Flight Check
Pre-send slide-deck review that catches AI-tell language, fabricated stats, and topic-label titles.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 14, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · dbb771a
Fed it an 8-slide deck seeded with a real numeric contradiction ($4B vs $1,200,000 'Q2 comparison'), a [TBD] placeholder, and boilerplate AI phrasing; the skill run caught the $4B/$1.2M contradiction by name with slide numbers and flagged it as the top must-fix, while the baseline generic review only vaguely said 'formatting is inconsistent in a couple places' and never surfaced the actual numeric conflict.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 9/10
- Docs & honesty 5/5
What Flight Check does
Runs a six-part diagnostic pass (AI-authorship tells, source/citation check, action-title check, specificity check, structural check, polish check) on a near-finished slide deck and files a severity-graded report with exact slide numbers and quotes. Triggers when a user shares a .pptx/PDF/pasted deck and asks for a final review, readiness check, or AI-tell check; explicitly does not trigger for early drafting or redesign requests.
How to install Flight Check
git clone https://github.com/analystacademy/flight-check
cd flight-check
mkdir -p ~/.claude/skills
cp -r . ~/.claude/skills/flight-check
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Flight Check
-
/flight-checkPre-send slide-deck review that catches AI-tell language, fabricated stats, and topic-label titles.
It also activates on plain-language prompts like these:
-
Give this slide deck a final read before I send it to the board -
Check my pitch deck for fabricated stats and vague AI-sounding titles -
Is this deck ready to send, or are there red flags I'm missing?
Frequently asked questions
- Is the Flight Check skill free?
- Yes. The skill itself is free from analystacademy/flight-check. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Flight Check work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Fed it an 8-slide deck seeded with a real numeric contradiction ($4B vs $1,200,000 'Q2 comparison'), a [TBD] placeholder, and boilerplate AI phrasing; the skill run caught the $4B/$1.2M contradiction by name with slide numbers and flagged it as the top must-fix, while the baseline generic review only vaguely said 'formatting is inconsistent in a couple places' and never surfaced the actual numeric conflict.
- What is the Flight Check SkillProof Score?
- 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
- How do I install Flight Check?
- 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 Flight Check 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.