New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Catia V5 MCP Maintainer

by daiemon12 in daiemon12/catia-v5-mcp-server

Maintain daiemon12/catia-v5-mcp-server against a production reliability contract.

MITAuto-check passedAgent Workflows

Install Catia V5 MCP Maintainer

skills CLI
$ npx skills add daiemon12/catia-v5-mcp-server --skill catia-v5-mcp-maintainer -a claude-code

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

GitHub CLI
$ gh skill install daiemon12/catia-v5-mcp-server catia-v5-mcp-maintainer --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/daiemon12/catia-v5-mcp-server.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/catia-v5-mcp-maintainer .claude/skills/catia-v5-mcp-maintainer && 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
catia-v5-mcp-maintainer
GitHub stars
114
Token cost
~2.4k tokens
SKILL.md length
1,114 words
Files
7 (incl. references)
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Maintain daiemon12/catia-v5-mcp-server against a production reliability contract.

  • Works in 12 steps: Inspect repository-local schema and… → Keep public schemas truthful: every… → Serialize CATIA COM access through a… → …
  • Changing tool schemas
  • SKILL.md covers Mandatory engineering rules, Reference loading, Source-first change process and Runtime execution contract, plus 11 more sections
  • Needs STALE_TOPOLOGY_TOKEN

What it does

Catia V5 MCP Maintainer is an agent skill from daiemon12/catia-v5-mcp-server. Maintain daiemon12/catia-v5-mcp-server against a production reliability contract. Use when changing tool schemas or implementations, COM execution, session health, structured results, object handles, topology references, recovery, diagnostics, CAA bridge integration, or regression evaluation. Requires source-first changes, truthful schemas, deterministic failure behavior, and live CATIA validation for COM/BRep semantics.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `evals/evals.json`, `references/production-architecture.md` and `references/production-readiness-checklist.md`). Compatibility notes: Python 3.10+; Windows with pywin32 and CATIA V5 for live validation. Source-level tests may run cross-platform when CATIA imports are isolated.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: CATIA V5 MCP Server - Control CATIA V5 with AI via Model Context Protocol. The licence is MIT.

When your agent uses it

  • Changing tool schemas
  • Implementations
  • Structured results
  • Topology references

Example prompts

  • “/catia-v5-mcp-maintainer”

Requirements

  • Python 3
  • A credential in STALE_TOPOLOGY_TOKEN
  • Compatibility (from SKILL.md): Python 3.10+; Windows with pywin32 and CATIA V5 for live validation. Source-level tests may run cross-platform when CATIA imports are isolated.

Workflow steps

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

  1. Inspect repository-local schema and implementation before changing or documenting a tool.
  2. Keep public schemas truthful: every advertised input must be consumed with defined semantics or removed/deprecated.
  3. Serialize CATIA COM access through a dedicated STA execution boundary; do not let arbitrary MCP request threads use shared COM objects…
  4. Return structured results with deterministic success/failure classification. Human-readable text is a secondary representation, not the…
  5. Separate CATIA update success from intended geometry effect.
  6. Give material-changing operations measurable postconditions and explicit no-effect/wrong-effect failures.
  7. Use server-managed handles for document/model objects rather than relying on display names or long mutable paths.
  8. Use generation/version-scoped topology references and reject stale references before mutation.
  9. Provide deterministic recovery for supported reversible operations. Do not depend on localized UI command strings for Undo.
  10. Treat modal dialogs, timeouts, and indeterminate COM completion as session-health events, not ordinary retryable exceptions.
  11. Keep CAA/native access behind typed adapters; do not expose raw native/COM pointers across the MCP boundary.
  12. Do not classify a capability as production-supported until schema tests, failure-path tests, and relevant live CATIA validation pass.

What it can do on your machine

Read from SKILL.md and the folder at commit 3e92601. 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 these keys or tokens, usually read from environment variables:

    • STALE_TOPOLOGY_TOKEN

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

  • Compatibility

    Python 3.10+; Windows with pywin32 and CATIA V5 for live validation. Source-level tests may run cross-platform when CATIA imports are isolated.

    From compatibility in the SKILL.md frontmatter.

