ImageNew
Property walkthrough video from listing photos
One shot per room with camera movement, a mandatory notice on any retouched image, and a list of flaws that must stay visible.
€24.90or 5 credits
The catalogue
457 resourcesPrompts are everywhere. Tested prompts, not so much.
Found online
VeyraForma
A few lines, no instructions
A complete, step-by-step prompt
Nobody has tried it
Tested, with the date to prove it
No files included
Scripts and templates included
Nobody knows where it came from
Official sources cited
You tinker.
You move forward.
76 results
- VideoNew
Install Ollama and run a first model
A read-only diagnostic and a step-by-step guide to run a first local language model.
€9.90or 2 credits - VideoNew
Evaluate a RAG with a question set
A 50-question set and a scoring script: recall, rank, expected keywords and refusal when no answer exists.
€24.90or 5 credits - VideoNew
Easy-to-read text (FALC)
A prompt to draft easy-to-read text, a script checking sentence and word length, and the reminder that validation belongs to the people concerned.
€19.90or 4 credits - VideoNew
Cut your bill with prompt caching
Cache the stable prefix of a prompt and compute the savings in advance with a script.
€14.90or 3 credits - VideoNew
Prompt-injection guardrails for an acting agent
An 11-point checklist scored by script and a filter that decides, action by action, whether the agent acts, asks a human or is blocked.
€19.90or 4 credits - VideoNew
Local model license table
A dated Llama, Gemma, Qwen and Mistral table and a script that gives a verdict for your use: internal, commercial, redistributed or hosted.
€9.90or 2 credits - VideoNew
Contextual Retrieval: add context to chunks
A dependency-free script that chunks your documents, has each chunk given a context sentence, searches with BM25 and measures the failure rate before and after.
€24.90or 5 credits - VideoNew
Define measurable success criteria
A criteria template, a validator that rejects vague criteria and an evaluator that tells you, with numbers, whether your LLM app meets its thresholds.
€14.90or 3 credits - VideoNew
File-based agent memory
A ready-to-plug Python handler for the Claude API memory tool: six commands, one folder per user, path-traversal protection and secret filtering.
€24.90or 5 credits - VideoNew
Your team's AI literacy plan
From an inventory of AI tools and roles, a script produces the annual AI literacy plan (AI Act Article 4) and the evidence register to fill in.
€14.90or 3 credits - VideoNew
Claude in Chrome for a supervised repetitive task
Hand a repetitive browser task to Claude in Chrome with a checked task card, human stop points and a log reviewed after the session.
€14.90or 3 credits - VideoNew
LLM judge with a Likert scale
Have a second model score an assistant's answers from 1 to 5, with an anchored rubric, a strict score format and checks against bias and injection.
€19.90or 4 credits - VideoNew
XML tags to separate instructions, documents and examples
Put each part of your prompt in a named block for more reliable, easy-to-extract answers, with a script that assembles, checks and extracts.
€9.90or 2 credits - VideoNew
Long documents first, question last
The right order to query a long document, with a script that spots and fixes a badly ordered prompt and an A/B kit to measure the gain yourself.
€9.90or 2 credits - VideoNew
Quote first, answer second (quote grounding)
Make the model copy the relevant passages verbatim before answering, then automatically check that every sentence rests on a real quote.
€14.90or 3 credits - VideoNew
Metaprompt: let the AI write your prompt's first draft
Describe the task in one sentence and get a full prompt with variables, steps and output format, checked and filled by a script.
€14.90or 3 credits - VideoNew
5-step prompt improver
Reproduce Anthropic's 5-step prompt improver yourself, for free, with a checker that guarantees no variable or example was lost.
€14.90or 3 credits - VideoNew
Context engineering: just-in-time loading, compaction, notes
Keep your agents' context lean: references instead of content, verified compaction that loses no decision, and persistent notes.
