Autogap
Diagnoses any project's top 3 gaps and implements the fixes you pick
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 17, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 70ee0ce
Pointed it at a half-built habit-tracker CLI with a launch deadline buried in a notes file: the skill run inferred the real objective (a newsletter launch by the 15th), spotted that the launch post and the unimplemented streak feature block each other, and produced a ranked 3-gap, 3-step plan with an execution menu — output that passed the repo's own bundled structural validator. The no-skill baseline found the same raw facts but delivered a flat 7-item list with no objective inference, no evidence-consequence framing, and no decision point. The trigger description is broad, so it may occasionally fire on adjacent 'analyze my project' requests that want a plain code review.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 4/5
- Output vs. baseline 7/10
- Docs & honesty 4/5
What Autogap does
Project analyst that deep-inspects any project type — code, docs, research, strategy, creative — infers the top-value objective from file signals, and reports the 3 biggest gaps blocking it plus 3 macro-steps with complexity/value/confidence ratings. Ends with a numbered menu; whatever you pick, it plans and implements autonomously. Triggers on /autogap, 'what's missing to reach the goal', and 'strategic diagnosis' requests.
How to install Autogap
git clone https://github.com/micpet7514088/autogap
mkdir -p ~/.claude/skills
cp -r autogap/skills/autogap ~/.claude/skills/autogap
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Autogap
-
/autogapDiagnoses any project's top 3 gaps and implements the fixes you pick
It also activates on plain-language prompts like these:
-
What's missing before I can launch this project on the 15th? -
Give me a strategic diagnosis of my half-built habit tracker -
Look at this repo and tell me the top 3 gaps blocking release
Frequently asked questions
- Is the Autogap skill free?
- Yes. The skill itself is free from micpet7514088/autogap. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Autogap work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Tested · Works. Pointed it at a half-built habit-tracker CLI with a launch deadline buried in a notes file: the skill run inferred the real objective (a newsletter launch by the 15th), spotted that the launch post and the unimplemented streak feature block each other, and produced a ranked 3-gap, 3-step plan with an execution menu — output that passed the repo's own bundled structural validator. The no-skill baseline found the same raw facts but delivered a flat 7-item list with no objective inference, no evidence-consequence framing, and no decision point. The trigger description is broad, so it may occasionally fire on adjacent 'analyze my project' requests that want a plain code review.
- What is the Autogap SkillProof Score?
- 8.0/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 4/5.
- How do I install Autogap?
- 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 Autogap 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.