Context cost

Catia V5 MCP Maintainer loads about 2.4k tokens when it runs, and up to ~6.6k if it reads all its reference files. Until then it costs about 112 tokens; SKILL.md has 1,114 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~112
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.6k

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 daiemon12/catia-v5-mcp-server at commit 3e92601, republished under its MIT licence (© daiemon12). 1,114 words, ~2,404 tokens.

Download SKILL.mdSave it as .claude/skills/catia-v5-mcp-maintainer/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
catia-v5-mcp-maintainer
description
Maintain daiemon12/catia-v5-mcp-server against a production reliability contract. Use when changing tool schemas or implementations, COM execution, session health, structured results, object handles, topology references, recovery, diagnostics, CAA bridge integration, or regression evaluation. Requires source-first changes, truthful schemas, deterministic failure behavior, and live CATIA validation for COM/BRep semantics.
compatibility
Python 3.10+; Windows with pywin32 and CATIA V5 for live validation. Source-level tests may run cross-platform when CATIA imports are isolated.
metadata.version
1.1.0
metadata.locale
en-US
metadata.target-repository
daiemon12/catia-v5-mcp-server

CATIA V5 MCP Maintainer

Use this skill when changing the target MCP server itself. Production support is a contract between schema, implementation, runtime behavior, diagnostics, recovery, and tests. Tool count alone is not a reliability metric.

Mandatory engineering rules

  1. Inspect repository-local schema and implementation before changing or documenting a tool.
  2. Keep public schemas truthful: every advertised input must be consumed with defined semantics or removed/deprecated.
  3. Serialize CATIA COM access through a dedicated STA execution boundary; do not let arbitrary MCP request threads use shared COM objects directly.
  4. Return structured results with deterministic success/failure classification. Human-readable text is a secondary representation, not the primary protocol.
  5. Separate CATIA update success from intended geometry effect.
  6. Give material-changing operations measurable postconditions and explicit no-effect/wrong-effect failures.
  7. Use server-managed handles for document/model objects rather than relying on display names or long mutable paths.
  8. Use generation/version-scoped topology references and reject stale references before mutation.
  9. Provide deterministic recovery for supported reversible operations. Do not depend on localized UI command strings for Undo.
  10. Treat modal dialogs, timeouts, and indeterminate COM completion as session-health events, not ordinary retryable exceptions.
  11. Keep CAA/native access behind typed adapters; do not expose raw native/COM pointers across the MCP boundary.
  12. Do not classify a capability as production-supported until schema tests, failure-path tests, and relevant live CATIA validation pass.

Reference loading

Read references/repository-contract-gaps.md before modifying an existing tool or capability group.

Read references/production-architecture.md before changing COM/session execution, object lifecycle, recovery, topology, diagnostics, or CAA integration.

Read references/result-contract.md before adding or changing tool outputs/errors.

Read references/test-strategy.md before accepting a behavior change.

Read references/production-readiness-checklist.md when assessing support level across capability groups.

Source-first change process

For each change:

  1. Inspect the exact schema, dispatch path, implementation, and relevant helper functions.
  2. Write the intended behavioral contract: inputs, units, target semantics, preconditions, effects, errors, and recovery metadata.
  3. Add or adjust an offline contract/failure test that can detect the current defect where possible.
  4. Implement the smallest deterministic change that satisfies the contract.
  5. Preserve a public tool name only when backward semantics remain compatible; otherwise version, narrow, or deprecate the contract explicitly.
  6. Add a live CATIA probe for any behavior that mocks cannot establish, especially COM apartment behavior, CATIA API signatures, BRep references, update diagnostics, and modal UI.
  7. Update capability classification only after the implementation and validation evidence agree.

Runtime execution contract

The target runtime should separate asynchronous MCP transport from CATIA execution:

MCP request -> typed validation -> operation orchestrator -> serialized STA worker -> CATIA Automation / optional CAA adapter -> result verification

The worker owns COM initialization and COM object resolution on its own STA thread. Request handlers enqueue logical operations and await structured results.

Do not transfer apartment-bound raw COM objects to request threads. Store logical handles and resolve them on the worker.