€19.90or 4 credits - VideoNew
Working across multiple context windows (tests.json, progress.txt, git)
A first session that sets up tests and scripts, later sessions that reload state and progress step by step, with a script that rejects deleted tests and false statuses.
€19.90or 4 credits - VideoNew
Metaprompting: ask the model which sentences to change
Have the model propose the minimal additions and deletions that fix a behavior, and apply them with a script that rejects full rewrites.
€9.90or 2 credits - VideoNew
Ralph loop: re-run the agent until a verified completion promise
The agent re-reads the same prompt turn after turn, one plan task at a time, until a completion phrase that is accepted only if tests pass.
€19.90or 4 credits - VideoNew
/goal: a completion condition judged by a separate evaluator
Write /goal conditions Claude Code's evaluator can actually judge: measurable end state, displayed proof, constraints and a turn bound.
€12.90or 3 credits - VideoNew
Subagent-driven development with two-stage review
A fresh subagent per plan task, then a spec-compliance review and a code-quality review before moving on.
€19.90or 4 credits - VideoNew
Writing a Skill through pressure tests (TDD for Skills)
A method to first make an agent fail without the Skill on trap scenarios, write the minimal Skill, then check it withstands rationalisations.
€19.90or 4 credits - VideoNew
Automatic formatting and linting after every edit (hook)
A PostToolUse hook that formats and checks every file Claude Code edits and only feeds back the useful errors.
€14.90or 3 credits - VideoNew
Dangerous command firewall (PreToolUse hook)
A Claude Code hook that parses every Bash command before it runs and allows it, asks you to confirm it, or blocks it with an explanation.
€14.90or 3 credits - VideoNew
Plan mode: explore, plan, then code
How to make Claude Code explore read-only, produce a code-anchored plan, check it with a script, and only then write code.
€9.90or 2 credits - VideoNew
Research, plan, implement with intentional compaction
Three phases separated by /clear, each closed by a short script-checked document that alone starts the next phase.
€14.90or 3 credits - VideoNew
Stagehand: half-code, half-AI web automation
Write durable web scripts: hard-coded where the page is stable, AI only where it varies, with a local selector cache.
€19.90or 4 credits - VideoNew
Jina Reader: any web page as Markdown with a URL prefix
Prefix a URL with r.jina.ai to get a page's clean text, with a script and an n8n workflow that handle rate limits, errors and hard pages.
€9.90or 2 credits - VideoNew
Turn an n8n webhook into a private AI API
A key-protected HTTP endpoint that receives text, has an AI process it and returns clean JSON, with validation, rate limiting and error handling.
€14.90or 3 credits - VideoNew
Call any API without a native integration (HTTP Request, cURL import)
From the doc's cURL example to a reliable n8n workflow: key in a credential, right pagination, no silent partial data.
€14.90or 3 credits - VideoNew
Capture a product or a place with Gaussian splatting
Film, sort, calibrate and publish a photorealistic 3D scene viewable in the browser, with commercially usable tools.
€19.90or 4 credits - VideoNew
Open-source music with lyric editing (ACE-Step, YuE)
Generate full songs locally from tagged lyrics, then rewrite a single passage (repaint) without touching the rest of the track.
€12.90or 3 credits - VideoNew
Agent team debating competing hypotheses
Have 3 to 5 Claude Code teammates investigate different hypotheses and refute each other, with a checked findings file and control hooks.
€14.90or 3 credits - VideoNew
Automatic compressed memory through hooks
Claude Code hooks capture the session, summarize it, index it in SQLite and inject only a short index at startup; details are searched on demand.
€14.90or 3 credits - VideoNew
Dependency task graph for agents (Beads)
Long work goes into Beads, a CLI issue tracker with dependencies and claimable ready work; a checker spots cycles, duplicates and abandoned claims.
€12.90or 3 credits - VideoNew
Status line: context, usage limits and running agents
Two dependency-free Node scripts continuously show context fill, 5-hour and 7-day limits, git branch and each subagent's state in Claude Code.
