Skip to main content
Prompts Folder Secrets Extractor and Notes Organizer

agent data_extraction template risk: high

Folder Secrets Extractor and Notes Organizer

Analyzes all files in a specified folder to extract sensitive data like API keys and credentials into secrets.md with source references. Identifies top topics across files, organiz…

  • Policy sensitive
  • Human review
  • External action: high

PROMPT 

Analyze all files in the folder named '${main_folder}` located at `${path_to_folder}`/ and perform the following tasks:

## Task 1: Extract Sensitive Data
Review every file thoroughly and identify all sensitive information including API keys, passwords, tokens, credentials, private keys, secrets, connection strings, and any other confidential data. Create a new file called `secrets.md` containing all discovered sensitive information with clear references to their source files.

## Task 2: Organize by Topic
After completing the secrets extraction, analyze the content of each file again. Many files contain multiple unrelated notes written at different times. Your job is to:

1. Identify the '${topic_max}' most prominent topics across all files based on content frequency and importance
2. Create '${topic_max}' new markdown files, one for each topic, named `${topic:#}.md` where you choose descriptive topic names
3. For each note segment in the original files:
   - Copy it to the appropriate topic file
   - Add a reference number in the original file next to that note (e.g., `${topic:2}` or `→ Security:2`)
   - This reference helps verify the migration later

## Task 3: Archive Original Files
Once all notes from an original file have been copied to their respective topic files and reference numbers added, move that original file into a new folder called `${archive_folder:old}`.

## Expected Final Structure
```
${main_folder}/
├── secrets.md (1 file)
├── ${topic:1}.md (topic files total)
├── ${topic:2}.md
├── ..... (more topic files)
├── ${topic:#}.md
└── ${archive_folder:old}/
      └── (all original files)
```

## Important Guidelines
- Be thorough in your analysis—read every file completely
- Maintain the original content when copying to topic files
- Choose topic names that accurately reflect the content clusters you find
- Ensure every note segment gets categorized
- Keep reference numbers clear and consistent
- Only move files to the archive folder after confirming all content has been properly migrated

Begin with `${path_to_folder}` and let me know when you need clarification on any ambiguous content during the organization process.

INPUTS

main_folder REQUIRED

name of the folder containing files to analyze

path_to_folder REQUIRED

base path to the location of the main_folder

topic_max REQUIRED

maximum number of prominent topics to create files for

e.g. 5

archive_folder

name of folder for archiving original files (default 'old')

e.g. old

REQUIRED CONTEXT

  • files in folder at path_to_folder/main_folder

ROLES & RULES

  1. Read every file completely.
  2. Maintain original content when copying to topic files.
  3. Choose topic names that accurately reflect content clusters.
  4. Ensure every note segment gets categorized.
  5. Keep reference numbers clear and consistent.
  6. Only move files to archive after confirming migration

EXPECTED OUTPUT

Format
markdown
Schema
directory_tree · secrets.md, topic files, archive_folder:old
Constraints
  • create secrets.md with source references
  • create topic markdown files with original content and references
  • add reference numbers to original files
  • move originals to archive folder
  • match expected final structure

SUCCESS CRITERIA

  • Extract all sensitive information into secrets.md
  • Identify top topics and create corresponding md files
  • Copy all note segments to topic files with references
  • Archive original files after migration

FAILURE MODES

  • Overlooking sensitive data in files
  • Mis categorizing notes into wrong topics
  • Incomplete copying leading to data loss
  • Inconsistent or unclear references
  • Archiving before full migration

CAVEATS

Dependencies
  • Requires access to folder at ${path_to_folder}/${main_folder}
  • Requires value for ${topic_max}
  • Requires values for placeholders like ${topic:#} and ${archive_folder:old}
Missing context
  • Values for placeholders like 'main_folder', 'path_to_folder', 'topic_max', 'archive_folder'.
  • Mechanism for accessing/reading files at 'path_to_folder' (LLMs cannot directly access local files).
  • Handling of non-text files or binary files.
  • Edge cases for sensitive data detection.
Ambiguities
  • What constitutes a 'note segment'?
  • Criteria for 'prominent topics based on content frequency and importance' are vague.
  • Inconsistent reference formats: '${topic:2}' vs '→ Security:2'.
  • Typo in expected structure: '${topic:1}.md (topic files total)'.

QUALITY

OVERALL
0.80
CLARITY
0.80
SPECIFICITY
0.70
REUSABILITY
0.90
COMPLETENESS
0.70

IMPROVEMENT SUGGESTIONS

  • Define 'note segment' explicitly, e.g., 'a contiguous block of related content separated by dates or headings'.
  • Specify topic selection criteria, e.g., 'use keyword frequency, TF-IDF, or clustering algorithms'.
  • Standardize reference format, e.g., '→ [TopicName]:[RefNum]'.
  • Correct expected structure to clearly show total topic files, e.g., '[topic1].md, [topic2].md, ..., up to ${topic_max}.md'.
  • Add instructions for file access, e.g., 'Assume files are provided as text input or use a tool for reading'.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR AGENT