Agent skill

AI Assistant

by AHS12 in AHS12/thoth-blueprint

Safely change the schema AI assistant, cloud or local providers, credentials, context construction, streamed patches, retries, validation, or atomic diagram application.

GPL-3.0Auto-check passed

Install AI Assistant

skills CLI
$ npx skills add AHS12/thoth-blueprint --skill ai-assistant -a claude-code

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

GitHub CLI
$ gh skill install AHS12/thoth-blueprint ai-assistant --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/AHS12/thoth-blueprint.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ai-assistant .claude/skills/ai-assistant && 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
ai-assistant
GitHub stars
626
Token cost
~534 tokens
SKILL.md length
231 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
GPL-3.0

At a glance

Safely change the schema AI assistant, cloud or local providers, credentials, context construction, streamed patches, retries, validation, or atomic diagram application.

  • Works in 7 steps: Preserve the pipeline: provider request… → Never apply raw model output or a… → Resolve references with the existing… → …
  • AI chat and provider work
  • SKILL.md covers Read First, Change Rules and Verification
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

AI Assistant is an agent skill from AHS12/thoth-blueprint. Safely change the schema AI assistant, cloud or local providers, credentials, context construction, streamed patches, retries, validation, or atomic diagram application. Use for AI chat and provider work.

Its SKILL.md is about 530 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Design databases the way you think. Create unlimited schemas, import existing designs, visualize relationships, export to multiple formats, and generate framework migrations… The licence is GPL-3.0.

When your agent uses it

  • AI chat and provider work

Example prompts

  • “/ai-assistant”

Workflow steps

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

  1. Preserve the pipeline: provider request -> streamed response -> parse -> Zod validation -> simulation on a clone -> atomic store commit.
  2. Never apply raw model output or a partially simulated patch. Return an actionable error and leave the current diagram unchanged on failure.
  3. Resolve references with the existing ID/name rules and handle duplicate names deliberately.
  4. Preserve locked diagram and locked zone protections in both direct store actions and AI simulation.
  5. Keep cloud and local providers distinct. Cloud providers receive diagram context; Ollama and LM Studio are intended for local keyless use…
  6. Never log API keys, decrypted credentials, session secrets, or full schema context. Avoid expanding context beyond what the user selected…
  7. Preserve retry and cancellation behavior for transient provider failures without duplicating a committed patch.

What it can do on your machine

Read from SKILL.md and the folder at commit 075e0e3. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

AI Assistant loads about 534 tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 231 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~534

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 passed

The automated check found no risky patterns in SKILL.md.

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 AHS12/thoth-blueprint at commit 075e0e3, republished under its GPL-3.0 licence (© AHS12). 231 words, ~534 tokens.

Download SKILL.mdSave it as .claude/skills/ai-assistant/SKILL.md (or your agent's skills folder).
name
ai-assistant
description
Safely change the schema AI assistant, cloud or local providers, credentials, context construction, streamed patches, retries, validation, or atomic diagram application. Use for AI chat and provider work.

AI Assistant

Read First

  • src/components/AiChatTab.tsx and src/components/AiProvidersDialog.tsx for UI behavior.
  • src/lib/ai/buildDiagramContext.ts for context scope and truncation.
  • src/lib/ai/diagramAssistantInstruction.ts for the model contract.
  • src/lib/ai/diagramPatchSchema.ts and src/lib/ai/diagramPatchJsonSchema.ts for the patch contract.
  • src/lib/ai/simulateAiPatch.ts and src/store/store.ts for validation and commit behavior.
  • src/lib/ai/aiCredentialStorage.ts for credential handling.

Change Rules

  1. Preserve the pipeline: provider request -> streamed response -> parse -> Zod validation -> simulation on a clone -> atomic store commit.
  2. Never apply raw model output or a partially simulated patch. Return an actionable error and leave the current diagram unchanged on failure.
  3. Resolve references with the existing ID/name rules and handle duplicate names deliberately.
  4. Preserve locked diagram and locked zone protections in both direct store actions and AI simulation.
  5. Keep cloud and local providers distinct. Cloud providers receive diagram context; Ollama and LM Studio are intended for local keyless use and may require local CORS configuration.
  6. Never log API keys, decrypted credentials, session secrets, or full schema context. Avoid expanding context beyond what the user selected or the feature requires.
  7. Preserve retry and cancellation behavior for transient provider failures without duplicating a committed patch.

Verification

  • Test valid patches, malformed JSON, schema-invalid operations, simulation failures, duplicate references, locked diagrams, and streamed/retried responses.
  • Verify provider setup does not expose secrets in logs or UI errors.
  • Confirm chat history remains scoped to the selected diagram and persists after reload.
  • Run the standard type-check, lint, and production build gate.

© AHS12, GPL-3.0. 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 .agents/skills/ai-assistant of AHS12/thoth-blueprint.

Open the folder on GitHubat commit 075e0e3

Compare with similar skills

AI Assistant 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.

