matlab-engineer-tabular-features

matlab/matlab-agentic-toolkit Data & analytics AI & ML engineering

matlab-engineer-tabular-features is a skill in matlab/matlab-agentic-toolkit, last changed 10 Sept 2026. It can run shell commands, name web addresses, bundle scripts and include files we can't read.

From the author

Use when engineering or selecting the best features for single-response classification or regression in MATLAB, whatever the data's modality — for non-tabular data it routes extraction to a domain skill, then selects, assesses, and delivers on the resulting table. Not for multi-response problems, model training, or raw data acquisition.

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

Pattern check

8 items to review

Binary, compiled, archived or document file

R32 · High · scripts/expandBlockMap.p and 7 more

Commit 032b4b6 · 3 Nov 2026

How the check works

Pattern check:8 items to reviewSee them

Install

Each tab says whether it installs commit 032b4b6, the one we checked, or the latest version.

OpenCode also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Goose also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Windsurf (Devin Desktop) also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Zed also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Roo Code also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Factory Droid also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Junie also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Amp also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

No install command here reaches Kiro. Copy the skill's folder into .kiro/skills/ in your project, or ~/.kiro/skills/ for all your projects. matlab/matlab-agentic-toolkit/skills-catalog/ai-and-statistics/matlab-engineer-tabular-features (opens in a new tab)

Antigravity also looks in .agents/skills/, so the Any agent steps reach it with This project. For All projects, see where Antigravity looks.

Cline also looks in .claude/skills/, so the Claude Code steps reach it with This project. For All projects, see where Cline looks.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie and Amp. With This project, Any agent also reaches Antigravity and Claude Code reaches Cline. Kiro needs the folder copied by hand.

Read these 8 items before installing, starting with Binary, compiled, archived or document file — scripts/expandBlockMap.p

Pinned to commit 032b4b6, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/matlab/matlab-agentic-toolkit.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 032b4b605999b1f4adecaac1efa1c9faad41adf6 &&git -C "$tmp" sparse-checkout set -- skills-catalog/ai-and-statistics/matlab-engineer-tabular-features &&git -C "$tmp" checkout -q 032b4b605999b1f4adecaac1efa1c9faad41adf6 &&mkdir -p .claude/skills &&mkdir .claude/skills/matlab-engineer-tabular-features &&cp -R "$tmp"/skills-catalog/ai-and-statistics/matlab-engineer-tabular-features/. .claude/skills/matlab-engineer-tabular-features/ &&rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Or install the ai-and-statistics plugin it ships in. Installs the latest version, not the one we checked. Installs everything in the plugin, including any hooks, MCP servers and scripts our check doesn't cover.

claude plugin marketplace add matlab/matlab-agentic-toolkit --scope project &&claude plugin install ai-and-statistics@matlab-agentic-toolkit --scope project

Claude Code docs

Pinned to commit 032b4b6, the one we checked.

Skills in the Claude apps belong to your account rather than to a project.

Make matlab-engineer-tabular-features.zip, with the skill folder at the top level:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/matlab/matlab-agentic-toolkit.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 032b4b605999b1f4adecaac1efa1c9faad41adf6 &&git -C "$tmp" sparse-checkout set -- skills-catalog/ai-and-statistics/matlab-engineer-tabular-features &&git -C "$tmp" checkout -q 032b4b605999b1f4adecaac1efa1c9faad41adf6 &&out="$(mktemp -d)" &&cp -R "$tmp"/skills-catalog/ai-and-statistics/matlab-engineer-tabular-features "$out"/matlab-engineer-tabular-features &&(cd "$out" && zip -qr - matlab-engineer-tabular-features) > matlab-engineer-tabular-features.zip &&rm -rf "$tmp" "$out"

In Claude, open Customize > Skills, select +, then + Create skill > Upload a skill, and choose matlab-engineer-tabular-features.zip.

On Free, Pro and Max plans, turn on Code execution and file creation (Create and edit files in newer settings) under Settings > Capabilities.

