resolve-design-errors is a skill in matlab/simulink-agentic-toolkit, last changed 16 Sept 2026. It can name web addresses and include files we can't read.

From the author
Use when asked to run Design Error Detection (quick defect scan), find design errors in a Simulink model, perform root cause analysis on DED findings, fix division-by-zero, overflow, dead logic or out-of-bounds defects detected by SLDV, or diagnose why missing coverage cannot be achieved (dead logic blocking coverage objectives). Do NOT use for requirement verification, test generation, Inf/NaN detection, active logic analysis, or coverage measurement.

At a glance

What it can touch

How much a skill can do, not whether it is risky.

Pattern check

14 items to review

Binary, compiled, archived or document file

R32 · High · scripts/buildDepthLimitedTrace.pand 13 more

Commit ef5d5f8 · 29 Oct 2026

How the check works

Pattern check:14 items to reviewSee them

Install

Each tab says whether it installs commit ef5d5f8, the one we checked, or the latest version.

Read these 14 items before installing, starting with Binary, compiled, archived or document file — scripts/buildDepthLimitedTrace.p

Read SKILL.md first
Licence not identified
Licence
1.3k
Repo stars
Publisher

What it can touch

From the files and frontmatter at commit ef5d5f8. This is how much a skill can do, not whether it is risky.

Pattern check

Pattern check: 14 items to review · commit ef5d5f8 · 29 Oct 2026

Show 4 more

We checked every text file in this skill, at commit ef5d5f8 on 29 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Files we didn't read

  • scripts/buildDepthLimitedTrace.p · binary file
  • scripts/buildSlice.p · binary file
  • scripts/checkEnvironment.p · binary file
  • scripts/classifyDeadLogic.p · binary file
  • scripts/computeReach.p · binary file
  • scripts/defaultConfig.p · binary file
  • scripts/detectCascade.p · binary file
  • scripts/extractFindings.p · binary file
  • scripts/isolateRootCauses.p · binary file
  • scripts/loadSldvResults.p · binary file
Show 4 more
  • scripts/runDesignErrorDetection.p · binary file
  • scripts/sldv_find_de_root_cause.p · binary file
  • scripts/sldv_run_defect_checker.p · binary file
  • scripts/writeReport.p · binary file
  • https://www.mathworks.com/content/dam/mathworks/license/pmrl/license.md

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses with warnings

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • Warning

      metadata values should be text; toolbox_dependencies (a list) is not. The spec's validator turns them into text; other readers may not. O4

      Fix: Quote each value, for example version: "1.0".

    • Note

      The first sentence of the description is 331 characters. Agents shorten long descriptions, so lead with the main job. D8

      Fix: Start with one short sentence that names the job.

  • Claude CodePasses

    Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

    • Note

      The first sentence of the description is 331 characters. Agents shorten long descriptions, so lead with the main job. D8

      Fix: Start with one short sentence that names the job.

  • Claude apps & API uploadPasses

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Note

      The description is 456 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

      Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

    • Note

      metadata values should be text; toolbox_dependencies (a list) is not. The spec defines metadata as text to text. O4

      Fix: Quote each value, for example version: "1.0".

  • OpenAI (Codex & API)Passes with warnings

    Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.

    • Warning

      metadata values should be text; toolbox_dependencies (a list) is not. OpenAI's upload follows the spec's text-to-text rule. O4

      Fix: Quote each value, for example version: "1.0".

    • Note

      The first sentence of the description is 331 characters. Agents shorten long descriptions, so lead with the main job. D8

      Fix: Start with one short sentence that names the job.

  • VS Code & CopilotPasses

SKILL.md

We only show SKILL.md text here when its licence clearly allows it.

Read SKILL.md on GitHub (opens in a new tab)

Files

28 files

PathSize
SKILL.md (opens in a new tab)8.4 KB
assets/design_error_assumption.yaml (opens in a new tab)1.1 KB
assets/design_error_cascading.yaml (opens in a new tab)2.5 KB
assets/design_error_conditionally_executed.yaml (opens in a new tab)1.7 KB
assets/design_error_enable_as_input.yaml (opens in a new tab)1.6 KB
assets/design_error_parameter.yaml (opens in a new tab)2.1 KB
assets/design_error_short_circuit_and.yaml (opens in a new tab)1016 B
assets/design_error_short_circuit_or.yaml (opens in a new tab)953 B
assets/intentional_defensive_logic.yaml (opens in a new tab)2.1 KB
assets/intentional_negation_guard_stateflow.yaml (opens in a new tab)1.7 KB
assets/pattern_catalog.yaml (opens in a new tab)4.5 KB
manifest.yaml (opens in a new tab)843 B
references/api-reference.md (opens in a new tab)3.9 KB
references/fix-strategy.md (opens in a new tab)4 KB
scripts/buildDepthLimitedTrace.p (opens in a new tab)8 KB
scripts/buildSlice.p (opens in a new tab)7.2 KB
scripts/checkEnvironment.p (opens in a new tab)3.8 KB
scripts/classifyDeadLogic.p (opens in a new tab)4.6 KB
scripts/computeReach.p (opens in a new tab)2.8 KB
scripts/defaultConfig.p (opens in a new tab)2 KB
Show 8 more

More from matlab/simulink-agentic-toolkit

SkillWhat it can touchPattern checkLicenceUpdated
  • Runs shell commands
  • Names web addresses
Pattern check: Nothing flaggedNo licence19 Aug 2026
  • Names web addresses
Pattern check: Nothing flaggedNo licence12 Aug 2026
  • Runs shell commands
  • Names web addresses
  • +1 more
Pattern check: Nothing flaggedNo licence21 Oct 2026
  • Runs shell commands
  • Names web addresses
Pattern check: Nothing flaggedNo licence26 Aug 2026
  • Runs shell commands
  • Names web addresses
  • +1 more
Pattern check: 4 items to reviewNo licence16 Sept 2026
  • Names web addresses
Pattern check: Nothing flaggedNo licence26 Aug 2026
All skills in matlab/simulink-agentic-toolkit

Other Testing & QA skills

Same category, most repo stars first.

SkillWhat it can touchPattern checkLicenceUpdated
finishing-a-development-branchUse when implementation is complete, all tests pass, and you need to decide how to integrate the work

obra/superpowers

  • Runs shell commands
  • +1 more

Pattern check: Nothing flaggedMITUpdated 12 Aug 2026

  • Runs shell commands
  • Reaches the network
Pattern check: Nothing flaggedMIT12 Aug 2026
systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes

obra/superpowers

  • Runs shell commands
  • +1 more

Pattern check: Nothing flaggedMITUpdated 9 Oct 2026

  • Runs shell commands
  • Bundles scripts
Pattern check: Nothing flaggedMIT9 Oct 2026
  • Runs shell commands
  • Reaches the network
Pattern check: Nothing flaggedMIT10 Oct 2026
  • Instructions only
Pattern check: Nothing flaggedMIT11 Aug 2026
  • Runs shell commands
  • Reaches the network
  • +2 more
Pattern check: Nothing flaggedApache 2.020 Apr 2026
  • Instructions only
Pattern check: Nothing flaggedMIT8 Oct 2026