Agent skill

Pneuma Project Tidy

Tidy a Pneuma project's session titles and descriptions. An agent skill from pandazki/pneuma-skills.

MITAuto-check passed

Install Pneuma Project Tidy

skills CLI

$ npx skills add pandazki/pneuma-skills --skill pneuma-project-tidy -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install pandazki/pneuma-skills pneuma-project-tidy --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/pandazki/pneuma-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/modes/project-tidy/skill .claude/skills/pneuma-project-tidy && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "pneuma-project-tidy" agent skill from https://github.com/pandazki/pneuma-skills/tree/main/modes/project-tidy/skill into .claude/skills/pneuma-project-tidy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pneuma-project-tidy", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/pandazki/pneuma-skills/tree/main/modes/project-tidy/skill

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add pandazki/pneuma-skills --skill pneuma-project-tidy -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install pandazki/pneuma-skills pneuma-project-tidy --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pandazki/pneuma-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/modes/project-tidy/skill .agents/skills/pneuma-project-tidy && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "pneuma-project-tidy" agent skill from https://github.com/pandazki/pneuma-skills/tree/main/modes/project-tidy/skill into .agents/skills/pneuma-project-tidy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pneuma-project-tidy", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add pandazki/pneuma-skills --skill pneuma-project-tidy -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install pandazki/pneuma-skills pneuma-project-tidy --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pandazki/pneuma-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/modes/project-tidy/skill .cursor/skills/pneuma-project-tidy && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "pneuma-project-tidy" agent skill from https://github.com/pandazki/pneuma-skills/tree/main/modes/project-tidy/skill into .cursor/skills/pneuma-project-tidy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pneuma-project-tidy", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/pandazki/pneuma-skills.git --path modes/project-tidy/skill

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add pandazki/pneuma-skills --skill pneuma-project-tidy -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install pandazki/pneuma-skills pneuma-project-tidy --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pandazki/pneuma-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/modes/project-tidy/skill .gemini/skills/pneuma-project-tidy && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "pneuma-project-tidy" agent skill from https://github.com/pandazki/pneuma-skills/tree/main/modes/project-tidy/skill into .gemini/skills/pneuma-project-tidy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pneuma-project-tidy", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install pandazki/pneuma-skills pneuma-project-tidy

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add pandazki/pneuma-skills --skill pneuma-project-tidy -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/pandazki/pneuma-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/modes/project-tidy/skill .github/skills/pneuma-project-tidy && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "pneuma-project-tidy" agent skill from https://github.com/pandazki/pneuma-skills/tree/main/modes/project-tidy/skill into .github/skills/pneuma-project-tidy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pneuma-project-tidy", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add pandazki/pneuma-skills --skill pneuma-project-tidy -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install pandazki/pneuma-skills pneuma-project-tidy --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pandazki/pneuma-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/modes/project-tidy/skill .opencode/skills/pneuma-project-tidy && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "pneuma-project-tidy" agent skill from https://github.com/pandazki/pneuma-skills/tree/main/modes/project-tidy/skill into .opencode/skills/pneuma-project-tidy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pneuma-project-tidy", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: pneuma-project-tidy
GitHub stars: 161
Token cost: ~1.5k tokens
SKILL.md length: 774 words
Files: 2 (incl. scripts)
Skills in repo: 30
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Tidy a Pneuma project's session titles and descriptions. An agent skill from pandazki/pneuma-skills.

Works in 4 steps: Enumerate → Write the initial report → Refine each session → …
SKILL.md covers The loop and Boundaries
Runs TypeScript scripts from its folder; calls bun

What it does

Pneuma Project Tidy is an agent skill from pandazki/pneuma-skills. Tidy a Pneuma project's session titles and descriptions. Use in the Project Tidy workspace to replace placeholder metadata with topic-specific names and report progress.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/list-project-sessions.ts`).

The repository describes itself as: Co-creation infrastructure for humans and code agents — visual environment, skills, continuous learning, and distribution. The licence is MIT.

Example prompts

“/pneuma-project-tidy”

Requirements

Node.js

Workflow steps

4 steps, taken from the step headings in SKILL.md.

Enumerate
Write the initial report
Refine each session
Finish

What it can do on your machine

Read from SKILL.md and the folder at commit 0023d3c. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (TypeScript), which the agent can run.
Shell commands in SKILL.md call:
- bun
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pneuma Project Tidy loads about 1.5k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 774 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~47
When it runs · the whole SKILL.md, loaded when a task matches: ~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from pandazki/pneuma-skills at commit 0023d3c, republished under its MIT licence (© pandazki). 774 words, ~1,529 tokens.

Download SKILL.mdSave it as .claude/skills/pneuma-project-tidy/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: pneuma-project-tidy
description: Tidy a Pneuma project's session titles and descriptions. Use in the Project Tidy workspace to replace placeholder metadata with topic-specific names and report progress.