Claude apps docs

Pinned to commit 032b4b6, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/matlab/matlab-agentic-toolkit.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 032b4b605999b1f4adecaac1efa1c9faad41adf6 &&git -C "$tmp" sparse-checkout set -- skills-catalog/ai-and-statistics/matlab-engineer-tabular-features &&git -C "$tmp" checkout -q 032b4b605999b1f4adecaac1efa1c9faad41adf6 &&mkdir -p .agents/skills &&mkdir .agents/skills/matlab-engineer-tabular-features &&cp -R "$tmp"/skills-catalog/ai-and-statistics/matlab-engineer-tabular-features/. .agents/skills/matlab-engineer-tabular-features/ &&rm -rf "$tmp"

Codex picks up new skills on its own; restart it if this one does not appear.

Codex docs

Pinned to commit 032b4b6, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/matlab/matlab-agentic-toolkit.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 032b4b605999b1f4adecaac1efa1c9faad41adf6 &&git -C "$tmp" sparse-checkout set -- skills-catalog/ai-and-statistics/matlab-engineer-tabular-features &&git -C "$tmp" checkout -q 032b4b605999b1f4adecaac1efa1c9faad41adf6 &&mkdir -p .cursor/skills &&mkdir .cursor/skills/matlab-engineer-tabular-features &&cp -R "$tmp"/skills-catalog/ai-and-statistics/matlab-engineer-tabular-features/. .cursor/skills/matlab-engineer-tabular-features/ &&rm -rf "$tmp"

Cursor docs

Pinned to commit 032b4b6, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/matlab/matlab-agentic-toolkit.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 032b4b605999b1f4adecaac1efa1c9faad41adf6 &&git -C "$tmp" sparse-checkout set -- skills-catalog/ai-and-statistics/matlab-engineer-tabular-features &&git -C "$tmp" checkout -q 032b4b605999b1f4adecaac1efa1c9faad41adf6 &&mkdir -p .github/skills &&mkdir .github/skills/matlab-engineer-tabular-features &&cp -R "$tmp"/skills-catalog/ai-and-statistics/matlab-engineer-tabular-features/. .github/skills/matlab-engineer-tabular-features/ &&rm -rf "$tmp"

In a running Copilot CLI session, run /skills reload.

Or install it with gh skill, which also installs the commit we checked. Needs GitHub CLI 2.90 or later.

gh skill install matlab/matlab-agentic-toolkit skills-catalog/ai-and-statistics/matlab-engineer-tabular-features/SKILL.md@032b4b605999b1f4adecaac1efa1c9faad41adf6 --agent github-copilot --scope project

Copilot & VS Code docs

Pinned to commit 032b4b6, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/matlab/matlab-agentic-toolkit.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 032b4b605999b1f4adecaac1efa1c9faad41adf6 &&git -C "$tmp" sparse-checkout set -- skills-catalog/ai-and-statistics/matlab-engineer-tabular-features &&git -C "$tmp" checkout -q 032b4b605999b1f4adecaac1efa1c9faad41adf6 &&mkdir -p .gemini/skills &&mkdir .gemini/skills/matlab-engineer-tabular-features &&cp -R "$tmp"/skills-catalog/ai-and-statistics/matlab-engineer-tabular-features/. .gemini/skills/matlab-engineer-tabular-features/ &&rm -rf "$tmp"

In a running session, run /skills reload.

Or use Gemini CLI’s own installer. Installs the latest version, not the one we checked.

gemini skills install https://github.com/matlab/matlab-agentic-toolkit.git --path skills-catalog/ai-and-statistics/matlab-engineer-tabular-features --scope workspace

Gemini CLI docs

Pinned to commit 032b4b6, the one we checked.

OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity read .agents/skills in a project.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/matlab/matlab-agentic-toolkit.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 032b4b605999b1f4adecaac1efa1c9faad41adf6 &&git -C "$tmp" sparse-checkout set -- skills-catalog/ai-and-statistics/matlab-engineer-tabular-features &&git -C "$tmp" checkout -q 032b4b605999b1f4adecaac1efa1c9faad41adf6 &&mkdir -p .agents/skills &&mkdir .agents/skills/matlab-engineer-tabular-features &&cp -R "$tmp"/skills-catalog/ai-and-statistics/matlab-engineer-tabular-features/. .agents/skills/matlab-engineer-tabular-features/ &&rm -rf "$tmp"

Or use the skills CLI from skills.sh. Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.

npx skills@1.7.4 add matlab/matlab-agentic-toolkit --skill matlab-engineer-tabular-features

Agent Skills docs

Read SKILL.md first

Licence not identified

Licence

1.2k

Repo stars

Folder last changed

Publisher

Files

Checked

3 Nov 2026

What it can touch

From the files and frontmatter at commit 032b4b6. This is how much a skill can do, not whether it is risky.

