Locate Missing Artifacts logo

Locate Missing Artifacts

OrganizationPopular
HKUDS
locate-missing-artifacts

Recover generated files in sandboxed environments by searching from confirmed roots and copying to expected locations

Overview

PublisherHKUDS
RepositoryOpenSpace
Skill namelocate-missing-artifacts
Stars
7.7K
Forks
918
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by HKUDS on GitHub. Read the source before you install it.

Installation

Install the Locate Missing Artifacts AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/HKUDS/OpenSpace.git /tmp/OpenSpace
mkdir -p .claude/skills
cp -r /tmp/OpenSpace/benchmarks/gdpval/skills/locate-missing-artifacts .claude/skills/locate-missing-artifacts
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Locate Missing Artifacts in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Locate Missing Artifacts on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Locate Missing Artifacts is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Locate Missing Artifacts in Sandboxed Environments

When to Use This Skill

Use this skill when:

  • A tool reports success but files are not found in their expected locations
  • You receive errors like "file not found" after a tool claims to have created it
  • You're working in a sandboxed/ephemeral environment where file paths may shift
  • Directory structure mismatches occur between tool execution and validation

Step-by-Step Instructions

Step 1: Confirm the Failure

Before searching, verify the file is actually missing from the expected location:

bash
ls -la /expected/path/filename.ext
# or
test -f /expected/path/filename.ext && echo "Found" || echo "Missing"

Step 2: Identify Confirmed Root Directories

Determine which directories you know exist and where tools typically write:

bash
# Common roots to check
ls -la /
ls -la $HOME
ls -la /tmp
ls -la /workspace
ls -la .

Step 3: Search for the Artifact Using find

Use find from confirmed root directories to locate the missing file:

bash
# Search by filename
find /workspace -name "filename.ext" 2>/dev/null

# Search by pattern if exact name varies
find /workspace -name "*.ext" 2>/dev/null

# Search broader paths if needed
find / -name "filename.ext" 2>/dev/null | head -20

Step 4: Copy Artifact to Expected Location

Once located, explicitly copy the file to where it should be:

bash
# Copy to expected location
cp /found/path/filename.ext /expected/path/filename.ext

# Or if you need to preserve the original
cp -r /found/path/filename.ext /expected/path/

# Verify the copy succeeded
ls -la /expected/path/filename.ext

Step 5: Validate Before Proceeding

Confirm the file is now accessible at the expected location:

bash
# Test file exists and is readable
test -f /expected/path/filename.ext && test -r /expected/path/filename.ext && echo "Ready"

# Check file size to ensure it's not empty
stat /expected/path/filename.ext

Common Patterns

Pattern: Output Written to Wrong Directory

bash
# Tool wrote to current directory instead of specified output dir
find . -name "*.docx" -type f
cp ./report.docx ./output/report.docx

Pattern: Temporary Directory Used

bash
# File ended up in /tmp or similar
find /tmp -name "*.pdf" -mtime -1
cp /tmp/generated.pdf ./deliverables/

Pattern: Nested Subdirectory Created

bash
# Tool created extra directory levels
find /workspace -type f -name "*.xlsx"
# May find: /workspace/output/2024/reports/file.xlsx
cp /workspace/output/2024/reports/file.xlsx /workspace/deliverables/

Prevention Tips

  1. Always specify absolute paths when giving tools output locations
  2. Check the working directory before and after tool execution: pwd
  3. Verify immediately after a tool reports success before proceeding
  4. Use tool-specific confirmations when available (e.g., return paths)

Example: Complete Recovery Workflow

bash
# 1. Tool reported creating report.docx but it's missing
ls ./deliverables/report.docx
# Output: ls: cannot access './deliverables/report.docx': No such file or directory

# 2. Search for it
find /workspace -name "report.docx" 2>/dev/null
# Output: /workspace/tmp/generated/report.docx

# 3. Copy to expected location
mkdir -p ./deliverables
cp /workspace/tmp/generated/report.docx ./deliverables/report.docx

# 4. Validate
ls -la ./deliverables/report.docx
# Output: -rw-r--r-- 1 user user 45678 Jan 15 10:30 ./deliverables/report.docx

# Success - file is now where it should be

Troubleshooting

ProblemSolution
find returns no resultsExpand search to broader paths (/, /home, /root)
Multiple matches foundCheck timestamps (-mtime -1) or file sizes to identify the correct one
Permission denied on copyUse sudo if available, or check if file is in a read-only mount
File exists but is emptyThe tool may have failed silently; regenerate the artifact

Frequently asked questions

What does the Locate Missing Artifacts AI skill do?

Recover generated files in sandboxed environments by searching from confirmed roots and copying to expected locations

Why use Locate Missing Artifacts on TypingMind?

Because you install it once and use it with any model. Locate Missing Artifacts is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Locate Missing Artifacts in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/locate-missing-artifacts. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Locate Missing Artifacts?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Locate Missing Artifacts?

As many as you like. As long as a model supports skills, you can use Locate Missing Artifacts with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Locate Missing Artifacts AI skill free?

Yes. It is published on GitHub by HKUDS under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