review-with-lgtm-tui-mm5t8alf/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/lgtm' && cp -R '.skill-downloads/interactive-markdown-review-with-lgtm-tui-mm5t8alf' '.claude/skills/lgtm'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/interactive-markdown-review-with-lgtm-tui-mm5t8alf'openskills read 'interactive-markdown-review-with-lgtm-tui-mm5t8alf'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/interactive-markdown-review-with-lgtm-tui-mm5t8alf/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.