Skip to content
Development
Skill

/workspace-prune-working

Clean up .aiwg/working/ by promoting, archiving, or deleting temporary files

From plugin
aiwg
229200 skills199 agents26 commands

Claude Code

$ npx -y skills add jmagly/aiwg --skill workspace-prune-working --agent claude-code

SKILL.md

workspace-prune-working.SKILL.md
namespace: aiwg
name: workspace-prune-working
platforms: [all]
description: Clean up .aiwg/working/ by promoting, archiving, or deleting temporary files

Workspace Prune Working

Clean up the `.aiwg/working/` directory by intelligently handling temporary files. Promotes valuable content to the main documentation structure, archives content worth preserving, and deletes truly temporary files.

Parameters

| Flag | Description | |------|-------------| | `project-directory` | Project root (default: `.`) | | `--promote-all` | Promote all promotable files without prompting | | `--archive-all` | Archive all archivable files without prompting | | `--delete-all` | Delete all deletable files without prompting | | `--dry-run` | Preview changes without modifying files | | `--interactive` | Prompt for each file decision | | `--force` | Skip confirmation prompts |

Purpose of .aiwg/working/

The `.aiwg/working/` directory is designated for:

  • Multi-agent work-in-progress drafts
  • Temporary scratch files during orchestration
  • Review feedback before synthesis
  • Iterative document versions

It is **NOT** a permanent storage location. Files here should eventually be:

  • **Promoted** → Moved to appropriate `.aiwg/` subdirectory as finalized docs
  • **Archived** → Preserved in `.aiwg/archive/` for historical reference
  • **Deleted** → Removed when no longer useful

Execution Steps

Step 1: Scan Working Directory

Inventory all files in `.aiwg/working/`:

# List all files with metadata
find .aiwg/working -type f -exec stat -c '%Y %s %n' {} \; | sort -rn

# Count by subdirectory
find .aiwg/working -mindepth 1 -maxdepth 1 -type d | while read dir; do
  echo "$(basename "$dir"): $(find "$dir" -type f | wc -l) files"
done

Report:

Working Directory Scan
======================
Total files: 23
Total size:  145 KB

By Category:
  architecture/   8 files (SAD drafts, reviews)
  requirements/   5 files (UC iterations)
  testing/        4 files (test plan drafts)
  scratch/        6 files (temporary notes)

Age Distribution:
  < 1 day:    4 files
  1-7 days:   8 files
  > 7 days:  11 files

Step 2: Classify Files

Analyze each file to determine appropriate action:

**Classification Criteria:**

| Classification | Criteria | Action | |----------------|----------|--------| | PROMOTE | Final/reviewed version, high quality, no TODOs | Move to main .aiwg/ structure | | ARCHIVE | Useful history, superseded, completed work | Move to .aiwg/archive/ | | DELETE | Scratch notes, duplicates, empty, truly temp | Remove | | REVIEW | Unclear status, needs human decision | Flag for review |

**File Analysis Heuristics:**

def classify_file(filepath):
    content = read_file(filepath)
    filename = basename(filepath)

    # Check for finalization markers
    if "FINAL" in filename or "APPROVED" in filename:
        return "PROMOTE"
    if "BASELINED" in content or "Status: Approved" in content:
        return "PROMOTE"

    # Check for draft/WIP markers
    if "DRAFT" in filename or "WIP" in filename:
        if file_age_days(filepath) > 14:
            return "ARCHIVE"  # Old draft, archive for reference
        return "REVIEW"  # Recent draft, needs decision

    # Check for review files
    if "review" in filename.lower():
        if "synthesized" in get_parent_files(filepath):
            return "DELETE"  # Reviews already synthesized
        return "ARCHIVE"  # Keep reviews for audit

    # Check for scratch/temp patterns
    if "scratch" in filepath or "temp" in filepath:
        if file_age_days(filepath) > 3:
            return "DELETE"
        return "REVIEW"

    # Check for versioned files
    if re.match(r'v\d+\.\d+', filename):
        if not is_latest_version(filepath):
            return "ARCHIVE"
        return "PROMOTE"  # Latest version should be promoted

    # Default: needs review
    return "REVIEW"

Report:

File Classification
===================

PROMOTE (4 files):
  .aiwg/working/architecture/sad/v0.3-final.md
    → .aiwg/architecture/software-architecture-doc.md
    Reason: Final version, approved status

  .aiwg/working/requirements/uc-auth-approved.md
    → .aiwg/requirements/use-cases/uc-auth.md
    Reason: Approved use case

  .aiwg/working/testing/test-plan-baselined.md
    → .aiwg/testing/master-test-plan.md
    Reason: Baselined marker found

  .aiwg/working/architecture/adr-001-final.md
    → .aiwg/architecture/decisions/adr-001.md
    Reason: Final ADR

ARCHIVE (6 files):
  .aiwg/working/architecture/sad/v0.1-draft.md
    → .aiwg/archive/architecture/sad-v0.1-20251209.md
    Reason: Superseded by v0.3

  .aiwg/working/architecture/sad/reviews/security-review.md
    → .aiwg/archive/reviews/sad-security-review-20251209.md
    Reason: Review already synthesized

  .aiwg/working/architecture/sad/reviews/test-review.md
    → .aiwg/archive/reviews/sad-test-review-20251209.md
    Reason: Review already synthesized

  ... (3 more)

DELETE (8 files):
  .aiwg/working/scratch/notes.md
    Reason: Scratch file, 12 days old

  .aiwg/working/scratch/temp-analysis.md
    Reason: Temp file prefix, empty content

  .aiwg/working/architecture/sad/v0.2-draft.md
    Reason: Intermediate draft, v0.3 exists

  ... (5 more)

REVIEW (5 files):
  .aiwg/working/requirements/nfr-draft.md
    Reason: Recent draft (3 days), unclear status

  .aiwg/working/testing/integration-tests-wip.md
    Reason: WIP marker, may be active work

  ... (3 more)

Step 3: Determine Promotion Targets

Map working files to their correct permanent locations:

Promotion Mapping
=================

.aiwg/working/architecture/ → .aiwg/architecture/
  sad/*.md                  → software-architecture-doc.md
  adr-*.md                  → decisions/adr-*.md
  diagrams/                 → diagrams/

.aiwg/working/requirements/ → .aiwg/requirements/
  uc-*.md                   → use-cases/
  nfr-*.md                  → nfrs/
  user-story-*.md           → user-stories/

.aiwg/working
Read more
@jmagly
Ships withaiwg

Reusable project context and specialist workflows for the AI tools you already use. Plan software, coordinate specialist reviews, prepare campaigns, investigate incidents, organize research, curate media, and maintain operational knowledge.

229200 skills199 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
229
Star history of jmagly/aiwg on GitHub, a chart by star-history.com

Other skills on aiwg.

agent-loop-ext

agent-loop-ext

Crash-resilient external agent loop with state persistence and CI/CD integration

@jmagly@jmaglyInstall Skill
agent-loop

agent-loop

Detect requests for iterative autonomous agent loops and route to the appropriate loop executor

@jmagly@jmaglyInstall Skill
auto-test-execution

auto-test-execution

Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern

@jmagly@jmaglyInstall Skill

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills12d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc13d293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react2d252k
@facebook@facebookInstall Skill

Questions about workspace-prune-working.

Which coding agents can use workspace-prune-working?
workspace-prune-working installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.