Project Tidy Agent

In script examples, <SKILL_DIR> means the actual directory containing this loaded SKILL.md. Substitute its full path and keep shell paths quoted. The runtime installs it under .claude/skills for Claude Code, .agents/skills for Codex, or .kimi-code/skills for Kimi; use the path given in your instructions.

You are the Project Tidy Agent. Your one job: sweep this project's Recent Sessions list and rewrite every session that's still on a placeholder title ("WebCraft session", "文档会话", …) so each row says what it's actually about.

You don't create anything. You re-label sessions that already exist, using the same pneuma session refine mechanism the pneuma-session skill runs inside a single session — but here you run it across the whole project in one pass.

The user opened this from the project's AI menu and is watching a live progress report (the viewer). Your output is two things:

The actual refines (applied directly to each session — titles are cheap and reversible).
A running report.json so the viewer can show progress.

The loop

brief (1 sentence)  →  enumerate  →  write initial report  →  refine each  →  done

Work autonomously start-to-finish. Do not stop to ask the user which sessions to do or to approve titles — they came here for a finished, tidied list, not a conversation. If they want to steer, they'll interrupt.

1. Enumerate

Run the bundled script — never hand-grep the session dirs:

bash

bun "<SKILL_DIR>/scripts/list-project-sessions.ts"

It prints one JSON object: { projectRoot, total, needsTidy, sessions: [...] }. Each session carries:

Field	Meaning
`sessionId`	the id you pass to `refine --target-session`
`mode`	which mode the session ran in
`displayName` / `description`	current stored title / summary (`null` = still on the default)
`sessionName`	the user's manual rename — if set, leave it alone
`needsTidy`	`true` when there's no manual name and no refined title
`skipReason`	why it was skipped (only when `needsTidy: false`)
`digest`	the first several real user messages (synthetic `<pneuma:…>` tags already dropped)
`messageCount`	how many real user messages the session has

Only refine sessions where needsTidy is true. Skip the rest — a stored displayName means it was already tidied, and a sessionName is the user's explicit choice that always wins.

2. Write the initial report

Create <sessionDir>/tidy/report.json listing every needsTidy session as pending. This is what the viewer renders. Shape:

json

{
  "schemaVersion": 1,
  "total": 7,
  "sessions": [
    {
      "sessionId": "abc123",
      "mode": "webcraft",
      "status": "pending",
      "before": { "displayName": null }
    }
  ]
}

total is the count of sessions you intend to refine (the needsTidy set). You may also include skipped sessions with "status": "skipped" and a short "skipReason" so the report is a complete account — but skipped rows don't count toward total.

Show full SKILL.md (377 more words)Show less

3. Refine each session

For each needsTidy session, work out a title + one-line summary from its digest (read the full <projectRoot>/.pneuma/sessions/<id>/history.json only if the digest is too thin to title confidently), then apply it:

bash

$PNEUMA_CLI session refine --target-session <sessionId> --json '{"displayName": "<≤40 chars>", "description": "<≤280 chars>"}'

Always call through $PNEUMA_CLI (not the literal pneuma) — it is a single executable path and behaves the same in any shell, quoted or unquoted.
--target-session <sessionId> is what makes this refine land on a sibling session instead of this temporary tidy session. Without it you'd re-title the tidy session itself — never do that.
Before moving to the next session, update that session's entry in report.json: set status to "done", fill after.displayName / after.description, and carry before.displayName as the old value (usually null / the default). Rewrite the whole file each time — the viewer re-reads it.

Set a row's status to "running" right before you refine it if you want the live spinner; it's optional but reads nicely for longer sweeps.

What goes in each field

Same philosophy as the pneuma-session skill — describe the session, not the work.

displayName (≤40 chars): a scannable label for what the session is about. No mode prefix (the row already shows a mode chip). No trailing period. Headline capitalization.
description (≤280 chars): one sentence on the topic / user-facing concern.
Match the user's register. If the session's digest is in Chinese, title it in Chinese. English digest → English. Read the room per session — different rows can be different languages.

Don't	Do
"Edited hero.html 7 times"	"记忆问题业务调研"
"Implemented three React hooks"	"Loading-state card exploration"
"Created pricing.html"	"Pricing page draft for the launch site"

4. Finish

When every needsTidy session is done, give a one-line summary in chat (e.g. "整理完成：7 个会话已重新命名，2 个已手动命名的跳过"). Don't re-run, don't ask for more. The user's Recent Sessions list now reads cleanly.

Boundaries

Refine only. Don't open, relaunch, or modify the contents of sibling sessions — you touch their session.json title/summary via the CLI and nothing else.
Never refine yourself. Every refine call must carry --target-session <sessionId> for a sibling. A call without it hits this tidy session.
Respect manual names. sessionName set → skip, always.
Don't fabricate. If a session is too sparse (e.g. messageCount 0) to title meaningfully, skip it with skipReason: "内容太少" rather than inventing a topic.
One pass. Sweep once and stop. This isn't an iterative dashboard.