Session-health contract

Use explicit session health such as:

  • healthy: CATIA state is known and mutations are allowed;
  • blocked: a known modal/blocked condition prevents safe calls;
  • unknown: call completion or model state cannot be established;
  • disconnected: no active CATIA connection.

A timeout does not prove an in-flight COM call was cancelled. If completion is indeterminate, transition to unknown or blocked and reject further mutations until health and model state are re-established.

Tool contract

Each engineering-intent tool should define:

  • narrow typed inputs;
  • units and enum semantics;
  • deterministic target references;
  • precondition checks;
  • mutation/update behavior;
  • measurable effects;
  • structured data/result fields;
  • typed failure codes;
  • recovery metadata where applicable;
  • tests for success, failure, and no-effect/wrong-effect behavior.

A mutation tool must not return only a phrase such as "created successfully" when design correctness can be measured.

Schema integrity

A schema field is part of the public contract. If implementation ignores an advertised input, choose one of two actions:

  • implement the input semantics and validate them; or
  • remove/deprecate the input and narrow the capability description.

Documentation must not be used to compensate for an ignored runtime input.

Show full SKILL.md (469 more words)Show less

Geometry-effect contract

For a tool expected to add/remove material:

  1. capture pre-operation update/measurement state;
  2. perform the mutation on the STA worker;
  3. update CATIA;
  4. collect post-operation measurement state;
  5. classify effect;
  6. return structured effect metadata.

At minimum support typed outcomes for FEATURE_NO_EFFECT, WRONG_GEOMETRY_EFFECT, and UPDATE_FAILED when applicable.

Object-handle contract

Expose opaque logical handles for session objects such as documents, bodies, sketches, features, and parameters. The handle registry should track owning document/session and object validity.

After document close/reload/session reset, affected handles must fail deterministically, for example with STALE_HANDLE or OBJECT_NOT_FOUND. Never silently rebind a stale handle by display name.

Topology-reference contract

Topology references are server-layer abstractions, not durable native CATIA IDs. Treat the external token format as opaque.

A topology record should include:

  • token;
  • face/edge kind;
  • owning document/body;
  • topology generation/version;
  • geometric descriptors;
  • resolver metadata required to reconstruct an exact CATIA/CAA reference.

Every shape-changing mutation increments or invalidates the topology generation. A token from an older generation must return STALE_TOPOLOGY_TOKEN before feature creation. Never fall back to the same numeric index in a changed topology.

Recovery contract

Use an operation journal or equivalent deterministic recovery record. This is a logical recovery mechanism, not an ACID transaction and not a claim of CATIA-native atomicity.

Record, as applicable:

  • created feature handle and deletion strategy;
  • parameter old/new value;
  • document/model generation before and after;
  • operation group identity for multi-step intent;
  • measurements used to verify rollback.

Rollback must run in reverse order, update CATIA, and verify restoration where measurable.

Modal-dialog contract

Detect/report blocking CATIA modal dialogs around fragile or long-running calls. Auto-close only an explicit allowlist of non-destructive dialogs. Return dialog metadata and session-health impact. Do not invoke arbitrary buttons based on caption similarity.

Diagnostics and CAA

Automation exceptions are insufficient for advanced repair. Expose the deepest available diagnostics without inventing native meaning.

When a CAA bridge is present:

  • keep the bridge behind a typed JSON/Automation boundary;
  • return locale-independent feature types where possible;
  • return native CATIA update diagnostics;
  • provide exact BRep reference helpers for topology-consuming features;
  • preserve lower-layer failure state without re-wrapping it as success.

When a CAA bridge is absent, return the limitation explicitly rather than synthesizing native diagnostic text.

Validation requirement

Offline tests establish schema/orchestration contracts. Live CATIA probes establish actual COM/API/BRep behavior. Agent task evaluations establish end-to-end capability.

All three levels are required before broad production-support claims for features that depend on CATIA runtime semantics.

Acceptance criteria

A production-supporting change is complete only when all applicable conditions hold:

  • schema and implementation semantics agree;
  • structured failure state propagates unchanged across layers;
  • no advertised input is silently ignored;
  • session/thread rules are preserved;
  • stale handles/tokens fail deterministically;
  • update success and geometry-effect success are evaluated separately;
  • success, failure, and no-effect/wrong-effect paths are tested;
  • relevant live CATIA validation passes, or the capability remains explicitly non-production-validated;
  • documentation states the supported contract and limitations without overstating them.