Runs shell commands
Its instructions or files give the agent commands to run on your computer.
Names web addresses
It mentions outside web addresses the agent may visit. We list them but don't follow them.
Outside links we did not follow
Bundles scripts
The folder holds code files the agent may run.
scripts/buildRecipe.m (opens in a new tab) · scripts/chooseNumBins.m (opens in a new tab) · scripts/macroF1Score.m (opens in a new tab) and 3 more
Includes files we can't read
It ships binaries, archives or documents whose contents this check cannot look inside.
scripts/expandBlockMap.p (opens in a new tab) · scripts/lambdaSequence.p (opens in a new tab) · scripts/lassoFeatureRanking.p (opens in a new tab) and 5 more

Pattern check

Pattern check: 8 items to review · commit 032b4b6 · 3 Nov 2026

R32 · HighBinary, compiled, archived or document file
scripts/expandBlockMap.p (opens in a new tab)
R32 · HighBinary, compiled, archived or document file
scripts/lambdaSequence.p (opens in a new tab)
R32 · HighBinary, compiled, archived or document file
scripts/lassoFeatureRanking.p (opens in a new tab)
R32 · HighBinary, compiled, archived or document file
scripts/mrmrFeatureRanking.p (opens in a new tab)
R32 · HighBinary, compiled, archived or document file
scripts/mutualInformationPanel.p (opens in a new tab)
R32 · HighBinary, compiled, archived or document file
scripts/ncaFeatureRanking.p (opens in a new tab)
R32 · HighBinary, compiled, archived or document file
scripts/oobFeatureRanking.p (opens in a new tab)
R32 · HighBinary, compiled, archived or document file
scripts/scoreFeaturePanel.p (opens in a new tab)

We checked every text file in this skill, at commit 032b4b6 on 3 Nov 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 works Report an incorrect finding

Files we didn't read

scripts/expandBlockMap.p · binary file
scripts/lambdaSequence.p · binary file
scripts/lassoFeatureRanking.p · binary file
scripts/mrmrFeatureRanking.p · binary file
scripts/mutualInformationPanel.p · binary file
scripts/ncaFeatureRanking.p · binary file
scripts/oobFeatureRanking.p · binary file
scripts/scoreFeaturePanel.p · binary file

Outside links we did not follow

https://www.mathworks.com/content/dam/mathworks/license/pmrl/license.md
https://www.mathworks.com/trademarks
https://jmlr.org/papers/v18/17-514.html

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
The open format from agentskills.io, held to the strictest version of each rule among the agents we check.
- Note
  The first sentence of the description is 264 characters. Agents shorten long descriptions, so lead with the main job. D8
  Fix: Start with one short sentence that names the job.
- Note
  Reference files that SKILL.md doesn't link: references/provider-protocol.md (linked only from references/domain-routing.md) and references/reproduce-pool.md (linked only from references/deliver.md). Anthropic suggests linking every reference file directly from SKILL.md. B4
  Fix: Link each one from SKILL.md and say when to read it.
- Note
  Reference files over 100 lines with no table of contents at the top: references/assess.md (297 lines), references/deliver.md (276 lines), references/domain-routing.md (327 lines), references/feature-pool.md (215 lines), references/intake.md (276 lines) and 5 more. B5
  Fix: Add a short list of the sections at the top of each.
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 264 characters. Agents shorten long descriptions, so lead with the main job. D8
  Fix: Start with one short sentence that names the job.
- Note
  Reference files that SKILL.md doesn't link: references/provider-protocol.md (linked only from references/domain-routing.md) and references/reproduce-pool.md (linked only from references/deliver.md). Anthropic suggests linking every reference file directly from SKILL.md. B4
  Fix: Link each one from SKILL.md and say when to read it.
- Note
  Reference files over 100 lines with no table of contents at the top: references/assess.md (297 lines), references/deliver.md (276 lines), references/domain-routing.md (327 lines), references/feature-pool.md (215 lines), references/intake.md (276 lines) and 5 more. B5
  Fix: Add a short list of the sections at the top of each.
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 338 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
  Reference files that SKILL.md doesn't link: references/provider-protocol.md (linked only from references/domain-routing.md) and references/reproduce-pool.md (linked only from references/deliver.md). Anthropic suggests linking every reference file directly from SKILL.md. B4
  Fix: Link each one from SKILL.md and say when to read it.
- Note
  Reference files over 100 lines with no table of contents at the top: references/assess.md (297 lines), references/deliver.md (276 lines), references/domain-routing.md (327 lines), references/feature-pool.md (215 lines), references/intake.md (276 lines) and 5 more. B5
  Fix: Add a short list of the sections at the top of each.
- Note
  Line 61 names an MCP tool as mcp__matlab__evaluate_matlab_code. For the Claude apps and API, Anthropic's guidance is Server:tool, such as GitHub:create_issue. B7
  Fix: Write it as matlab:evaluate_matlab_code, using the server's own name.
OpenAI (Codex & API)Passes
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.
- Note
  The first sentence of the description is 264 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

