Skill reviews

Zoho CRM API integration with managed OAuth. Manage leads, contacts, accounts, deals, and other CRM records. Use this skill when users want to read, create, update, or delete CRM r

• References files that are not bundled: references/<source>/triggers.md, references/{source}/triggers.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill

Notion API integration with managed OAuth. Query databases, search pages, and read workspace content. Write operations require explicit user confirmation of the target resource and

• References files that are not bundled: references/<source>/triggers.md, references/{source}/triggers.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 16 top-level sections: this looks like several domains in one skill

Polis Protocol: A Self-Optimizing City of Agents

• References files that are not bundled: references/troubleshooting.md, references/protocol-spec.md, references/templates.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 16 top-level sections: this looks like several domains in one skill

Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting. Use when shipping any feature that runs in production an

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Implement Conversational Language Understanding (CLU) using the azure-ai-language-conversations Python SDK. Use when working with ConversationAnalysisClient to analyze conversation

• The response is described with custom markup (3 tags): a typed call is more reliable
• Does not say what the result is
• No condition that starts the skill

Diagnoses pipeline performance issues -- slow jobs, expensive queries, latency trends -- using Monte Carlo's cross-platform observability. Uses a tiered investigation approach: dis

• References files that are not bundled: references/investigation-tiers.md, references/query-analysis.md
• 2 referenced file(s) missing: references/investigation-tiers.md, references/query-analysis.md
• Does not say what the result is

Analyze a warehouse for stale, unused, or redundant tables via the analyze_storage_costs MCP tool. Classifies waste patterns and table categories, computes safety tiers, and handle

• References files that are not bundled: references/output-structure.md
• The response is described with custom markup (3 tags): a typed call is more reliable
• 1 referenced file(s) missing: references/output-structure.md

Lightweight Google Calendar integration with standalone OAuth authentication. No MCP server required.

• References files that are not bundled: scripts/gcal.py
• 1 referenced file(s) missing: scripts/gcal.py
• No condition that starts the skill

Investigate data incidents and find root causes using Monte Carlo's observability data. Guides the agent through systematic investigation: alert lookup, lineage tracing, ETL checks

• References files that are not bundled: references/<type>-investigation.md, references/data-exploration.md, references/intake-no-incident.md
• 10 referenced file(s) missing: references/<type>-investigation.md, references/data-exploration.md, references/intake-no-incident.md
• Does not say what the result is

Analyze data coverage, create monitors for warehouse tables and AI agents. Covers coverage gaps, use-case analysis, data monitor creation, and agent observability.

• References files that are not bundled: references/data-monitor-creation.md, references/agent-monitor-creation.md, references/data-*.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill

Build comprehensive 3-5 year financial models with revenue projections, cost structures, cash flow analysis, and scenario planning for early-stage startups.

• References files that are not bundled: references/model-templates.md, references/unit-economics.md, references/fundraising-scenarios.md
• 14 top-level sections: this looks like several domains in one skill
• 6 referenced file(s) missing: references/model-templates.md, references/unit-economics.md, references/fundraising-scenarios.md

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel

• 14 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you n

• References files that are not bundled: references/definition-of-done.md
• 11 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: references/definition-of-done.md

Train or fine-tune SentenceTransformer, CrossEncoder, and SparseEncoder models for retrieval, similarity, clustering, classification, reranking, and related embedding tasks.

• References files that are not bundled: scripts/train_<type>_example.py, scripts/train_sentence_transformer_<matryoshka|multi_dataset|with_lora|distillation|make_multilingual|static_embedding>_example.py, scripts/train_cross_encoder_<distillation|listwise>_example.py
• The skill ranks results itself: that belongs to the system behind the tool, not the model
• The response is described with custom markup (4 tags): a typed call is more reliable

Instrument browser/web apps with the Application Insights JavaScript SDK (@microsoft/applicationinsights-web).

• 25 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Architecture patterns for multi-stage CI/CD pipelines with approval gates and deployment strategies.

• References files that are not bundled: assets/approval-gate-template.yml, references/pipeline-orchestration.md
• 14 top-level sections: this looks like several domains in one skill
• 2 referenced file(s) missing: assets/approval-gate-template.yml, references/pipeline-orchestration.md

Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when

• References files that are not bundled: references/definition-of-done.md
• 12 top-level sections: this looks like several domains in one skill
• 1 referenced file(s) missing: references/definition-of-done.md

Manage Mailtrap contacts, lists, segments, custom fields, imports, CRM syncs, and campaign audiences through the UI or API.

• 10 top-level sections: this looks like several domains in one skill
• Does not say what the result is
• No condition that starts the skill

Expert guide for pushing metadata, lineage, and query logs to Monte Carlo from any data warehouse.

• References files that are not bundled: scripts/templates/<warehouse>/
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 18 top-level sections: this looks like several domains in one skill

AI-powered browser automation — navigate sites, fill forms, extract structured data, log in with stored credentials, and build reusable workflows.

• References files that are not bundled: references/prompt-writing.md, references/engines.md, references/schemas.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 top-level sections: this looks like several domains in one skill

Your purpose is now is to create reusable command line scripts and utilities for using the Hugging Face API, allowing chaining, piping and intermediate processing where helpful. Yo

• References files that are not bundled: references/hf_model_papers_auth.sh, references/find_models_by_paper.sh, references/hf_model_card_frontmatter.sh
• 7 referenced file(s) missing: references/hf_model_papers_auth.sh, references/find_models_by_paper.sh, references/hf_model_card_frontmatter.sh
• No condition that starts the skill

Reference document for monopoly scale-benchmarks.

• Does not say what the result is
• No condition that starts the skill

Designs composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework

• References files that are not bundled: references/interfaces.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill ranks results itself: that belongs to the system behind the tool, not the model

CRITICAL: Use for Matrix SDK integration with Makepad. Triggers on: Matrix SDK, sliding sync, MatrixRequest, timeline, matrix-sdk, matrix client, robrix, matrix room, Matrix 集成, 聊天

• References files that are not bundled: references/matrix-client.md, references/timeline-handling.md, references/moly-api-integration.md
• 10 top-level sections: this looks like several domains in one skill
• 3 referenced file(s) missing: references/matrix-client.md, references/timeline-handling.md, references/moly-api-integration.md

Build a minimal but real security policy for sensitive apps. The output is a single, coherent Blue Book document using MUST/SHOULD/CAN language, with explicit assumptions, scope, a

• References files that are not bundled: references/bluebook_template.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 1 referenced file(s) missing: references/bluebook_template.md