Not in the top 1,000 by GitHub stars

chengzhongwei/Prompt-sensei

Local-first prompt coach for Claude Code and Codex that improves prompts, observes prompting habits, and analyzes local history with explicit consent.

Claude Code Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → ea1e3810c26f

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit ea1e3810c26ff3bb115be8019739439f6ae8f41c

Version-pinned installation · Claude Code

git clone --filter=blob:none --no-checkout https://github.com/chengzhongwei/Prompt-sensei.git .hotskills/chengzhongwei-prompt-sensei && git -C .hotskills/chengzhongwei-prompt-sensei checkout --detach ea1e3810c26ff3bb115be8019739439f6ae8f41c
# Copy each selected skill directory from .hotskills/chengzhongwei-prompt-sensei into .claude/skills/<skill-name>/

109GitHub stars

0stars in 7 days

1skill in this repository

0commits in 30 days

Heat

0.3

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

prompt-sensei /

How it works

prompt-sensei

When your agent uses it

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.

What it loads into context

Frontmatter

60 tokens

Always available to the agent

SKILL.md

3,143 tokens

When the skill is activated

Reference documents

25,235 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Invocation
Stages
Dimensions
Observe
Improve
Other Modes
Help
Tone

Scripts executed separately

package.json
scripts/clear.ts
scripts/eval.ts
scripts/lib/coaching.ts
scripts/lib/host.ts
scripts/lib/paths.ts
scripts/lib/redact.ts
scripts/lib/settings.ts
scripts/lookback.ts
scripts/observe.ts
scripts/pre-compact.ts
scripts/report.ts
scripts/session-start.ts
scripts/settings.ts
scripts/setup-hooks.ts
scripts/smoke-test.ts
scripts/stop.ts
scripts/sync-codex-install.ts
scripts/update.ts

Files

.github/DISCUSSION_TEMPLATE/scoring-feedback.ymlasset1,148 bytes
.github/ISSUE_TEMPLATE/scoring-feedback.mddoc536 bytes
.gitignoreasset54 bytes
CHANGELOG.mddoc4,677 bytes
CLAUDE.mddoc8,644 bytes
LICENSEasset11,344 bytes
README-zh.mddoc10,273 bytes
README.mddoc10,035 bytes
SKILL.mdcore13,792 bytes
SKILL.mdcore13,792 bytes
assets/prompt-sensei-banner-en.jpgasset405,079 bytes
assets/prompt-sensei-banner-zh.jpgasset376,389 bytes
docs/advanced-setup-zh.mddoc6,653 bytes
docs/advanced-setup.mddoc6,645 bytes
docs/faq.mddoc5,123 bytes
docs/philosophy.mddoc7,208 bytes
docs/privacy.mddoc10,795 bytes
docs/scoring-rubric.mddoc10,904 bytes
docs/skill-flows.mddoc13,848 bytes
eval/README.mddoc1,171 bytes
eval/prompts.jsonasset12,638 bytes
examples/claude-settings.example.jsonasset1,128 bytes
examples/codex-hooks.example.jsonasset840 bytes
examples/debugging-journey.mddoc6,492 bytes
examples/prompt-gallery.mddoc6,194 bytes
package-lock.jsonasset1,519 bytes
package.jsonruns1,416 bytes
scripts/clear.tsruns2,946 bytes
scripts/eval.tsruns4,649 bytes
scripts/lib/coaching.tsruns11,708 bytes
scripts/lib/host.tsruns617 bytes
scripts/lib/paths.tsruns416 bytes
scripts/lib/redact.tsruns1,515 bytes
scripts/lib/settings.tsruns5,801 bytes
scripts/lookback.tsruns20,196 bytes
scripts/observe.tsruns7,641 bytes
scripts/pre-compact.tsruns1,671 bytes
scripts/report.tsruns15,673 bytes
scripts/session-start.tsruns3,191 bytes
scripts/settings.tsruns9,177 bytes
scripts/setup-hooks.tsruns6,978 bytes
scripts/smoke-test.tsruns11,497 bytes
scripts/stop.tsruns6,973 bytes
scripts/sync-codex-install.tsruns1,976 bytes
scripts/update.tsruns5,492 bytes
tsconfig.jsonasset358 bytes

