Agent skill

Gaik Add Examples

by GAIK-project in GAIK-project/gaik-toolkit

Adds or updates working code examples for GAIK toolkit components and pipelines in implementationlayer/examples/.

MITAuto-check: notesAI & LLM Engineering

Install Gaik Add Examples

skills CLI
$ npx skills add GAIK-project/gaik-toolkit --skill gaik-add-examples -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install GAIK-project/gaik-toolkit gaik-add-examples --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/GAIK-project/gaik-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/gaik-add-examples .claude/skills/gaik-add-examples && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gaik-add-examples
GitHub stars
100
Token cost
~2.4k tokens
SKILL.md length
822 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Adds or updates working code examples for GAIK toolkit components and pipelines in implementationlayer/examples/.

  • Works in 5 steps: Choose the right location → Follow the standard file structure → Add or update README.md in the… → …
  • Adding a new example
  • SKILL.md covers Steps, Configuration pattern, Step 6 — Optional follow-ups… and Notes
  • Calls pip, git and python

What it does

Gaik Add Examples is an agent skill from GAIK-project/gaik-toolkit. Adds or updates working code examples for GAIK toolkit components and pipelines in implementationlayer/examples/. Use when adding a new example, demonstrating a feature, creating a usage sample, or showing how a building block or pipeline works. After the example is in place, offers optional follow-ups: update API docs (guidancelayer/docs/), update the Fumadocs website (guidancelayer/website/content/docs/), expose the feature in the demo app (toolkitdemoapp/api/routers + UI), and push a PyPI release tag. Covers…

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Technical documentation, Text to speech and voice and Performance reviews. It works with PostgreSQL. The repository describes itself as: Python toolkit providing reusable AI/ML utilities: schema extraction, structured outputs, and production-ready components. The licence is MIT.

When your agent uses it

  • Adding a new example
  • Demonstrating a feature
  • Creating a usage sample
  • Showing how a building block

Example prompts

  • “/gaik-add-examples”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Choose the right location
  2. Follow the standard file structure
  3. Add or update README.md in the component/module directory covering
  4. Update the parent README.md (software_components/README.md or software_modules/README.md) to list the new example.
  5. Add sample input files if needed (PDFs, audio files, images) to an input/ subdirectory. Keep samples small and redistributable.

What it can do on your machine

Read from SKILL.md and the folder at commit e66fcca. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pip
    • git
    • python
    • pnpm
    • bun
    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, git, pnpm and uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gaik Add Examples loads about 2.4k tokens when it runs. Until then it costs about 257 tokens; SKILL.md has 822 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~257
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:61
    v(Path(__file__).parent.parent.parent / ".env")
  • NoteMentions a .env fileSKILL.md:78
    ample.py` → `.parent.parent.parent` for `.env`, `.parent.parent.parent.parent / "src"` for src

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from GAIK-project/gaik-toolkit at commit e66fcca, republished under its MIT licence (© GAIK-project). 822 words, ~2,373 tokens.

Download SKILL.mdSave it as .claude/skills/gaik-add-examples/SKILL.md (or your agent's skills folder).
name
gaik-add-examples
description
Adds or updates working code examples for GAIK toolkit components and pipelines in implementation_layer/examples/. Use when adding a new example, demonstrating a feature, creating a usage sample, or showing how a building block or pipeline works. After the example is in place, offers optional follow-ups: update API docs (guidance_layer/docs/), update the Fumadocs website (guidance_layer/website/content/docs/), expose the feature in the demo app (toolkit_demo_app/api/routers + UI), and push a PyPI release tag. Covers software_components (extractor, parsers, transcriber, RAG, classifier, TTS, enhance_transcript, postgres_agent, tabular_agent, validators (LLMJudge / panel / pairwise / calibration), evaluators (ExtractionEvaluator, RAGEvaluator, BatchEvaluationRunner), form_understander, observability) and software_modules (AudioToStructuredData, DocumentsToStructuredData, RAGWorkflow, MultiSourceReportGenerator). Not for creating a brand-new component package — use build-software-component for that.
argument-hint
[component name or feature to demonstrate]

Add GAIK Examples

Adds or updates working examples under implementation_layer/examples/. After the example is added, asks the user whether to propagate the new capability to docs, the demo app, and a PyPI release.

Not this skill's job — use build-software-component instead when the user wants to create a brand-new component package (new source files under implementation_layer/src/gaik/software_components/..., new pyproject.toml extra, installable pip install "gaik[...]" flow).

