Preflight
Eleven open-source, MIT-licensed skills for AI coding agents — /preflight, /audit, /ship, /remember and more. Plain-Markdown agent guardrails for Claude Code, Codex, Cursor & Hermes. Free layer of SlashStack.
npx -y skills add mverab/slashstack-skills --skill preflightAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 18 days oldThe repository was created 18 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use before editing code to inspect project state and constraints.
SKILL.md
2.1 KB, as published. Nobody here has run it
Preflight
Purpose
Inspect repo state before coding, in beginner-friendly language.
When to Use
Use before editing code to inspect project state and constraints.
Workflow
- Respond in the user's language. If the user writes Spanish, answer in Spanish.
- Explain what just happened: state that SlashStack added local agent guidance files and did not change app code.
- Inspect git status: current branch, uncommitted changes, recent commits, and dirty working tree.
- Inspect installed SlashStack skills: list the skills folder found, count the
SKILL.mdfiles, and name the installed skills. - Discover constraints: identify the test command, build command, lint command, and project conventions from
.agents/memory/project.mdor project files. - Flag risks with severity:
- High: wrong branch, uncommitted changes that will conflict, failing tests on main.
- Medium: missing tests for the target area, unknown build/lint commands.
- Low: stale references in
.agents/references/, unused dependencies, thin project memory.
- Modo Aprendiz: for EACH risk item, include three sub-fields in beginner-friendly Spanish:
- Qué significa: what the risk means in plain language.
- Por qué importa: why it matters for the project.
- Qué hacer ahora: one concrete action to take now.
- Avoid jargon. Explain risks in beginner-friendly language without hiding exact commands or file paths.
- Do not edit files, run fixes, deploy, or change configuration.
Output
Use exactly these sections:
- What just happened: one short explanation of what SlashStack installed and what it did not change
- SlashStack installed: skills folder, number of skills, installed skill names
- Project state: branch, commits, uncommitted changes
- Commands detected: test, build, lint
- Risks: High / Medium / Low items with plain-language impact and recommended action; each item includes Qué significa, Por qué importa, and Qué hacer ahora
- What to do now: one concrete safest next step
- Exact next prompt: one copy-paste prompt the user can send next