Read SKILL.md


# 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

View the complete source on GitHub

Skills included

prompt-sensei

Repository facts

License: Apache-2.0
Created: Apr 25, 2026
Last pushed: Jul 13, 2026
Forks: 10
Open issues: 0
Project activity: Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 7, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 1 note

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
1 dangerous shell commandin 1 file: docs/privacy.md:219
18 network referencesin 4 files: package-lock.json:19 LICENSE:1 README-zh.md:7 and 1 more
No hidden or obfuscated text
No instruction overrides
19 executable scriptsin 19 files: package.json:1 scripts/clear.ts:1 scripts/eval.ts:1 and 16 more
3 references to secretsin 2 files: docs/privacy.md:183 scripts/lib/redact.ts:8
No requests to vote in Hot

Show all 41 signals by file

`LICENSE`

Network accessline 1

Apache License                            Version 2.0, January 2004                         http://www.apache.org/licenses/

Network accessline 3
```
http://www.apache.org/licenses/
```

Network accessline 195

http://www.apache.org/licenses/LICENSE-2.0

`README-zh.md`

Network accessline 7

[Quickstart](#5-分钟快速开始) · [FAQ](docs/faq.md) · [Privacy](docs/privacy.md) · [Examples](examples/prompt-gallery.md) · [Advanced setup](docs/advanced-setup-zh.md) · [Discussions](https://github.com/chengzhongwei/Prompt-sensei/discussions)

Network accessline 42

git clone https://github.com/chengzhongwei/Prompt-sensei ~/.claude/skills/prompt-sensei

Network accessline 51

git clone https://github.com/chengzhongwei/Prompt-sensei ~/.codex/skills/prompt-sensei

`README.md`

Network accessline 7

[Quickstart](#5-minute-quickstart) · [FAQ](docs/faq.md) · [Privacy](docs/privacy.md) · [Examples](examples/prompt-gallery.md) · [Advanced setup](docs/advanced-setup.md) · [Discussions](https://github.com/chengzhongwei/Prompt-sensei/discussi

Network accessline 42

git clone https://github.com/chengzhongwei/Prompt-sensei ~/.claude/skills/prompt-sensei

Network accessline 51

git clone https://github.com/chengzhongwei/Prompt-sensei ~/.codex/skills/prompt-sensei

`docs/privacy.md`

Access to secretsline 183
```
[Credential-related source omitted]
```
Access to secretsline 188
```
[Credential-related source omitted]
```
Dangerous shell operationline 219
```
rm -rf ~/.prompt-sensei/
```

`package-lock.json`

Network accessline 19

"node_modules/@types/node": {       "version": "22.19.17",       "resolved": "https://registry.npmjs.org/@types/node/-/node-22.19.17.tgz",

Network accessline 20

"version": "22.19.17",       "resolved": "https://registry.npmjs.org/@types/node/-/node-22.19.17.tgz",       "integrity": "sha512-wGdMcf+vPYM6jikpS/qhg6WiqSV/OhG+jeeHT/KlVqxYfD40iYJf9/AE1uQxVWFvU7MipKRkRv8NSHiCGgPr8Q==",

Network accessline 21

"resolved": "https://registry.npmjs.org/@types/node/-/node-22.19.17.tgz",

Network accessline 29

"node_modules/typescript": {       "version": "5.9.3",       "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.9.3.tgz",

Network accessline 30

"version": "5.9.3",       "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.9.3.tgz",       "integrity": "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw==",

Network accessline 31

"resolved": "https://registry.npmjs.org/typescript/-/typescript-5.9.3.tgz",

Network accessline 43

"node_modules/undici-types": {       "version": "6.21.0",       "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-6.21.0.tgz",

Network accessline 44

"version": "6.21.0",       "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-6.21.0.tgz",       "integrity": "sha512-iwDZqg0QAGrg9Rav5H4n0M64c3mkR59cJ6wQp+7C4nI0gsmExaedaYLNO44eT4AtBBwjbTiGPMlt2Md0T9H9JQ==",

Network accessline 45

"resolved": "https://registry.npmjs.org/undici-types/-/undici-types-6.21.0.tgz",

`package.json`

Executable scriptline 1
```
Executable file
```

`scripts/clear.ts`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/eval.ts`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/lib/coaching.ts`

