Skip to content
cccskills
FreePublished on GitHub

flashtext

Routes FlashText tasks for keyword extraction, replacement, fuzzy matching, keyword loading, and keyword-inspection workflows.

The English summary is being prepared. Showing the original description.

See how to install

Files included (8)

  • SKILL.md3.3 KB
  • references/api-reference.md3.8 KB
  • references/data-formats.md1.9 KB
  • references/repo-provenance.md1.3 KB
  • references/repo-routing-metadata.json336 B
  • references/troubleshooting.md3.0 KB
  • references/workflows.md3.7 KB
  • scripts/check_install.py5.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

FlashText

Use this skill when a request names FlashText or asks to extract, replace, load, inspect, or fuzzily match keywords with KeywordProcessor.

This repository is small enough that one router covers the whole package. Read the bundled references for exact API details instead of reopening the original checkout.

Install and verify

  • Public install: python -m pip install flashtext
  • From a checkout: python -m pip install -e .
  • Safe smoke check: python scripts/check_install.py
  • JSON smoke output: python scripts/check_install.py --json
  • Minimal import check: python -I -c "from flashtext import KeywordProcessor; print(KeywordProcessor().__class__.__name__)"

If you are checking whether this skill still matches the repository snapshot, read references/repo-provenance.md before making that call.

Route map

  • Need to add, remove, count, or inspect keywords with dictionary-like behavior (len, in, [], get_keyword, get_all_keywords)? Read references/api-reference.md and references/workflows.md.
  • Need sentence extraction, replacement, spans, case_sensitive, or fuzzy max_cost behavior? Start with references/workflows.md, then open references/api-reference.md for exact signatures and return shapes.
  • Need to load keywords from a file, list, or dictionary, or you want the expected input shapes? Read references/data-formats.md.
  • Need to debug import errors, bad file paths, malformed list/dict shapes, replace_keywords with tuple clean names, or missed matches caused by word boundaries or case handling? Read references/troubleshooting.md, then rerun scripts/check_install.py.
  • Need to compare the current checkout against the recorded baseline? Read references/repo-provenance.md.

Typical request phrases

  • "extract keywords from this sentence"
  • "replace keywords with clean names"
  • "show spans for each match"
  • "make matching case sensitive"
  • "load keywords from a file"
  • "load from a list or dictionary"
  • "remove a keyword variant"
  • "allow punctuation like / inside keywords"
  • "debug why a keyword did not match"
  • "check whether the package is installed correctly"

What to read or run next

  • Use references/workflows.md for step-by-step usage patterns.
  • Use references/api-reference.md when you need the exact signature or return type for a method on KeywordProcessor.
  • Use references/data-formats.md when shaping file, list, or dictionary inputs.
  • Use references/troubleshooting.md for predictable input and matching failures.
  • Run scripts/check_install.py whenever you need a quick install/import/ smoke verification.

What this skill does not cover

  • No CLI entry point is shipped by the package.
  • No network service, model backend, or accelerator-specific workflow is involved.
  • No training, benchmarking, or docs-build workflow is part of the runtime route.

Working rule

Keep runtime instructions self-contained. Use the bundled references and script instead of the original repository when you need API details, data-shape reminders, or a fast validation check.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.

The English summary is being prepared. Showing the original description.

VectorSpaceLab/AREX-Skill339Updated Sep 3, 2026

3ddfa

Free

Guide 3DDFA Python inference, geometry rendering, training/evaluation, and optional C++ ONNX workflows for 3D dense face alignment.

The English summary is being prepared. Showing the original description.

VectorSpaceLab/AREX-Skill339Updated Sep 3, 2026

Routes 3DDFA_V2 face-alignment setup, still-image demos, video tracking, and ONNX benchmarking workflows.

The English summary is being prepared. Showing the original description.

VectorSpaceLab/AREX-Skill339Updated Sep 3, 2026

Operate AB3DMOT 3D multi-object tracking workflows for KITTI and nuScenes data, tracking, evaluation, and visualization.

The English summary is being prepared. Showing the original description.

VectorSpaceLab/AREX-Skill339Updated Sep 3, 2026

Use Hugging Face Accelerate for PyTorch training-loop migration, distributed launch/configuration, DeepSpeed/FSDP/TPU backend setup, big-model inference/offload, checkpointing, tracking, and troubleshooting.

The English summary is being prepared. Showing the original description.

VectorSpaceLab/AREX-Skill339Updated Sep 3, 2026

acme

Free

Route Acme reinforcement-learning framework tasks across core loops, replay/data, JAX agents, and TensorFlow/Sonnet agents.

The English summary is being prepared. Showing the original description.

VectorSpaceLab/AREX-Skill339Updated Sep 3, 2026

See all skills by VectorSpaceLab

Report a problem with this skill