Prompt Sensei
Scores your prompts to coding agents by stage and coaches one habit at a time
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 17, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · a4beabc
Scored nine prompts from the repo's own 24-case calibration set twice — once cold, once following the skill body — and checked both against the fixtures' expected score bands and tip labels. Cold, I landed in the expected band 5 of 9 times and walked straight into two traps the fixtures flag explicitly: I told "fix this test" and "refactor the whole app" to specify an output format, which the fixture marks as the wrong advice for a debugging prompt. I also scored "run the tests" at roughly 15/100 as vague, where the skill's Action stage correctly reads it as a clear follow-through directive worth 90+. Following the skill body: 9 of 9 in band, zero traps, because the tipKind priority table forces expected/actual and scope ahead of response polish. Caveat worth stating plainly — the fixtures ship with the skill, so the band-matching is partly a self-consistency check; the non-circular wins are the output-format trap and the systematic under-scoring of short prompts. Storage claims check out: zero network calls in the compiled scripts, a real redactor, and every consent flag defaulting to not-granted on a fresh install.
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 7/10
- Docs & honesty 5/5
What Prompt Sensei does
A local-first prompt coach for Claude Code and Codex that classifies each prompt by stage (exploration, diagnosis, execution, verification, workflow, action), scores it across seven dimensions, and returns one concrete habit to fix. Triggers on "improve this prompt", "/prompt-sensei observe", or "look back at my prompt history". Stores only hashes and redacted previews under ~/.prompt-sensei/ with no network calls.
How to install Prompt Sensei
git clone https://github.com/chengzhongwei/Prompt-sensei ~/.claude/skills/prompt-sensei
(cd ~/.claude/skills/prompt-sensei && npm install && npm run build)
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Prompt Sensei
-
/prompt-senseiScores your prompts to coding agents by stage and coaches one habit at a time
It also activates on plain-language prompts like these:
-
Score my last few prompts to you and tell me what habit to fix first -
Look back at my prompt history and coach me on writing better ones -
Was telling you to 'fix this test' too vague, or was that a fine prompt
Frequently asked questions
- Is the Prompt Sensei skill free?
- Yes. The skill itself is free from chengzhongwei/Prompt-sensei. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Prompt Sensei work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Tested · Works. Scored nine prompts from the repo's own 24-case calibration set twice — once cold, once following the skill body — and checked both against the fixtures' expected score bands and tip labels. Cold, I landed in the expected band 5 of 9 times and walked straight into two traps the fixtures flag explicitly: I told "fix this test" and "refactor the whole app" to specify an output format, which the fixture marks as the wrong advice for a debugging prompt. I also scored "run the tests" at roughly 15/100 as vague, where the skill's Action stage correctly reads it as a clear follow-through directive worth 90+. Following the skill body: 9 of 9 in band, zero traps, because the tipKind priority table forces expected/actual and scope ahead of response polish. Caveat worth stating plainly — the fixtures ship with the skill, so the band-matching is partly a self-consistency check; the non-circular wins are the output-format trap and the systematic under-scoring of short prompts. Storage claims check out: zero network calls in the compiled scripts, a real redactor, and every consent flag defaulting to not-granted on a fresh install.
- What is the Prompt Sensei SkillProof Score?
- 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
- How do I install Prompt Sensei?
- 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 Prompt Sensei 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.