Examples live in implementation_layer/examples/ split into two categories:

  • software_components/ — individual building blocks (extractor, parsers, transcriber, RAG, classifier, TTS, etc.)
  • software_modules/ — end-to-end pipelines (audio_to_structured_data, documents_to_structured_data, RAG_workflow, multi_source_report_generator)

Steps

  1. Choose the right location

    • New building block example → software_components/<component_name>/
    • New pipeline example → software_modules/<pipeline_name>/
    • Adding to existing component → add a numbered/named file alongside the existing ones: demo_<variant>.py, <component>_example_2.py, etc.
  2. Follow the standard file structure

python
"""
Example: [one-line summary]
Workflow: [input] -> [step1] -> [step2] -> [output]
"""

from __future__ import annotations

import sys
from pathlib import Path

from dotenv import load_dotenv

# Load environment variables before importing gaik modules
load_dotenv(Path(__file__).parent.parent.parent / ".env")

# Add src directory to path to import modules (works without pip install)
sys.path.insert(0, str(Path(__file__).parent.parent.parent.parent / "src"))

from gaik... import ...


def main() -> None:
    # example code here


if __name__ == "__main__":
    main()

Adjust .parent depth to reach implementation_layer/ from the example file's location.

  • software_components/<comp>/example.py → .parent.parent.parent for .env, .parent.parent.parent.parent / "src" for src
  • software_modules/<mod>/example.py → same depth
  • Subdirectory example (e.g. software_modules/<mod>/subdir/example.py) → add one more .parent
  1. Add or update README.md in the component/module directory covering:

    • Prerequisites (pip extras: e.g. pip install "gaik[extract]", required env vars)
    • How to run: python example.py
    • What the example demonstrates
  2. Update the parent README.md (software_components/README.md or software_modules/README.md) to list the new example.

  3. Add sample input files if needed (PDFs, audio files, images) to an input/ subdirectory. Keep samples small and redistributable.

Configuration pattern

OpenAI/Azure-only examples use the legacy config — always import from gaik.software_components.config:

python
from gaik.software_components.config import get_openai_config, create_openai_client

config = get_openai_config(use_azure=True)   # Azure OpenAI
config = get_openai_config(use_azure=False)  # Standard OpenAI
client = create_openai_client(config)        # OpenAI/AzureOpenAI client

Pipeline constructors accept use_azure=True/False directly:

python
pipeline = DocumentsToStructuredData(use_azure=True)

Multi-provider examples (anything that must run on another provider than OpenAI/Azure) use the multi-provider surface; component constructors accept the same dict as config / api_config:

python
from gaik.software_components.llm import get_llm_config, create_llm_client

config = get_llm_config("anthropic")  # or "openai", "azure", "aitta", "openai_compatible",
                                      #    "google", "vertex", "anthropic_foundry", "litellm"
client = create_llm_client(config)    # ProviderClient (chat / chat_parsed / chat_stream / embed)

gaik[llm-anthropic], gaik[llm-google] and gaik[llm-litellm] pull in the provider SDKs on demand; OpenAI, Azure, Aitta and openai_compatible need no extra.

Step 6 — Optional follow-ups (ask the user)

After Steps 1–5 are done, the example is working. Ask the user whether to propagate the new capability further. Each sub-step is gated by its own yes/no question — run only the ones the user approves.

Default suggestion: ask all four unless the example is a trivial tweak to an existing file. Skip straight to a single question in that case.

6a. Update API docs (guidance_layer/docs/)

Ask: "Update API-level Markdown docs under guidance_layer/docs/?"

Update when: the example introduces a new public API surface, new constructor params, or a new public method.

  • guidance_layer/docs/software_components/<component>.md — per-component API reference
  • guidance_layer/docs/software_modules/<pipeline>/ — pipeline API reference
6b. Update Fumadocs website (guidance_layer/website/content/docs/)

Ask: "Update the user-facing Fumadocs website?"

Update when: the example demonstrates a new capability users would discover via the website.

  • toolkit/software-components.mdx or toolkit/software-modules.mdx — component catalog
  • use-cases/<case>.mdx — new or updated use case walkthrough
  • Update the relevant meta.json if a new page is added
  • Preview locally: cd guidance_layer/website && pnpm dev (uses pnpm, not bun)
Show full SKILL.md (383 more words)Show less
6c. Expose in toolkit_demo_app/

Ask: "Expose this in the demo app (implementation_layer/toolkit_demo_app/)?"

Default: yes for interactive, user-facing features (parsers, transcribers, extractors, RAG, TTS, classifiers); no for internal utilities.