Executable scriptline 1
```
Executable file
```

`scripts/lib/host.ts`

Executable scriptline 1
```
Executable file
```

`scripts/lib/paths.ts`

Executable scriptline 1
```
Executable file
```

`scripts/lib/redact.ts`

Executable scriptline 1
```
Executable file
```
Access to secretsline 8
```
[Credential-related source omitted]
```

`scripts/lib/settings.ts`

Executable scriptline 1
```
Executable file
```

`scripts/lookback.ts`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/observe.ts`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/pre-compact.ts`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/report.ts`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/session-start.ts`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/settings.ts`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/setup-hooks.ts`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/smoke-test.ts`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/stop.ts`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/sync-codex-install.ts`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/update.ts`

Executable scriptline 1
```
#!/usr/bin/env node
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 29 facts

Network access in prose of documentationREADME-zh.md:7Low confidence
Network access in code of documentationREADME-zh.md:42Low confidence
Network access in code of documentationREADME-zh.md:51Low confidence
Network access in prose of documentationREADME.md:7Low confidence
Network access in code of documentationREADME.md:42Low confidence
Network access in code of documentationREADME.md:51Low confidence
Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valuedocs/privacy.md:183Low confidence
Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valuedocs/privacy.md:188Low confidence
Dangerous shell operation in code of documentationdocs/privacy.md:219Low confidence
Executable script in code of a file that runspackage.json:1High confidence
Executable script in code of a file that runsscripts/clear.ts:1High confidence
Executable script in code of a file that runsscripts/eval.ts:1High confidence
Executable script in code of a file that runsscripts/lib/coaching.ts:1High confidence
Executable script in code of a file that runsscripts/lib/host.ts:1High confidence
Executable script in code of a file that runsscripts/lib/paths.ts:1High confidence
Executable script in code of a file that runsscripts/lib/redact.ts:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/lib/redact.ts:8Low confidence
Executable script in code of a file that runsscripts/lib/settings.ts:1High confidence
Executable script in code of a file that runsscripts/lookback.ts:1High confidence
Executable script in code of a file that runsscripts/observe.ts:1High confidence
Executable script in code of a file that runsscripts/pre-compact.ts:1High confidence
Executable script in code of a file that runsscripts/report.ts:1High confidence
Executable script in code of a file that runsscripts/session-start.ts:1High confidence
Executable script in code of a file that runsscripts/settings.ts:1High confidence
Executable script in code of a file that runsscripts/setup-hooks.ts:1High confidence
Executable script in code of a file that runsscripts/smoke-test.ts:1High confidence
Executable script in code of a file that runsscripts/stop.ts:1High confidence
Executable script in code of a file that runsscripts/sync-codex-install.ts:1High confidence
Executable script in code of a file that runsscripts/update.ts:1High confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Path CLAUDE.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

chengzhongwei/Prompt-sensei

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

prompt-sensei

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Before you install

LICENSE

README-zh.md

README.md

docs/privacy.md

package-lock.json

package.json

scripts/clear.ts

scripts/eval.ts

scripts/lib/coaching.ts

scripts/lib/host.ts

scripts/lib/paths.ts

scripts/lib/redact.ts

scripts/lib/settings.ts

scripts/lookback.ts

scripts/observe.ts

scripts/pre-compact.ts

scripts/report.ts

scripts/session-start.ts

scripts/settings.ts

scripts/setup-hooks.ts

scripts/smoke-test.ts

scripts/stop.ts

scripts/sync-codex-install.ts

scripts/update.ts

How the signals fit together

Works with

You might also use

ginuim/skill-base

alirezarezvani/claude-skills

michael-denyer/pstack-claude

zenstory-ai/drama-skills

wuji-labs/nopua

jiweiyeah/Skills-Manager

`SKILL.md`

`LICENSE`

`README-zh.md`

`README.md`

`docs/privacy.md`

`package-lock.json`

`package.json`

`scripts/clear.ts`

`scripts/eval.ts`

`scripts/lib/coaching.ts`

`scripts/lib/host.ts`

`scripts/lib/paths.ts`

`scripts/lib/redact.ts`

`scripts/lib/settings.ts`

`scripts/lookback.ts`

`scripts/observe.ts`

`scripts/pre-compact.ts`

`scripts/report.ts`

`scripts/session-start.ts`

`scripts/settings.ts`

`scripts/setup-hooks.ts`

`scripts/smoke-test.ts`

`scripts/stop.ts`

`scripts/sync-codex-install.ts`

`scripts/update.ts`