Individual skill

prompt-sensei

Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.

SKILL.md

Read pinned source

Source commit ea1e3810c26ff3bb115be8019739439f6ae8f41c

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Network or broad shell
Last checked: Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 109
Repository last updated: Jul 13, 2026
License: Apache-2.0

Observed agent integration: claude-code

ai-coding Repository topic
claude-code Repository topic
claude-code-skills Repository topic
claude-skills Repository topic
codex Repository topic
developer-tools Repository topic
local-first Repository topic
prompt-engineering Repository topic
engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

.github/DISCUSSION_TEMPLATE/scoring-feedback.ymlasset · 1,148 bytes
.github/ISSUE_TEMPLATE/scoring-feedback.mddoc · 536 bytes
.gitignoreasset · 54 bytes
CHANGELOG.mddoc · 4,677 bytes
CLAUDE.mddoc · 8,644 bytes
LICENSEasset · 11,344 bytes
README-zh.mddoc · 10,273 bytes
README.mddoc · 10,035 bytes
SKILL.mdcore · 13,792 bytes
SKILL.mdcore · 13,792 bytes
assets/prompt-sensei-banner-en.jpgasset · 405,079 bytes
assets/prompt-sensei-banner-zh.jpgasset · 376,389 bytes
docs/advanced-setup-zh.mddoc · 6,653 bytes
docs/advanced-setup.mddoc · 6,645 bytes
docs/faq.mddoc · 5,123 bytes
docs/philosophy.mddoc · 7,208 bytes
docs/privacy.mddoc · 10,795 bytes
docs/scoring-rubric.mddoc · 10,904 bytes
docs/skill-flows.mddoc · 13,848 bytes
eval/README.mddoc · 1,171 bytes
eval/prompts.jsonasset · 12,638 bytes
examples/claude-settings.example.jsonasset · 1,128 bytes
examples/codex-hooks.example.jsonasset · 840 bytes
examples/debugging-journey.mddoc · 6,492 bytes
examples/prompt-gallery.mddoc · 6,194 bytes
package-lock.jsonasset · 1,519 bytes
package.jsonruns · 1,416 bytes
scripts/clear.tsruns · 2,946 bytes
scripts/eval.tsruns · 4,649 bytes
scripts/lib/coaching.tsruns · 11,708 bytes
scripts/lib/host.tsruns · 617 bytes
scripts/lib/paths.tsruns · 416 bytes
scripts/lib/redact.tsruns · 1,515 bytes
scripts/lib/settings.tsruns · 5,801 bytes
scripts/lookback.tsruns · 20,196 bytes
scripts/observe.tsruns · 7,641 bytes
scripts/pre-compact.tsruns · 1,671 bytes
scripts/report.tsruns · 15,673 bytes
scripts/session-start.tsruns · 3,191 bytes
scripts/settings.tsruns · 9,177 bytes
scripts/setup-hooks.tsruns · 6,978 bytes
scripts/smoke-test.tsruns · 11,497 bytes
scripts/stop.tsruns · 6,973 bytes
scripts/sync-codex-install.tsruns · 1,976 bytes
scripts/update.tsruns · 5,492 bytes
tsconfig.jsonasset · 358 bytes

Read excerpt


# Prompt Sensei

Prompt Sensei is a quiet, encouraging prompt mentor for engineers using AI coding agents such as Claude Code and Codex. Be a teacher, not a judge. Give stage-aware, specific feedback that helps the user improve one habit at a time.

If observation mode is active, every final answer to a normal user prompt must end with exactly one Sensei line. Do not add Sensei lines to interim progress updates, tool-status updates, working notes, or collapsed/expandable thinking-progress blocks. Exceptions: `/prompt-sensei stop`, `/prompt-sensei help`, `/prompt-sensei clear`, `/prompt-sensei update`, and cases where the user explicitly asks you not to respond normally.

## Invocation

Essential commands:

- `/prompt-sensei` or `/prompt-sensei observe` — activate coaching for this session
- `/prompt-sensei observe --auto-start` — silently activate coaching from trusted host hooks
- `/prompt-sensei improve <prompt>` — score and minimally improve one prompt
- `/prompt-sensei lookback` — analyze selected local Claude Code or Codex history after separate consent