If yes:

  • Add/extend a FastAPI router under implementation_layer/toolkit_demo_app/api/routers/ (e.g. parser.py, extractor.py, rag.py)
  • Add schema(s) under implementation_layer/toolkit_demo_app/api/schemas/
  • Add or update a Next.js page/route under implementation_layer/toolkit_demo_app/app/
  • Handle missing optional dependencies gracefully (the extra may not be installed by default)
  • If the endpoint makes chat or vision calls, let Model settings (a user's own key, sent as the x-gaik-model-settings header) reach it: add its POST path to _PATHS in api/utils/model_settings.py and SUPPORTED_PATHS in lib/model-settings.ts, add the page to pageUsesModelSettings (its "own model" notice), and build the config with get_api_config() from api/utils/config.py. A path missing from the frontend list silently runs on the server key, and the API answers the header on an unlisted path with 400. Leave audio and embedding endpoints out: an own key selects one chat/vision model only.
  • Dev preview: bun run dev:all from implementation_layer/toolkit_demo_app/
6d. Tag a PyPI release

Ask: "Tag a PyPI release now?"

Only relevant if the example accompanies a code change in implementation_layer/src/gaik/ (pure docs/example-only changes don't need a release).

If yes:

  1. Choose the semver bump (patch / minor / major); call the planned version X.Y.Z.
  2. Set implementation_layer/solution_wizard/gaik_validated_version.txt to X.Y.Z (run the gaik-sync skill first if gaik's public surface changed), then commit the intended release.
  3. Certify that commit — mandatory before every tag: uv run python scripts/release_check.py --live --version X.Y.Z. Set RELEASE_PROVIDERS and explicit RELEASE_<PROVIDER>_MODEL IDs first (docs/releasing.md). The passing results/release-check.json must name this commit and X.Y.Z; rerun after any tracked change. A failed, skipped or timed-out check, or missing credentials, stops the release — never bypass it.
  4. Push, then tag and push the tag: git tag vX.Y.Z && git push origin vX.Y.Z.
  5. .github/workflows/publish.yml triggers on the v*.*.* tag, reruns the full gate including live certification (release_gate: true), and only then builds, uploads to PyPI and creates a GitHub Release.
  6. setuptools-scm derives the version from the tag — never edit version strings manually.

Notes

  • Examples serve as both usage documentation and integration tests
  • Keep each file focused on one concept — add a new numbered/named file for a new concept
  • Real-world complexity examples go in a subdirectory (e.g., diary_workflow/)
  • For the full mapping of "what changed → what to update", see the gaik-toolkit skill

© GAIK-project, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/gaik-add-examples of GAIK-project/gaik-toolkit.

Open the folder on GitHubat commit e66fcca

Compare with similar skills

Gaik Add Examples next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gaik Add Examples compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gaik Add Examples this skillGAIK-project/gaik-toolkit100—~2.4kAutomated safety check: NotesMIT
Vss Deploy Detection Tracking 3DNVIDIA-AI-Blueprints/video-search-and-summarization1.9k—~5.1kAutomated safety check: NotesApache-2.0
AI SDK Developmenttrypostit/trypost6911 repos~3.5kAutomated safety check: PassMIT
evlog Enricher Creatorevloghq/evlog1.9k—~1.7kAutomated safety check: PassMIT
Neurolink Guidejuspay/neurolink145—~1.4kAutomated safety check: PassMIT
Pgvector Semantic Searchtimescale/pg-aiguide1.9k—~3.8kAutomated safety check: PassApache-2.0

Similar skills

  • Vss Deploy Detection Tracking 3D

    NVIDIA-AI-Blueprints/video-search-and-summarization

    A skill your agent uses when deploying or operating standalone RTVI-CV-3D / MV3DT multi-camera 3D tracking for calibrated MP4/file inputs and live RTSP streams: missing-calibration handoff to AMC…

    1.9k GitHub stars~5.1k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • AI SDK Development

    trypostit/trypost

    TRIGGER when working with ai-sdk which is Laravel official first-party AI SDK.

    691 GitHub starsUsed in 1 repo~3.5k tokens
    AI & LLM EngineeringAuto-check passed
  • Guides adding a new built-in enricher to the evlog package, covering the source, tests, docs, README, a related skill and a changeset.

    1.9k GitHub stars~1.7k tokensUpdated today
    DevelopmentAuto-check passed
  • Neurolink Guide

    juspay/neurolink

    Guide for using the NeuroLink SDK and CLI. An agent skill from juspay/neurolink.

    145 GitHub stars~1.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Pgvector Semantic Search

    timescale/pg-aiguide

    A skill your agent uses for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search.