€9.90or 2 credits - VideoNew
Usage report from local session logs
A read-only script reads Claude Code session logs and reports usage by day, session, project and model, with a list-price cost equivalent.
€12.90or 3 credits - VideoNew
Pack a repository into a single file for a model
Repomix produces a single file with tree, filtered files and token count, then our checker blocks leftover secrets and oversized packs.
€9.90or 2 credits - VideoNew
Second opinion from another model inside Claude Code
Claude has the change reviewed by another model (Codex, advisor or subagent), compares both reviews by script and lets the human decide within two rounds.
€12.90or 3 credits - VideoNew
Specialised subagents with a model matched to each role
A library of six Claude Code subagents where each definition sets its role, tools and model, with a checker that flags tiering mistakes and duplicates.
€14.90or 3 credits - VideoNew
Teaching output styles: explain, or have the learner code
Two French Claude Code output styles: one explains its choices, the other leaves the learner a 3-10 line formative piece with a failing test and graded hints.
€9.90or 2 credits - VideoNew
One instruction file for every coding agent (AGENTS.md)
A single AGENTS.md imported by CLAUDE.md and wired into Gemini CLI and Cursor, with a checker and a canary word to prove each tool loaded it.
€9.90or 2 credits - VideoNew
Hook-enforced TDD: no code without a failing test
A Claude Code hook reads real pytest results and blocks production code without a failing test, functions no test asks for, and Bash workarounds.
€19.90or 4 credits - VideoNew
Checkpoints and rewind in a Claude Code session
What /rewind really restores, its blind spots, and an original git safety net (side-effect-free snapshot, dry-run then real restore, automatic hook before risky shell commands).
€12.90or 3 credits - VideoNew
Routing Claude Code to other models
Design and test Claude Code Router rules offline (order, conditions, subagents) and estimate savings on your own prices before routing anything.
€14.90or 3 credits - VideoNew
Task Master: a PRD split into tasks for a coding agent
Write a precise PRD, have Task Master split it into dependent tasks, check and re-split before starting the agent, then have it execute one task at a time.
€14.90or 3 credits - VideoNew
Multi-model second opinion from Claude (PAL, formerly Zen MCP)
Have another model review, debate or settle a decision without leaving Claude Code, sending a prepared excerpt instead of whole files, and settling disagreements with a test rather than a vote.
€19.90or 4 credits - VideoNew
FastMCP: build your own MCP server in Python
Turn an in-house tool into an MCP server with a few decorated Python functions, model-friendly descriptions, bounded parameters, clean errors and automated tests.
€14.90or 3 credits - VideoNew
MCP Inspector: test and debug an MCP server
A 4-step diagnostic method with MCP Inspector (web UI and CLI mode) and a script that recognises the 6 most common MCP server failures and explains the fix.
€9.90or 2 credits - VideoNew
Vibe Kanban: several coding agents in parallel on a board
Run several coding agents at once, each in its own worktree, with batches that share no file and a check of each branch (conflict, overflow, tests) before merging.
€14.90or 3 credits - VideoNew
Claude Skills reused in an n8n agent
Replace an n8n agent's giant system prompt with an index of Claude-format skills stored in a GitHub repository: the agent loads only the useful method, through a tool that rejects any name outside the index.
€14.90or 3 credits - VideoNew
Docling: complex PDFs (tables, columns) ready for RAG
Converts PDFs with tables and columns using Docling, then chunks them for RAG without ever breaking a table or losing the heading path.
€14.90or 3 credits - VideoNew
Self-hosted AI kit: n8n, Ollama and Qdrant running locally
Install n8n, Ollama models and the Qdrant vector database on your machine with Docker Compose, secured and ready for a first workflow on your documents.
€14.90or 3 credits - VideoNew
mcp-remote: connect a remote MCP server to a local client
A local bridge that relays a remote MCP server (OAuth or token) to a client that only runs local servers, with token-safe cache troubleshooting.
€12.90or 3 credits - VideoNew
MCP-UI: agent responses with an interactive interface
An MCP tool that returns an interactive table with buttons in compatible clients, and complete text everywhere else, with no injection risk.
€14.90or 3 credits - VideoNew
OmniParser: a screenshot turned into numbered clickable elements
OmniParser detects every button and icon in a screenshot; our scripts clean, number and locate them, flagging ambiguity instead of guessing.
€14.90or 3 credits - VideoNew
Graphiti: temporal graph memory for agents
How to give an agent a memory that dates every fact and knows what was true when, with a tested reference model and a ready-to-adapt Graphiti script.
€19.90or 4 credits - VideoNew
Agent Mail: coordinating several coding agents
Agent-to-agent messaging, file reservations and written rules so several coding agents share one repository without overwriting each other, with a pre-commit check.
€19.90or 4 credits - VideoNew
Tuning a GPT-5 agent's eagerness: effort, tool budget, preambles
Settings and three instruction templates so an agent neither over- nor under-searches, plus a script that flags contradictory instructions and checks an execution trace.
€12.90or 3 credits - VideoNew
Iterative prompt optimisation with side-by-side comparison
Improve a prompt in short rounds: fixed test cases, old and new outputs compared blind, per-case voting and a decision rule that protects critical cases.
€11.90or 2 credits - VideoNew
Prompting rules specific to Gemini 3
The official rules that change with Gemini 3 (delimiters, constraints first, question last, verbosity, temperature), two templates and a script that converts and checks your prompts.
€9.90or 2 credits - VideoNew
Structured Markdown prompt: role, profile, rules, workflow
A fixed-section template for GPTs, Gems and Projects instructions, with a checker that flags missing sections, contradictory rules and excessive rigidity.
€9.90or 2 credits - VideoNew
Structured extraction grounded in the source text
A prompt that extracts verbatim values, and a script that finds each value's exact position in the text, highlights it and isolates invented values.
€14.90or 3 credits - VideoNew
Convert any document to Markdown before prompting
Convert PDF, Word and Excel to Markdown, strip conversion noise, flag doubtful tables and assemble a prompt with tagged documents and the question last.
€9.90or 2 credits - VideoNew
10-page illustrated book with narration
A 10-page story with the same hero in every picture thanks to word-for-word character sheets, script-checked, with local audio narration.
€12.90or 3 credits - VideoNew
Structured outputs instead of prefilling
Replace the prefill trick, rejected by recent Claude models, with a JSON schema, a no-preamble instruction and code-side checks.
€12.90or 3 credits - VideoNew
DSPy: optimize your prompts programmatically
Describe the task, provide examples and a metric: DSPy picks the prompt demonstrations itself, with a complete, tested and saveable pipeline.
€19.90or 4 credits - VideoNew
Advanced reasoning: step-back, self-consistency, tree of thoughts
Three complete prompts that make the chatbot step back, compare several answers and explore options before concluding, with a voting script.
€9.90or 2 credits - VideoNew
Reusable command-line prompt library
Five original French patterns for Fabric, a maintainable layout checked by a script and a fallback runner for a local model.
€12.90or 3 credits - VideoNew
POML: write your prompts as a marked-up page
A French guide to POML with a complete template, data kept in separate JSON files and a script that renders, sanitizes and checks the prompt before sending.
€14.90or 3 credits - VideoNew
Prompt tournament ranked by Elo score
Several candidate prompts run on test cases, judged pairwise in both orders, then ranked by Elo score with reliability warnings.
€14.90or 3 credits - VideoNew
Prompt compression to cut costs
Shorten a long context two to five times before sending it to the model, and measure lost facts and quality before adopting the compression.
€14.90or 3 credits - VideoNew
LivePortrait: transfer your own expressions to a character
Shoot a clean driving video, check and crop it, then animate a portrait or a pet with LivePortrait locally.
€12.90or 3 credits