aiskillstore/marketplace / skills/0xdarkmatter/tool-discovery
tool-discovery
VerifiedRecommend the right agents and skills for any task. Covers both heavyweight agents (Task tool) and lightweight skills (Skill tool). Triggers on: which agent, which skill, what tool should I use, help me choose, recommend agent, find the right tool.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.5 KB |
| assets/.gitkeep | other | 0 B |
| reference.md | markdown | 5.1 KB |
| references/agents-catalog.md | markdown | 4.2 KB |
| references/skills-catalog.md | markdown | 19.3 KB |
| scripts/.gitkeep | other | 0 B |
| skill-report.json | config | 20.0 KB |
reference.md
View on GitHub# Tool Discovery Reference
Authoritative recommendations for common tasks. Use these instead of manual implementations.
## File Formats
### Documents
| Format | Python | CLI | Notes |
|--------|--------|-----|-------|
| **PDF** | `PyMuPDF`, `pdfplumber` | `pdftotext` | PyMuPDF for complex, pdfplumber for tables |
| **Word (.docx)** | `python-docx` | `pandoc` | |
| **Excel (.xlsx)** | `openpyxl`, `pandas` | | openpyxl for formatting, pandas for data |
| **CSV** | `pandas`, `csv` | `csvkit` | pandas for analysis, csv for streaming |
| **JSON** | `json`, `orjson` | `jq` | orjson 10x faster than json |
| **YAML** | `PyYAML`, `ruamel.yaml` | `yq` | ruamel preserves comments |
| **TOML** | `tomllib` (3.11+), `toml` | `yq` | |
| **XML** | `lxml`, `xml.etree` | `xmlstarlet` | lxml for speed |
| **Markdown** | `markdown`, `mistune` | `pandoc` | |
### Images
| Task | Python | CLI | Notes |
|------|--------|-----|-------|
| **Read/Write** | `Pillow (PIL)` | `imagemagick` | |
| **Computer Vision** | `opencv-python` | | |
| **OCR** | `pytesseract`, `paddleocr` | `tesseract` | paddleocr more accurate |
| **Metadata** | `exifread`, `Pillow` | `exiftool` | |
| **QR Codes** | `qrcode`, `pyzbar` | `zbarimg` | |
### Audio/Video
| Task | Python | CLI | Notes |
|------|--------|-----|-------|
| **Audio I/O** | `pydub`, `soundfile` | `ffmpeg` | |
| **Audio Analysis** | `librosa` | | Feature extraction, spectrograms |
| **Speech-to-Text** | `whisper`, `vosk` | | whisper most accurate |
| **Video** | `moviepy`, `opencv` | `ffmpeg` | |
| **Transcoding** | `ffmpeg-python` | `ffmpeg` | |
### Archives
| Format | Python | CLI |
|--------|--------|-----|
| **ZIP** | `zipfile` | `unzip` |
| **TAR/GZ** | `tarfile` | `tar` |
| **7z** | `py7zr` | `7z` |
| **RAR** | `rarfile` | `unrar` |
## Data Processing
### Structured Data
| Task | Python | CLI |
|------|--------|-----|
| **DataFrames** | `pandas`, `polars` | | polars 10x faster |
| **SQL Queries** | `sqlalchemy`, `sqlite3` | `sqlite3` |
| **GraphQL** | `gql`, `sgqlc` | |
| **Protobuf** | `protobuf` | `protoc` |
### Text Processing
| Task | Python | CLI |
|------|--------|-----|
| **Regex** | `re` | `rg`, `grep` |
| **Find/Replace** | `re.sub()` | `sd`, `sed` |
| **Diff** | `difflib` | `delta`, `difft` |
| **Fuzzy Match** | `fuzzywuzzy`, `rapidfuzz` | `fzf` |
| **NLP** | `spacy`, `nltk` | |
| **Tokenization** | `tiktoken` | | OpenAI tokenizer |
### Web/Network
| Task | Python | CLI |
|------|--------|-----|
| **HTTP Requests** | `httpx`, `requests` | `curl`, `http` |
| **Web Scraping** | `beautifulsoup4`, `selectolax` | `firecrawl` |
| **HTML Parsing** | `lxml`, `html5lib` | |
| **URL Parsing** | `urllib.parse`, `furl` | |
| **WebSockets** | `websockets`, `socketio` | `websocat` |
| **DNS** | `dnspython` | `dig` |
## Domain-Specific
### Scientific Computing
| Domain | Python |
|--------|--------|
| **Arrays/Math** | `numpy` |
| **Scientific** | `scipy` |
| **Statistics** | `statsmodels`, `scipy.stats` |
| **Symbolic Math** | `sympy` |
| **Plotting** | `matplotlib`, `plotly` |
| **Geospatial** | `geopandas`, `shapely` |
### Machine Learning
| Task | Python |
|------|--------|
| **General ML** | `scikit-learn` |
| **Deep Learning** | `pytorch`, `tensorflow` |
| **NLP Models** | `transformers` (HuggingFace) |
| **Computer Vision** | `torchvision`, `timm` |
| **Embeddings** | `sentence-transformers` |
| **LLM Inference** | `llama-cpp-python`, `vllm` |
### Cryptography
| Task | Python |
|------|--------|
| **Hashing** | `hashlib` |
| **Encryption** | `cryptography` |
| **JWT** | `pyjwt` |
| **Passwords** | `bcrypt`, `argon2-cffi` |
| **Secrets** | `secrets` (stdlib) |
### Games/Puzzles
| Domain | Python |
|--------|--------|
| **Chess** | `python-chess` |
| **Sudoku** | `py-sudoku` |
| **Graph Problems** | `networkx` |
| **Optimization** | `ortools`, `pulp` |
### Bioinformatics
| Task | Python |
|------|--------|
| **Sequences** | `biopython` |
| **Genomics** | `pysam`, `pyvcf` |
| **Protein** | `biotite` |
## CLI Tools (Modern Replacements)
| Instead of | Use | Why |
|------------|-----|-----|
| `find` | `fd` | 5x faster, simpler syntax |
| `grep` | `rg` (ripgrep) | 10x faster, respects .gitignore |
| `ls` | `eza` | Git status, icons, tree view |
| `cat` | `bat` | Syntax highlighting |
| `du` | `dust` | Visual tree sorted by size |
| `man` | `tldr` | Practical examples only |
| `sed` | `sd` | Simpler syntax |
| `diff` | `delta`, `difft` | Syntax highlighting, AST-aware |
| `top` | `btm` | Better graphs |
| `ps` | `procs` | Enhanced process view |
## Verification Commands
Before using a tool, verify it's available:
```bash
# Python packages
pip list | grep <package>
python -c "import <package>; print(<package>.__version__)"
# CLI tools
which <tool>
<tool> --version
# Install if missing
pip install <package>
# or
uv pip install <package> # 10-100x faster
```
## Decision Tree
```
Need to process X?
├── Is X a standard file format?
│ └── Check "File Formats" section
├── Is X a data transformation?
│ └── Check "Data Processing" section
├── Is X domain-specific?
│ └── Check "Domain-Specific" section
└── Is X a CLI operation?
└── Check "CLI Tools" section
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |