microsoft/cat-agent-skills is a static website that catalogs reusable instruction sets and related packages for AI agents. People use it to search, filter, rate, and download skills for Cowork, Copilot Studio, and Scout, along with Copilot plugins and Scout automations. The catalogue entries are the skills, instructions, plugins, and settings displayed by the site.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add microsoft/cat-agent-skills --skill lab-column-mappergit clone --depth 1 https://github.com/microsoft/cat-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/microsoft/cat-agent-skills/lab-column-mapper)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/lab-column-mapper"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/lab-column-mapper/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/lab-column-mapper"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/lab-column-mapper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 111 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00133 | $0.01610 |
| Opus 5.5 | $0.00053 | $0.00644 |
| Sonnet 5.5 | $0.00027 | $0.00322 |
| Haiku 4.5 | $0.00013 | $0.00161 |
Grade A, and why
lab-column-mapper scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lab Column Mapper
What this skill does
Given an unknown column from an incoming lab results file, retrieve the most likely canonical destination column from a health system's clinical warehouse, explain why, and write the suggestion to the review queue.
Input payload
The skill is invoked with a JSON payload delivered by Power Automate. Every field is required unless marked optional.
| Field | Type | Description |
|---|---|---|
source_column_name |
string | The unrecognized column header from the incoming file (e.g., PT_MRN, spec_collected_dt). |
source_column_sample_values |
array of strings | Up to 5 sample values, de-identified. Never include raw PHI — the caller must hash or redact patient identifiers before invoking. |
source_lab_id |
string | Stable identifier for the sending lab (e.g., LAB-QUEST-001). |
source_lab_name |
string | Human-readable lab name (e.g., Quest Diagnostics). |
source_file_name |
string | Name of the file that failed ingestion. |
source_domain |
string | One of lab-observations, orders, specimens, results. Used to scope the search. |
pipeline_run_id |
string | ADF pipeline run ID for traceability. |
source_column_description |
string, optional | If the sending lab publishes a data dictionary, the human description of the column. Boosts match confidence significantly when present. |
Retrieval steps
Perform these steps in order. Do not skip to a broader search until the previous scope has been tried.
Step 1 — Same-lab scoped search
Query the Azure AI Search index lab-canonical-schema with:
- Search text:
source_column_name+source_column_description(if present) + a synthesized query from the sample values (e.g., if samples look like dates, add "date time timestamp"; if samples look like numeric with units, add "quantity measurement value"). - Filter:
source_lab_id eq '{source_lab_id}' or previously_mapped_from_labs/any(l: l eq '{source_lab_id}') - Top: 5
- Semantic ranking: on. Use the
column-descriptionssemantic configuration.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 119 lines · 133 tokens per session scan A 6335573951b9
lab-column-mapper is a skill published in the GitHub repository microsoft/cat-agent-skills (93 stars, last pushed today), licensed MIT. It adds 133 tokens to every session and 1,610 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
arboreto
Infers candidate gene regulatory networks from bulk or single-cell expression data using AertsLab Arboreto GRNBoost2 and GENIE3. Use for transcription factor-target association ranking, compatible Dask execution, sparse expression inputs, and network stability checks.
torchdrug
Builds and troubleshoots TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
deepspot-m
Generates transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Used for predicted log1p-CPM expression from 224x224 tiles at about 20x, querying the released protein-coding gene panel by symbol, and whole-slide prediction after resolution-aware tiling with histolab.
pyhealth
Builds and validates PyHealth clinical machine-learning pipelines for EHR, signals, imaging, and medical codes. Use for PyHealth dataset loading, MIMIC-III/IV, eICU or OMOP prediction tasks, patient-level evaluation, mortality/readmission/length-of-stay modeling, medication recommendation, sleep staging, Trainer…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…