Files

63 files

Path	Size
SKILL.md (opens in a new tab)	18.9 KB
manifest.yaml (opens in a new tab)	570 B
references/assess.md (opens in a new tab)	16.7 KB
references/deliver.md (opens in a new tab)	13 KB
references/domain-routing.md (opens in a new tab)	18.1 KB
references/feature-pool.md (opens in a new tab)	10.9 KB
references/intake.md (opens in a new tab)	16.9 KB
references/internal-helpers.md (opens in a new tab)	12.2 KB
references/provider-protocol.md (opens in a new tab)	12.3 KB
references/report.md (opens in a new tab)	9.7 KB
references/reproduce-pool.md (opens in a new tab)	7.1 KB
references/select.md (opens in a new tab)	7.1 KB
scripts/BordaVoter.m (opens in a new tab)	2.3 KB
scripts/ConsensusVoter.m (opens in a new tab)	2.5 KB
scripts/MajorityVoter.m (opens in a new tab)	2 KB
scripts/RRFVoter.m (opens in a new tab)	1.9 KB
scripts/assessGenerationStability.m (opens in a new tab)	11.9 KB
scripts/assessKFold.m (opens in a new tab)	20.6 KB
scripts/assessSelectionStability.m (opens in a new tab)	9.8 KB
scripts/baselineComparison.m (opens in a new tab)	18.9 KB

Show 43 more

Path	Size
scripts/buildRecipe.m (opens in a new tab)	8.2 KB
scripts/chooseNumBins.m (opens in a new tab)	5 KB
scripts/chooseStandardization.m (opens in a new tab)	4.5 KB
scripts/computeNSelect.m (opens in a new tab)	2.9 KB
scripts/createConsensusVoter.m (opens in a new tab)	2.2 KB
scripts/describeFeatures.m (opens in a new tab)	5.1 KB
scripts/expandBlockMap.p (opens in a new tab)	440 B
scripts/featureSetQuality.m (opens in a new tab)	12.3 KB
scripts/generateFeatureReport.m (opens in a new tab)	67.2 KB
scripts/generateFeatureReportPdf.m (opens in a new tab)	64.9 KB
scripts/generateFeatures.m (opens in a new tab)	14.6 KB
scripts/hasReportGenerator.m (opens in a new tab)	630 B
scripts/isDomainRecipe.m (opens in a new tab)	1.4 KB
scripts/isStringEmpty.m (opens in a new tab)	577 B
scripts/lambdaSequence.p (opens in a new tab)	637 B
scripts/lassoFeatureRanking.p (opens in a new tab)	971 B
scripts/macroF1Score.m (opens in a new tab)	931 B
scripts/mrmrFeatureRanking.p (opens in a new tab)	239 B
scripts/mutualInformationPanel.p (opens in a new tab)	1.1 KB
scripts/ncaFeatureRanking.p (opens in a new tab)	464 B
scripts/nogueiraStability.m (opens in a new tab)	3.8 KB
scripts/oobFeatureRanking.p (opens in a new tab)	414 B
scripts/plotSelectionConsensus.m (opens in a new tab)	2.7 KB
scripts/plotSelectionDecision.m (opens in a new tab)	6.3 KB
scripts/plotSelectionStability.m (opens in a new tab)	10.2 KB
scripts/plotValidationBaseline.m (opens in a new tab)	6.1 KB
scripts/printSummary.m (opens in a new tab)	18.3 KB
scripts/profileForSplit.m (opens in a new tab)	6.2 KB
scripts/rankAgreement.m (opens in a new tab)	1.3 KB
scripts/rankFeatures.m (opens in a new tab)	6.2 KB
scripts/reserveHoldoutForUser.m (opens in a new tab)	5.5 KB
scripts/runConsensusSelection.m (opens in a new tab)	9.4 KB
scripts/sampleSkewness.m (opens in a new tab)	600 B
scripts/saveResults.m (opens in a new tab)	2.1 KB
scripts/scoreFeaturePanel.p (opens in a new tab)	1.6 KB
scripts/screenPredictors.m (opens in a new tab)	13.3 KB
scripts/selectFeatures.m (opens in a new tab)	2.3 KB
scripts/splitStrategy.m (opens in a new tab)	5.4 KB
scripts/stratifiedDownsampleRows.m (opens in a new tab)	2.2 KB
scripts/stratifiedSubsampleIndices.m (opens in a new tab)	3.4 KB
scripts/transformFeatures.m (opens in a new tab)	6.1 KB
scripts/validateRecipe.m (opens in a new tab)	12.3 KB
scripts/writeInferenceScript.m (opens in a new tab)	10.5 KB