Files

SKILL.md and 1 other file (scripts) in modes/project-tidy/skill of pandazki/pneuma-skills.

SKILL.md
scripts/list-project-sessions.ts

Open the folder on GitHubat commit 0023d3c

Compare with similar skills

Pneuma Project Tidy next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pneuma Project Tidy compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Pneuma Project Tidy this skillpandazki/pneuma-skills	161	—	~1.5k	Automated safety check: Pass	MIT	2 days ago
Duplicate Descriptionthedaviddias/Front-End-Checklist	74k	—	~695	Automated safety check: Pass	MIT	5 days ago
Meta Descriptionthedaviddias/Front-End-Checklist	74k	—	~513	Automated safety check: Pass	MIT	5 days ago
Meta Titlethedaviddias/Front-End-Checklist	74k	—	~494	Automated safety check: Pass	MIT	5 days ago
Audio Descriptionsthedaviddias/Front-End-Checklist	74k	—	~549	Automated safety check: Pass	MIT	5 days ago
Frame Titlethedaviddias/Front-End-Checklist	74k	—	~438	Automated safety check: Pass	MIT	5 days ago

Similar skills

Duplicate Description
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing a site's meta tag uniqueness, generating page-specific meta descriptions, or reviewing CMS templates that inject the same description globally.
74k GitHub stars~695 tokensUpdated 5 days ago
Marketing & SEOAuto-check passed
Meta Description
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing page metadata or generating descriptions for new pages.
74k GitHub stars~513 tokensUpdated 5 days ago
Marketing & SEOAuto-check passed
Meta Title
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing page metadata or generating SEO-optimized titles.
74k GitHub stars~494 tokensUpdated 5 days ago
Frontend & DesignAuto-check passed
Audio Descriptions
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Provide audio descriptions for video.
74k GitHub stars~549 tokensUpdated 5 days ago
Frontend & DesignAuto-check passed
Frame Title
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Provide titles for iframes and frames.
74k GitHub stars~438 tokensUpdated 5 days ago
Frontend & DesignAuto-check passed
Titles And Description
JimLiu/baocut
用户要为准备发布的视频起标题、要几个标题候选、再来一批或照某个再来几个，或要写视频简介（视频页标题下的说明文字、章节列表、标签）时用。写给发布视频的人：吸引人，并且每句都由视频兑现。需要视频的转写。不用于给文章起标题等与视频无关的写作。
646 GitHub stars~428 tokensUpdated today
Media & CreativeAuto-check passed

Questions about Pneuma Project Tidy

What does Pneuma Project Tidy do?

Tidy a Pneuma project's session titles and descriptions. An agent skill from pandazki/pneuma-skills. Pneuma Project Tidy is an agent skill from pandazki/pneuma-skills. Tidy a Pneuma project's session titles and descriptions.

How do I install Pneuma Project Tidy in Claude Code?

Run `npx skills add pandazki/pneuma-skills --skill pneuma-project-tidy -a claude-code`. Or copy the skill folder (modes/project-tidy/skill in pandazki/pneuma-skills) into .claude/skills/pneuma-project-tidy in your project. Claude Code loads it when a task matches its description.

How do I install Pneuma Project Tidy in Codex?

Run `npx skills add pandazki/pneuma-skills --skill pneuma-project-tidy -a codex`. Or copy the skill folder (modes/project-tidy/skill in pandazki/pneuma-skills) into .agents/skills/pneuma-project-tidy in your project. Codex loads it when a task matches its description.

Can I use Pneuma Project Tidy in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pandazki/pneuma-skills --skill pneuma-project-tidy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pneuma-project-tidy, .gemini/skills/pneuma-project-tidy, .github/skills/pneuma-project-tidy and .opencode/skills/pneuma-project-tidy in your project.

What does Pneuma Project Tidy need to run?

Going by SKILL.md and its folder, Pneuma Project Tidy needs TypeScript for the scripts in its folder and the command-line tools its instructions call (bun). Our summary lists: Node.js.

Does Pneuma Project Tidy access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Pneuma Project Tidy safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Pneuma Project Tidy use?

Pneuma Project Tidy is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pneuma Project Tidy use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pneuma Project Tidy?

Skills that share tags, products or a category with Pneuma Project Tidy: Duplicate Description (thedaviddias/Front-End-Checklist, 74k stars), Meta Description (thedaviddias/Front-End-Checklist, 74k stars), Meta Title (thedaviddias/Front-End-Checklist, 74k stars) and Audio Descriptions (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pneuma Project Tidy?

pandazki (a GitHub user) maintains it in pandazki/pneuma-skills, which has 161 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 9, 2026.

Source: pandazki/pneuma-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Pneuma Project Tidy

Facts

At a glance

What it does

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Project Tidy Agent

The loop

1. Enumerate

2. Write the initial report

3. Refine each session

What goes in each field

4. Finish

Boundaries

Files

Compare with similar skills

Similar skills

More from pandazki/pneuma-skills

Questions about Pneuma Project Tidy