© daiemon12, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (references) in .claude/skills/catia-v5-mcp-maintainer of daiemon12/catia-v5-mcp-server.

  • SKILL.md
  • evals/evals.json
  • references/production-architecture.md
  • references/production-readiness-checklist.md
  • references/repository-contract-gaps.md
  • references/result-contract.md
  • references/test-strategy.md

Open the folder on GitHubat commit 3e92601

Compare with similar skills

Catia V5 MCP Maintainer 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.

Catia V5 MCP Maintainer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Catia V5 MCP Maintainer this skilldaiemon12/catia-v5-mcp-server114—~2.4kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence
Context Mode Output Sandboxmksglu/context-mode26k—~4.1kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Warp GUI to Agent CLI Migration

    warpdotdev/warp

    Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.

    65k GitHub starsUsed in 1 repo~2.1k tokens
    Agent WorkflowsAuto-check passed

More from daiemon12/catia-v5-mcp-server

  • Catia V5 Production Operator

    daiemon12/catia-v5-mcp-server

    Operate CATIA V5 through daiemon12/catia-v5-mcp-server under a conservative production execution contract.

    114 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Catia V5 MCP Maintainer

What does Catia V5 MCP Maintainer do?

Maintain daiemon12/catia-v5-mcp-server against a production reliability contract. Catia V5 MCP Maintainer is an agent skill from daiemon12/catia-v5-mcp-server. Maintain daiemon12/catia-v5-mcp-server against a production reliability contract.

When should I use Catia V5 MCP Maintainer?

Catia V5 MCP Maintainer fits situations like: changing tool schemas; implementations; structured results; topology references.

How do I install Catia V5 MCP Maintainer in Claude Code?

Run `npx skills add daiemon12/catia-v5-mcp-server --skill catia-v5-mcp-maintainer -a claude-code`. Or copy the skill folder (.claude/skills/catia-v5-mcp-maintainer in daiemon12/catia-v5-mcp-server) into .claude/skills/catia-v5-mcp-maintainer in your project. Claude Code loads it when a task matches its description.

How do I install Catia V5 MCP Maintainer in Codex?

Run `npx skills add daiemon12/catia-v5-mcp-server --skill catia-v5-mcp-maintainer -a codex`. Or copy the skill folder (.claude/skills/catia-v5-mcp-maintainer in daiemon12/catia-v5-mcp-server) into .agents/skills/catia-v5-mcp-maintainer in your project. Codex loads it when a task matches its description.

Can I use Catia V5 MCP Maintainer 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 daiemon12/catia-v5-mcp-server --skill catia-v5-mcp-maintainer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/catia-v5-mcp-maintainer, .gemini/skills/catia-v5-mcp-maintainer, .github/skills/catia-v5-mcp-maintainer and .opencode/skills/catia-v5-mcp-maintainer in your project.

What does Catia V5 MCP Maintainer need to run?

Going by SKILL.md and its folder, Catia V5 MCP Maintainer needs credentials named STALE_TOPOLOGY_TOKEN. Our summary lists: Python 3; A credential in STALE_TOPOLOGY_TOKEN. Compatibility (from SKILL.md): Python 3.10+; Windows with pywin32 and CATIA V5 for live validation. Source-level tests may run cross-platform when CATIA imports are isolated..

Does Catia V5 MCP Maintainer 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 Catia V5 MCP Maintainer 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 Catia V5 MCP Maintainer use?

Catia V5 MCP Maintainer 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 Catia V5 MCP Maintainer use?

About 2.4k tokens (SKILL.md is roughly 9.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.2k tokens, read only when the agent opens those files.

What are the alternatives to Catia V5 MCP Maintainer?

Skills that share tags, products or a category with Catia V5 MCP Maintainer: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Crush Configuration (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Catia V5 MCP Maintainer?

daiemon12 (a GitHub user) maintains it in daiemon12/catia-v5-mcp-server, which has 114 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 10, 2026.

Source: daiemon12/catia-v5-mcp-server on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.