More from matlab/matlab-agentic-toolkit

Skill	What it can touch	Pattern check	Licence	Updated
matlab-access-datafeedGuide for accessing financial and economic data in MATLAB using the Datafeed Toolbox. Covers Bloomberg (market data via bloomberg/blp/bloombergHypermedia), FRED (Federal Reserve economic data via fredrs), Haver Analytics (economic data via haver/haverdirect/haverview), and LSEG Datastream (historical data via datastreamws). Use when connecting to any of these data providers from MATLAB. Reaches the network +1 more Pattern check: Nothing flaggedNo licenceUpdated 10 Sept 2026	Reaches the network Names web addresses	Pattern check: Nothing flagged	No licence	10 Sept 2026
matlab-add-awgnRead BEFORE writing any code that adds Additive White Gaussian Noise (AWGN) to signals and converts between SNR, Eb/No, Es/No, and per-subcarrier SNR for communications simulations, using awgn(), convertSNR(), berawgn(). The default MATLAB patterns for AWGN (e.g., 'measured' option, manual SNR formulas) produce subtly incorrect results. This skill specifies the correct calling conventions, required function usage, and critical anti-patterns that must be avoided. Names web addresses Pattern check: Nothing flaggedNo licenceUpdated 24 Sept 2026	Names web addresses	Pattern check: Nothing flagged	No licence	24 Sept 2026
matlab-analyze-ams-waveformAnalyze AMS waveform data using Mixed-Signal Blockset utilities: phase noise measurement, clock jitter, anti-aliased resampling, timing measurements, lock time, INL/DNL, ADC/DAC calibration, HSpice import. Use when analyzing time-domain voltage from PLL/VCO/clock simulations, measuring phase noise from variable-step solver output, computing jitter, or resampling non-uniform data. Names web addresses Pattern check: Nothing flaggedNo licenceUpdated 31 Jul 2026	Names web addresses	Pattern check: Nothing flagged	No licence	31 Jul 2026
matlab-analyze-antenna-structuresDesign and analyze electrically large antenna structures using MATLAB Antenna Toolbox. Covers reflector antennas (parabolic, Cassegrain, Gregorian, offset, corner, cylindrical, spherical, custom STL), reflectarrays and reconfigurable intelligent surfaces (RIS), antennas installed on platforms (vehicles, aircraft, ships, satellites), and radar cross section (RCS) analysis. Includes solver selection (MoM-PO, PO, MoM, FMM), mesh control, and GPU acceleration. Use when the user wants to design a dish/reflector antenna, reflectarray, analyze an antenna on a platform, or compute RCS. Names web addresses Pattern check: Nothing flaggedNo licenceUpdated 13 Aug 2026	Names web addresses	Pattern check: Nothing flagged	No licence	13 Aug 2026
matlab-analyze-dataAnalyze data using MATLAB. Use when the task involves tables, timetables, time-series data, numeric arrays, sensor matrices, or gridded data — including but not limited to exploring, row filtering, sorting, cleaning, transforming, aggregating, smoothing, padding, trimming, and answering questions about data. MATLAB provides extensive, easy-to-use built-in functions for these workflows with no additional products required. Runs shell commands +1 more Pattern check: Nothing flaggedNo licenceUpdated 8 Oct 2026	Runs shell commands Names web addresses	Pattern check: Nothing flagged	No licence	8 Oct 2026
matlab-analyze-emS-parameters, insertion loss, fields, currents, mesh control, and solver selection for RF PCB performance validation. TRIGGER: user asks to compute S-parameters, analyze insertion/return loss, extract fields or currents, compare MoM vs FEM, or control mesh for any RF PCB component. Invoke BEFORE writing sparameters() or solver code — API is non-obvious. SKIP: designing or creating components (use the specific matlab-design-pcb-* skill), material/stackup setup only (use matlab-manage-pcb-material), optimization sweeps (use matlab-optimize-pcb-design), PDN/IR-drop analysis (use matlab-analyze-pcb-pdn). Runs shell commands +1 more Pattern check: Nothing flaggedNo licenceUpdated 13 Aug 2026	Runs shell commands Names web addresses	Pattern check: Nothing flagged	No licence	13 Aug 2026

