Open plan in lgtm for review

VerifiedCaution

Opens the current plan file in lgtm for user review. This skill is used after generating a plan to let the user provide feedback, then reads and returns that feedback to the conversation.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#plan-review#feedback#lgtm#workflow

Recommended for

Automated summary

Opens a plan file in the lgtm TUI for user review and collects feedback after the user quits.

Strengths

  • Integrates smoothly with plan file workflows
  • Exports feedback automatically on exit
  • Supports both local dev and marketplace installation
  • Works in tmux or current terminal

Limitations

  • Requires lgtm to be installed and configured
  • Only works with plan files, not arbitrary markdown
  • Feedback is read as plain text, not structured
When to use it

Use after generating a plan file to get user feedback before proceeding with implementation.

When not to use it

Do not use for simple yes/no approvals or when the user prefers inline feedback in the conversation.

Security analysis

Caution
Quality score75/100

The skill executes a third-party TUI tool from npm using bunx, which could potentially contain malicious code or vulnerabilities. The use of tmux adds a minor risk of session interference, but the overall purpose is safe.

Findings
  • •Uses third-party npm package via bunx, introducing supply chain risk.
  • •Uses tmux, which can split terminal and may interact with other sessions if not properly isolated.
How this analysis is made

Examples

Open plan file for review
Open the plan file for review
Review current plan
I've generated a plan, let me review it before we proceed.

name: lgtm-plan description: Open the current plan file in lgtm for user review allowed-tools: Bash(bun run *), Bash(bunx *), Bash(tmux *), Read

Open the plan file in lgtm so the user can review and add feedback. After the user quits the TUI, read their feedback and return it to the conversation.

When to use

After generating a plan file, invoke this skill to open it for user review.

Steps

  1. Determine the export path based on the plan file basename:

    /tmp/lgtm-plan-{basename}.md
    
  2. Run lgtm with export-on-quit (use the unique export path from step 1). Check if ${CLAUDE_PLUGIN_ROOT}/node_modules exists to determine the run command:

    • If ${CLAUDE_PLUGIN_ROOT}/node_modules exists (local dev):
      bun run ${CLAUDE_PLUGIN_ROOT}/src/cli.ts $ARGUMENTS --export-on-quit /tmp/lgtm-plan-{basename}.md
      
    • If node_modules does not exist (marketplace install):
      bunx @hapticdata/lgtm $ARGUMENTS --export-on-quit /tmp/lgtm-plan-{basename}.md
      
  3. After the TUI exits, read the exported feedback file:

    Read /tmp/lgtm-plan-{basename}.md
    
  4. Present the user's feedback and incorporate it into your response.

Note: If the user has LGTM_TMUX=1 set, this will open in a tmux split. Otherwise it opens in the current terminal.

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 files

This 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.md

From the root of a test project, save the file as .skill-downloads/open-plan-in-lgtm-for-review-mmbizj90/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/open-plan-in-lgtm-for-review-mmbizj90' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/open-plan-in-lgtm-for-review-mmbizj90/download' --output '.skill-downloads/open-plan-in-lgtm-for-review-mmbizj90/SKILL.md.part' && mv '.skill-downloads/open-plan-in-lgtm-for-review-mmbizj90/SKILL.md.part' '.skill-downloads/open-plan-in-lgtm-for-review-mmbizj90/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/open-plan-in-lgtm-for-review-mmbizj90/SKILL.md' && test -s '.skill-downloads/open-plan-in-lgtm-for-review-mmbizj90/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/lgtm-plan' && cp -R '.skill-downloads/open-plan-in-lgtm-for-review-mmbizj90' '.claude/skills/lgtm-plan'

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 installation
openskills install './.skill-downloads/open-plan-in-lgtm-for-review-mmbizj90'

openskills read 'open-plan-in-lgtm-for-review-mmbizj90'

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 sync

Manual 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/open-plan-in-lgtm-for-review-mmbizj90/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.

Related skills