AI Assistant compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI Assistant this skillAHS12/thoth-blueprint626—~534Automated safety check: PassGPL-3.0
Generic Assistantmastra-ai/mastra29k—~1.1kAutomated safety check: PassCustom licence
Safe PushJetBrains/intellij-community21k—~1.1kAutomated safety check: PassCustom licence
Safe RefactorJuliusBrussee/caveman110k1 repos~177Automated safety check: PassApache-2.0
N8n Docs Assistantn8n-io/n8n207k—~550Automated safety check: PassCustom licence
Safe SQL Executionsupabase/supabase111k—~4.2kAutomated safety check: PassApache-2.0

Similar skills

  • Generic Assistant

    mastra-ai/mastra

    Fallback authoring playbook for building general-purpose personal assistant agents that do not fit a more specific archetype.

    29k GitHub stars~1.1k tokensUpdated today
    Sales & SupportAuto-check passed
  • Safe Push

    JetBrains/intellij-community

    Official

    Push IntelliJ repository changes through the Safe Push workflow.

    21k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Safe Refactor

    JuliusBrussee/caveman

    Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.

    110k GitHub starsUsed in 1 repo~177 tokens
    DevelopmentAuto-check passed
  • Official

    Answers n8n product, setup, credential, node, hosting, API, and usage questions from current n8n docs.

    207k GitHub stars~550 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Safe SQL Execution

    supabase/supabase

    Official

    A skill your agent uses whenever code will build, return, fetch, or execute SQL that runs against a user's real Postgres database — even when the request reads like an ordinary feature or bug fix…

    111k GitHub stars~4.2k tokensUpdated today
    DatabasesAuto-check passed
  • Performing Ot Vulnerability Scanning Safely

    mukul975/Anthropic-Cybersecurity-Skills

    Perform vulnerability scanning in OT/ICS environments safely using passive monitoring, native protocol queries, and carefully controlled active scanning with Tenable OT Security to identify…

    34k GitHub stars~2.9k tokensUpdated 1 mo ago
    SecurityAuto-check passed

More from AHS12/thoth-blueprint

  • Diagram Editor

    AHS12/thoth-blueprint

    Safely change the React Flow database diagram editor, including table, note, zone, relationship, selection, locking, layout, keyboard, and viewport behavior.

    626 GitHub stars~506 tokensUpdated 1 mo ago
    Auto-check passed
  • Import Export

    AHS12/thoth-blueprint

    Change SQL, SQLite worker, DBML, JSON, Mermaid, SVG, or database export/import flows while preserving diagram semantics and round trips.

    626 GitHub stars~499 tokensUpdated 1 mo ago
    Auto-check passed
  • Persistence

    AHS12/thoth-blueprint

    Safely change browser-local persistence, Dexie schemas, store synchronization, backups, trash, restore, or checkpoints.

    626 GitHub stars~463 tokensUpdated 1 mo ago
    Auto-check passed
  • Pwa Release

    AHS12/thoth-blueprint

    Safely change Vite, service-worker, offline fallback, cache, Docker, Vercel, or release-distribution behavior.

    626 GitHub stars~505 tokensUpdated 1 mo ago
    Auto-check passed
  • Migration Codegen

    AHS12/thoth-blueprint

    Change Laravel, TypeORM, or Django migration generation and generated SQL parsing.

    626 GitHub stars~425 tokensUpdated 1 mo ago
    Auto-check passed

Questions about AI Assistant

What does AI Assistant do?

Safely change the schema AI assistant, cloud or local providers, credentials, context construction, streamed patches, retries, validation, or atomic diagram application. AI Assistant is an agent skill from AHS12/thoth-blueprint. Safely change the schema AI assistant, cloud or local providers, credentials, context construction, streamed patches, retries, validation, or atomic diagram application.

When should I use AI Assistant?

AI Assistant fits situations like: AI chat and provider work.

How do I install AI Assistant in Claude Code?

Run `npx skills add AHS12/thoth-blueprint --skill ai-assistant -a claude-code`. Or copy the skill folder (.agents/skills/ai-assistant in AHS12/thoth-blueprint) into .claude/skills/ai-assistant in your project. Claude Code loads it when a task matches its description.

How do I install AI Assistant in Codex?

Run `npx skills add AHS12/thoth-blueprint --skill ai-assistant -a codex`. Or copy the skill folder (.agents/skills/ai-assistant in AHS12/thoth-blueprint) into .agents/skills/ai-assistant in your project. Codex loads it when a task matches its description.

Can I use AI Assistant 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 AHS12/thoth-blueprint --skill ai-assistant -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-assistant, .gemini/skills/ai-assistant, .github/skills/ai-assistant and .opencode/skills/ai-assistant in your project.

What does AI Assistant need to run?

SKILL.md names no scripts, command-line tools or credentials: AI Assistant is instructions for the agent only.

Does AI Assistant access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is AI Assistant safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does AI Assistant use?

AI Assistant is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does AI Assistant use?

About 534 tokens (SKILL.md is roughly 2.1k 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 AI Assistant?

Skills that share tags, products or a category with AI Assistant: Generic Assistant (mastra-ai/mastra, 29k stars), Safe Push (JetBrains/intellij-community, 21k stars), Safe Refactor (JuliusBrussee/caveman, 110k stars) and N8n Docs Assistant (n8n-io/n8n, 207k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Assistant?

AHS12 (a GitHub user) maintains it in AHS12/thoth-blueprint, which has 626 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on August 12, 2026.

Source: AHS12/thoth-blueprint on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.