Project Pruning

VerifiedCaution

Cleans up temporary files, stale tasks, and reorganizes the ai/ directory. Helpful when your project feels cluttered, ensuring a clear structure and removing unnecessary artifacts.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude CodeCursorCodex
#cleanup#organization#project-maintenance#file-management#task-management

Recommended for

Automated summary

Cleans up temp files, stale tasks, and reorganizes the ai/ directory of a project.

Strengths

  • Automates removal of unnecessary files and relocation of misplaced files.
  • Reorganizes ai/ documentation into a clear hierarchical structure.
  • Manages tasks via the 'tk' tool (marking done, deleting stale, consolidating duplicates).
  • Produces a clean Git commit with a summary of changes.

Limitations

  • Requires the user to understand each file's purpose to avoid incorrect deletions.
  • Depends on the 'tk' tool for task management, which may not be present in all projects.
  • The reorganization phase of the ai/ directory can be slow if many files are involved.
When to use it

When the project feels cluttered with scattered files and stale tasks, to restore a clean structure.

When not to use it

If the project is already well-organized and you don't want to risk losing potentially important files.

Security analysis

Caution
Quality score85/100

The skill leverages Bash for file cleanup operations. While not inherently malicious, it has the potential to delete important files if the user misjudges their purpose. No network or obfuscation concerns.

Findings
  • •Uses Bash to delete and move files, which could lead to accidental data loss if misapplied.
How this analysis is made

Examples

General project cleanup
Run the prune skill to clean up temp files, stale tasks, and organize the ai/ directory.
Clean root directory
Use prune to remove unnecessary files from the root directory and move misplaced ones to appropriate folders.
Organize AI documentation
Apply the prune skill to reorganize the ai/ folder: consolidate duplicate topics and split overly broad files.

name: prune description: Clean up temp files, stale tasks, and organize ai/ directory. allowed-tools: Read, Write, Edit, Glob, Grep, Bash

Prune

Clean up project cruft. Run when things feel cluttered.

1. Survey

ls -la
ls -la ai/ ai/**/* 2>/dev/null
tk ls
git status --short

2. Clean

Files: For each file in root and other unexpected places—does it serve an ongoing purpose?

  • No purpose → delete it
  • Has purpose, wrong location → move to proper place (tests/, scripts/, etc.)
  • Has purpose, right location → keep

Examples:

  • test.py in root, throwaway → delete
  • test.py in root, useful test → move to tests/
  • debug.sh worth keeping → move to scripts/
  • benchmark.py with structure → keep (ongoing tooling)

The difference is purpose, not name. Ask when uncertain.

Don't touch: .git/, config files, source code

Tasks: Mark completed done, delete stale ones, consolidate duplicates.

3. Organize ai/

Goal: hierarchical organization where agents can find any topic easily.

  • Overview docs at top level for high-level context
  • Detailed docs split out by specific topic
  • One doc per topic - no scattered duplicates

Read each file to understand its content before acting.

Root files:

  • STATUS.md - prune aggressively (resolved blockers, completed work, outdated state)
  • DESIGN.md - update if stale (remove descriptions of deleted code)
  • DECISIONS.md - keep all entries (it's a log)
  • SPRINTS.md - update sprint status

Subdirs (research/, design/, sprints/, etc.):

  • Consolidate scattered content on same topic into one file
  • Split multi-topic files into focused single-topic docs
  • Leave alone if already well-organized

Preserve all important content. Delete old files only after content is safely moved. If already well-organized, say so and move on.

4. Finish

git add -A
git diff --cached --stat  # review what changed
git commit -m "Prune: clean up and organize"

Report what was removed, reorganized, or left alone.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/project-pruning-mm8o51lw/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/project-pruning-mm8o51lw' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/project-pruning-mm8o51lw/download' --output '.skill-downloads/project-pruning-mm8o51lw/SKILL.md.part' && mv '.skill-downloads/project-pruning-mm8o51lw/SKILL.md.part' '.skill-downloads/project-pruning-mm8o51lw/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Write, Edit, Glob, Grep, Bash

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/project-pruning-mm8o51lw/SKILL.md' && test -s '.skill-downloads/project-pruning-mm8o51lw/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/prune' && cp -R '.skill-downloads/project-pruning-mm8o51lw' '.claude/skills/prune'

Cursor
test -f '.skill-downloads/project-pruning-mm8o51lw/SKILL.md' && test -s '.skill-downloads/project-pruning-mm8o51lw/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/prune' && cp -R '.skill-downloads/project-pruning-mm8o51lw' '.cursor/skills/prune'

Codex
test -f '.skill-downloads/project-pruning-mm8o51lw/SKILL.md' && test -s '.skill-downloads/project-pruning-mm8o51lw/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/prune' && cp -R '.skill-downloads/project-pruning-mm8o51lw' '.agents/skills/prune'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/project-pruning-mm8o51lw'

openskills read 'project-pruning-mm8o51lw'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/project-pruning-mm8o51lw/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills