agentmods.dev

Synaptic-Tuner: Skill for Claude Code

.agents/skills/synthetic-data-generation/SKILL.md

synthetic-data-generation is a skill for Claude Code from ProfSynapse/Synaptic-Tuner. It costs 83 tokens per session (1,132 once invoked), scanned A, original, MIT.

A configuration-based workflow for creating, checking, improving, and exporting synthetic datasets or structured documents. Synthetic data is computer-generated data made to resemble real data without directly using the original records.

In plain words
What is it for?
Use it to write generation scenarios and review rules, run small quality checks, create training datasets, project run sizes and costs, and export accepted results to Markdown.
Why use it?
It provides repeatable settings for generation, quality checks, privacy checks, and selected-row regeneration instead of relying on ad hoc commands.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is ProfSynapse/Synaptic-Tuner's own configuration. It tells Claude Code how to work on Synaptic-Tuner itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Synaptic-Tuner configures →

not rated 28repo changed 22d ago A scan 83 tokens original MIT
View source ↗ ProfSynapse/Synaptic-Tuner
Reuse

Borrowing it

Nothing to install: this file belongs to ProfSynapse/Synaptic-Tuner. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ProfSynapse/Synaptic-Tuner/main/.agents/skills/synthetic-data-generation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ProfSynapse/Synaptic-Tuner

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for synthetic-data-generation

README.md
[![agentmods](https://agentmods.dev/badge/skills/profsynapse/synaptic-tuner/synthetic-data-generation/github.svg)](https://agentmods.dev/skills/profsynapse/synaptic-tuner/synthetic-data-generation)
Your own site
<a href="https://agentmods.dev/skills/profsynapse/synaptic-tuner/synthetic-data-generation"><img src="https://agentmods.dev/badge/skills/profsynapse/synaptic-tuner/synthetic-data-generation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for synthetic-data-generation

Your own site · 80×15
<a href="https://agentmods.dev/skills/profsynapse/synaptic-tuner/synthetic-data-generation"><img src="https://agentmods.dev/badge/skills/profsynapse/synaptic-tuner/synthetic-data-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,132 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.01132
Opus 5.5 $0.00033 $0.00453
Sonnet 5.5 $0.00017 $0.00226
Haiku 4.5 $0.00008 $0.00113

Measured 22d ago against content hash ddf707bf077a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

synthetic-data-generation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/combine_datasets.sh, scripts/dry_run.sh, scripts/jsonl_to_markdown.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/synthetic-data-generation/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Synthetic Data Generation

Use checked-in SynthChat commands and declarative configuration to produce locally admitted, reviewable data. Keep corpus shape, provider routing, prompts, schemas, mappings, and quality policy in caller configuration.

Workflow

  1. Classify the task, then read only the matching route:
    • Generate, improve, validate, sanitize, or inspect CLI options: references/cli-commands.md.
    • Configure providers, models, workers, targets, privacy, or runtime checks: references/settings-config.md.
    • Author or revise scenarios: references/scenario-authoring.md.
    • Author or revise rubrics: references/rubric-authoring.md.
    • Understand generation quality gates, repair loops, privacy, and config-first architecture: references/generation-workflow.md.
    • Collect on-policy student rollouts with a reviewing agent that passes or replaces each turn (agent-as-harness): references/harness-review.md.
    • Regenerate selected rows with checked-in commands: references/targeted-regeneration.md.
    • Project environment rollouts into SFT, KTO, or GRPO data, or pick the validation_group_key for training on them: references/rollout-projection.md.
    • Plan run-size and cost projections: references/rollout-projection.md.
    • Export admitted structured results to Markdown: references/structured-document-export.md.
  2. Before any nontrivial or scaled generation, follow protocols/testing-before-scale.md. You MUST dry-run a small representative sample, inspect the raw and rendered artifacts, and obtain the user's approval before scaling. Treat judge-less runs as explicit plumbing exceptions.
  3. Keep format assumptions in YAML, JSON Schema, rubric text, templates, and explicit mappings. NEVER hardcode a current wrapper, corpus, filename rule, metadata convention, or dataset shape into runtime code for a generation job.
  4. For structured documents, use the checked-in bakeoff lifecycle to generate, collect, locally validate, and judge results. Then use the checked-in exporter lifecycle in order: preflight, dry-run, execute with explicit write authority, verify. NEVER promote staged output into authored locations implicitly.
  5. For the single grounded Markdown recipe, load references/recipes/yaml-frontmatter-markdown.md. Treat its names as placeholders and adapt all schema fields and paths through configuration.
  6. Validate outputs with the command appropriate to the route. Preserve run manifests, usage, local schema failures, judgment dispositions, digests, and review gates. Stop on drift, unsafe paths, collisions, or verification failure.

Read the full file on GitHub · 94 lines

Files

What ships with it

15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 22d ago Changed · +2 lines ddf707bf077a
  2. 23d ago Changed · +21 lines 13e6405f1c3e
  3. 24d ago Changed · +13 lines ec853b02d857
  4. 1mo ago First seen · 58 lines · 83 tokens per session scan A 21db393cc671

Subscribe to this mod's changes

synthetic-data-generation is a skill published in the GitHub repository ProfSynapse/Synaptic-Tuner (28 stars, last pushed 3d ago), licensed MIT. It adds 83 tokens to every session and 1,132 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.

Data and AIDocuments
Related

synthetic-data-generation compared with skills from other repositories

synthetic-data-generation next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
synthetic-data-generationProfSynapse/Synaptic-TunerSkill283d agoMITA83Claude Code
markitdownK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA62Claude Code, Codex
agents-llamaindexdavila7/claude-code-templatesSkill33kyesterdayMITA72Claude Code, Codex
jupyter-notebooksXiaomiMiMo/MiMo-CodeSkill14kyesterdayMITA49Codex
azure-ai-document-intelligence-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA83Claude Code
azure-ai-document-intelligence-tsmicrosoft/skillsSkill3.2kyesterdayMITA47Claude Code
docetlucbepic/docetlSkill4.2k7d agoMITA59Claude Code, Codex