All skills in matlab/matlab-agentic-toolkit

Other Data & analytics skills

Same category, most repo stars first.

Skill	What it can touch	Pattern check	Licence	Updated
change-impactPerform evidence-backed impact analysis before changing code, data, interfaces, or governance documents, then compare the planned impact with the actual diff after implementation. Covers call paths, data and schema, API contracts, tests, documentation, ADRs, deployment, migration, and rollback. Use for cross-module or high-risk changes, database migrations, authentication, public interfaces, blast-radius questions, pre-change checks, and post-implementation alignment. affaan-m/ECC Runs shell commands Pattern check: Nothing flaggedMITUpdated 2 Oct 2026	Runs shell commands	Pattern check: Nothing flagged	MIT	2 Oct 2026
clickhouse-ioClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads. Use when writing ClickHouse schemas or queries, or when an analytical query is too slow. affaan-m/ECC Instructions only Pattern check: Nothing flaggedMITUpdated 11 Aug 2026	Instructions only	Pattern check: Nothing flagged	MIT	11 Aug 2026
healthCode quality dashboard. (gstack) garrytan/gstack Runs shell commands +1 more Pattern check: 1 item to reviewMITUpdated 2 Nov 2026	Runs shell commands Pre-approves tools	Pattern check: 1 item to review	MIT	2 Nov 2026
landing-reportRead-only queue dashboard for workspace-aware ship. (gstack) garrytan/gstack Runs shell commands +2 more Pattern check: 1 item to reviewMITUpdated 2 Nov 2026	Runs shell commands Reaches the network +1 more	Pattern check: 1 item to review	MIT	2 Nov 2026
performance-optimizationOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. addyosmani/agent-skills Runs shell commands Pattern check: Nothing flaggedMITUpdated 23 Oct 2026	Runs shell commands	Pattern check: Nothing flagged	MIT	23 Oct 2026
status-card-queryCreate and maintain agent-authored Paperclip status cards, or compile a prose interest prompt into bounded CompanySearchQuery objects and write the first summary from the assigned Summarizer run. paperclipai/paperclip Runs shell commands +1 more Pattern check: Nothing flaggedMITUpdated 24 Jul 2026	Runs shell commands Reaches the network	Pattern check: Nothing flagged	MIT	24 Jul 2026

At a glance

What it can touch

Pattern check

Install

Claude Code

Claude apps

Codex

Cursor

Copilot & VS Code

Gemini CLI

Any agent

What it can touch

Pattern check

Files we didn't read

Outside links we did not follow

Format check

SKILL.md

Files

More from matlab/matlab-agentic-toolkit

Other Data & analytics skills