    1.9k GitHub stars~3.8k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed
  • Postgres Hybrid Text Search

    timescale/pg-aiguide

    A skill your agent uses to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF).

    1.9k GitHub stars~3.1k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

More from GAIK-project/gaik-toolkit

All 15 skills in this repo
  • Brief To Slides

    GAIK-project/gaik-toolkit

    Builds a visual, editable PowerPoint (.pptx) deck with speaker-ready notes, exact timing, citations and a layout-checked design from a topic, an audience and a length, using only the user's own…

    100 GitHub stars~2.8k tokensUpdated yesterday
    Auto-check passed
  • Gaik Toolkit

    GAIK-project/gaik-toolkit

    GAIK toolkit overview and reference. An agent skill from GAIK-project/gaik-toolkit.

    100 GitHub stars~5.7k tokensUpdated yesterday
    Auto-check passed
  • Extracting Structured Data

    GAIK-project/gaik-toolkit

    Extracts structured data — fields, tables, line items — out of documents into a validated schema using the gaik toolkit, and designs schemas that stay inside provider limits and produce checkable…

    100 GitHub stars~3.2k tokensUpdated yesterday
    Auto-check passed
  • Parsing Documents

    GAIK-project/gaik-toolkit

    Converts PDFs, scans, and Word documents into text or markdown with the gaik toolkit's parsers, choosing the parser that will not silently destroy the structure the downstream task depends on.

    100 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed
  • Searching Documents

    GAIK-project/gaik-toolkit

    Builds and debugs retrieval with the gaik toolkit — PgVectorStore, Ranker, FinnishTextProcessor, RelevanceGate — as hybrid search: pgvector similarity plus Postgres full-text, fused by rank, and the…

    100 GitHub stars~4.2k tokensUpdated yesterday
    Auto-check passed
  • Construction Diary Creation

    GAIK-project/gaik-toolkit

    Extracts structured data from Finnish construction site daily diary audio recordings (Työmaapäiväkirja) and creates a formatted Word document with extracted fields.

    100 GitHub stars~3.6k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Gaik Add Examples

What does Gaik Add Examples do?

Adds or updates working code examples for GAIK toolkit components and pipelines in implementationlayer/examples/. Gaik Add Examples is an agent skill from GAIK-project/gaik-toolkit. Adds or updates working code examples for GAIK toolkit components and pipelines in implementationlayer/examples/.

When should I use Gaik Add Examples?

Gaik Add Examples fits situations like: adding a new example; demonstrating a feature; creating a usage sample; showing how a building block.

How do I install Gaik Add Examples in Claude Code?

Run `npx skills add GAIK-project/gaik-toolkit --skill gaik-add-examples -a claude-code`. Or copy the skill folder (.claude/skills/gaik-add-examples in GAIK-project/gaik-toolkit) into .claude/skills/gaik-add-examples in your project. Claude Code loads it when a task matches its description.

How do I install Gaik Add Examples in Codex?

Run `npx skills add GAIK-project/gaik-toolkit --skill gaik-add-examples -a codex`. Or copy the skill folder (.claude/skills/gaik-add-examples in GAIK-project/gaik-toolkit) into .agents/skills/gaik-add-examples in your project. Codex loads it when a task matches its description.

Can I use Gaik Add Examples in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GAIK-project/gaik-toolkit --skill gaik-add-examples -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gaik-add-examples, .gemini/skills/gaik-add-examples, .github/skills/gaik-add-examples and .opencode/skills/gaik-add-examples in your project.

What does Gaik Add Examples need to run?

Going by SKILL.md and its folder, Gaik Add Examples needs the command-line tools its instructions call (pip, git, python, pnpm, bun and uv). Our summary lists: Python 3.

Does Gaik Add Examples access the network?

SKILL.md contains no URLs. Its commands use pip, git and uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Gaik Add Examples safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Gaik Add Examples use?

Gaik Add Examples is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gaik Add Examples use?

About 2.4k tokens (SKILL.md is roughly 9.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gaik Add Examples?

Skills that share tags, products or a category with Gaik Add Examples: Vss Deploy Detection Tracking 3D (NVIDIA-AI-Blueprints/video-search-and-summarization, 1.9k stars), AI SDK Development (trypostit/trypost, 691 stars), evlog Enricher Creator (evloghq/evlog, 1.9k stars) and Neurolink Guide (juspay/neurolink, 145 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gaik Add Examples?

GAIK-project (a GitHub organization) maintains it in GAIK-project/gaik-toolkit, which has 100 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 9, 2026.

Source: GAIK-project/gaik-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.