Skip to content
Skills Library
Programming · Analysis

debug

/debug

This skill should be used when the user runs /touchdesigner:debug or asks to debug, investigate, or find TouchDesigner node errors — trigger phrases include "debug my TouchDesigner project", "why is this node broken", "find errors in TD", "investigate node errors", "what's wrong with /project1/geo1", or "fix this TouchDesigner error".

Licence
MIT
Last repository change
12.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 12.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

This skill should be used when the user runs /touchdesigner:debug or asks to debug, investigate, or find TouchDesigner node errors — trigger phrases include "debug my TouchDesigner project", "why is this node broken", "find errors in TD", "investigate node errors", "what's wrong with /project1/geo1", or "fix this TouchDesigner error".

Triggers from the description

debug my TouchDesigner projectwhy is this node brokenfind errors in TDinvestigate node errorswhat, or
Original author description

This skill should be used when the user runs /touchdesigner:debug or asks to debug, investigate, or find TouchDesigner node errors — trigger phrases include "debug my TouchDesigner project", "why is this node broken", "find errors in TD", "investigate node errors", "what's wrong with /project1/geo1", or "fix this TouchDesigner error".

How it works

  1. Client integration
  2. Workflow
  3. Failure handling
Original SKILL.md headings · 45 lines, 1,066 words
SKILL.md preview
---
description: This skill should be used when the user runs /touchdesigner:debug
  or asks to debug, investigate, or find TouchDesigner node errors — trigger
  phrases include "debug my TouchDesigner project", "why is this node broken",
  "find errors in TD", "investigate node errors", "what's wrong with
  /project1/geo1", or "fix this TouchDesigner error".
name: debug
---

## Client integration

Use the connected TouchDesigner server's tools by logical name; discover the actual client namespace instead of constructing a Claude tool prefix. Slash-command examples also work as natural-language requests for the named skill. After any network mutation, read back affected parameters, check `get_td_node_errors`, and inspect `get_top_image` for TOP output when relevant. Do not rely on a post-tool hook to remind you.

# TD Debug

Systematically investigate TouchDesigner node errors within a scope, classify each one, and propose fixes.

## Workflow

1. Resolve the scope to inspect: use the `node-path` argument if the user supplied one; otherwise default to `/project1` if it exists, else `/` (a project launched by opening the tox as a document has no `/project1` — the component sits at the root). If neither is available and the default seems wrong for the user's project (e.g. they referenced a specific component earlier), ask which path to scope to before continuing.

2. Optionally call `get_td_info` first if connectivity hasn't been confirmed this session — if it fails, stop and point the user at `/touchdesigner:setup` rather than proceeding against a dead connection.

3. Call `get_td_node_errors` with `nodePath` set to the resolved scope. This tool requires a `nodePath` but aggregates errors from that node **and all of its descendants**, so one call against `/project1` (or whatever scope was resolved) covers the whole subtree — there's no need to call it once per node.

4. Read the report as it is actually rendered, and decide what it licenses you to say. By default it comes back as markdown rather than the raw schema: a `## Node <path>` heading, an `- Errors: N · Warnings: M` line, and — when there is anything to list — a table whose rows are `| Level | Node | Type | Message |`, warnings included. Three things follow from that shape:

   - **Warnings are findings, not noise.** A missing file, a dangling operator reference and a shader that will not compile are all reported as warnings rather than errors, so a `warning` row is usually the answer rather than a footnote to it.
   - **`_No errors or warnings reported._` is the only all-clear.** That sentence is withheld whenever a message stream could not be read, the warning stream was never inspected (an older `mcp_webserver_base.tox`, predating warning collection), or the reported counts disagree with the rows returned — those cases print a `> ⚠️` blockquote instead. An empty table *without* that sentence is a scope that could not be fully seen, not a clean one. Say which of the two it was rather than reporting both as "no errors".
   - **Even a genuine all-clear is not proof the node cooked.** This tool reads the operator error and warning streams only. An exception raised inside a Script OP callback — a `scriptCHOP`'s `onCook`, an Execute DAT's callback — lands on neither stream and is reported nowhere here, producing exactly the same empty report as a healthy node.

   So: if the report is clean and the user described no specific symptom, say so, and suggest widening or narrowing the scope. If the report is clean but the user pointed at a concrete misbehaviour, do **not** stop there — carry on from step 6 against the operator they named, and when it is a Script OP or an Execute DAT, probe the callback directly with `execute_python_script` (read the DAT's text, then `op(path).cook(force=True)` and print what comes back) rather than trusting the empty report.

