agentleFS
Sign inStart free
tonmoy007tonmoy007/forge-plugins/skills/forge-preflight/SKILL.md

preflight

Skill2 starsChanged 5 months agoMITView on GitHub

Detect missing required CLIs (docker, docker compose, gh) for the

47 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use adr, ship and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • asterkinSkill

    adr

    Create Architecture Decision Records (ADRs) following project standards. Guides template usage, process, and best practices for documenting architecturally significant decisions.

    Also in 3 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 5 projects that use this

  • MicrosoftSkill

    report

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.

    Also in 3 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 4 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 3 projects that use this

  • GitHubSkill

    refactor

    Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If a tool has no install_cmd for the current OS (an unsupported platform), say so and point at the tool's own documentation instead of …

    line 49
  2. Very specific:

    After any installs, re-run tool_preflight.py check --cwd .

    line 54

“Common” is measured: kept by at least 6 in 10 of the 42 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

forge-preflight

Surfaces which required tools are missing for this project and, only after the user confirms, runs the exact install command for one of them. This is the only surface in Forge that runs an installer — hooks/session-start.py and scripts/doctor.py only ever detect and report.

When to Use

  • User runs /forge:preflight
  • session-start's tool advisory line points here (⚠ Required tool ... run /forge:preflight)
  • /forge:doctor reports a missing required tool
  • User asks whether a needed CLI is installed, or hits a wall at deploy/release because a tool turned out to be missing

Detect

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/tool_preflight.py check --cwd .

This prints JSON — one entry per registry tool (references/tool-registry.md), each with present, version, required, reason, and install_cmd fields. Present the tools where required is true and present is false. If none, tell the user everything required is already installed and stop here.

Confirm, Then Install — Never Auto-Run

For each missing required tool, show its exact install command (install_cmd from the JSON above — this is per-OS, resolved by tool_preflight.py from the registry, never invented) and ask the user to confirm before running anything. Only once the user explicitly confirms a specific tool, run that tool's exact command via Bash. If the user declines a tool, or does not respond affirmatively, do not run its install command — move on to the next tool or stop. Never run an install command the user has not seen and approved, and never install a tool the user has declined.

If a tool has no install_cmd for the current OS (an unsupported platform), say so and point at the tool's own documentation instead of guessing a command.

Report

After any installs, re-run tool_preflight.py check --cwd . and confirm the tool now shows present: true. Summarize what was installed, what was declined, and what remains missing.

Orchestration Rules

This skill SHALL detect via tool_preflight.py check first; show every missing required tool's exact install command before running it; run an install command only after the user's explicit confirmation for that specific tool; and re-check after installing.

This skill SHALL NOT run any install command without prior confirmation; install a tool the user declined; invent an install command not sourced from the registry; or treat a missing optional (non-required) tool as blocking anything.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free