   Pass `responseFormat: "json"` when the raw `hasErrors` / `errors[]` / `hasWarnings` / `warnings[]` fields are actually needed; `detailLevel: "detailed"` returns YAML rather than markdown.

5. Otherwise iterate the reported entries. Each table row carries `level` (`error` or `warning`), `nodePath`, `opType`, and `message`; `nodeName` appears only in the JSON form. For a large error set, triage rather than processing every entry one by one: group by `opType` and by similar `message` text, and prioritize distinct root causes over duplicate symptoms.

6. For each distinct errored node (or a representative of a group), call `get_td_node_parameters` with that node's `nodePath` to inspect its current parameter values.

7. Inspect upstream context with `get_td_nodes` (`parentPath` set to the errored node's parent, plus `pattern: ""` — the default `"*"` returns that parent's entire subtree rather than just its direct children) to see sibling/input nodes feeding it, using naming and `opType` as a proxy for likely wiring since this tool does not report connections directly. When the error message or parameter values don't make the root cause clear enough this way, use `execute_python_script` for deeper probing (e.g. reading `op(path).inputs` or a DAT's script text) — this call may prompt for permission; that's expected, not a bug.

8. Classify each distinct error using the message text and the context gathered so far, into one of: **missing input** (message references no/disconnected input), **bad parameter or expression** (parameter or expression syntax/evaluation failure), **file not found** (a file-based TOP/DAT/SOP path doesn't resolve), **script error** (a DAT's Python/GLSL raised an exception), **callback exception** (a Script OP or Execute DAT callback failed — reached through the probe in step 4, never through the error report, which cannot see it), or **other/unclassified** when none fit.

9. Propose a concrete fix per classified error (e.g. connect the missing input, correct the parameter value or expression, fix the file path, fix the script). Present these as a list before touching anything.

10. Apply fixes only with explicit user consent, one at a time, using whichever tool fits (`update_td_node_parameters`, `create_td_node`, `exec_node_method`, or `execute_python_script`) — each of these may prompt for permission. Do not batch-apply without confirming each change.

11. After applying any fix, re-run `get_td_node_errors` on the same scope to verify the error is actually gone rather than assuming the fix worked — except for a **callback exception**, which never appeared in that report and so cannot disappear from it. Verify that one the way it was found: re-run the `execute_python_script` probe and check the callback now returns what it should.

## Failure handling

If `get_td_node_errors` itself fails (connection lost, invalid path), report the raw error and suggest `/touchdesigner:setup` or ask for a corrected path — don't fabricate an error report. If the user declines to apply a proposed fix, leave the node untouched and report the diagnosis as the final output. If a fix is applied but the re-check still shows the same error, say so plainly and reconsider the classification rather than repeating the same fix.

Versions

RepositoryScoreLicence
This page · 8beeeaaat/touchdesigner-mcp100MIT
ericrisco/rsc-harness100MIT
nicsuzor/academicops100MIT
duronext/jig100MIT
drosam/agents100MIT
rizukirr/vibekit100MIT
DingyangLyu/MatClaw100Apache-2.0
Kanevry/session-orchestrator100MIT
kdlbs/kandev100AGPL-3.0

Database snapshot: 13.11.2026 · package version 95e97410bf00 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100setup
    This skill should be used when the user runs /touchdesigner:setup or asks to verify, check, fix, or set up the TouchDesigner connection — trigger phrases include "check my TD connection", "is TouchDesigner connected", "set up touchdesigner-mcp", "TD isn't responding", "fix the…
  • 90overview
    This skill should be used when the user runs /touchdesigner:overview or asks for a project structure report, hierarchy summary, or health check of a TouchDesigner project — trigger phrases include "give me an overview of this TD project", "summarize the project structure",…
  • 100popx-touchdesigner
    Local POPX knowledge base and workflow for TouchDesigner. Use when the user mentions POPX, popsextension, POPX examples, POPX operators, or wants to build, inspect, explain, debug, or modify POPX-based setups in TouchDesigner using the bundled POPX reference corpus and live…
  • 90tdpilot-brain-explorer
    Use when investigating an unfamiliar TouchDesigner project, target root, selected nodes, errors, operator availability, or planning context.
  • 100verify-and-fix
    This skill should be used when the user reports an error, bug, or unexpected behavior and wants it diagnosed and fixed. Trigger on phrases like "check this error", "check this bug", "here's an error", "here's a bug", "I have an error", "I have a bug", "found a bug", "got an…
  • 81shadow-debug
    Diagnose and fix a reported failure using a reproducible symptom, a focused cause investigation, and regression verification. Use for broken behavior, errors, crashes, or failing checks.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.