Tous les skills

Helps a Marketing Manager review anonymous synthetic abandonment patterns without contacting shoppers.

Compare synthetic acceleration options and clearly separate scenario value from forecast commitments.

Use this skill whenever the user asks to check, review, or fix the accessibility of a PowerPoint deck, Word document, HTML page, or Markdow…

Create a synthetic Acme account overview and identify evidence that merits seller attention.

Draft reviewable action plans for the synthetic stalled deals; do not assign tasks.

Summarize findings and candidate next steps without activating programs or approvals.

Adds Azure DevOps connector to a Power Apps code app. Use when querying work items, creating bugs, managing pipelines, or making ADO API ca…

Guide the user to add a data source, connection, or API connector to a Canvas App via Power Apps Studio, then verify and continue. USE WHEN…

Adds Excel Online (Business) connector to a Power Apps code app. Use when reading or writing Excel workbook data from OneDrive or SharePoin…

Adds Microsoft Copilot Studio connector to a Power Apps code app. Use when invoking Copilot Studio agents, sending prompts to agents, or in…

Add a new TRF rule to the mlinter. Checks for duplicates, creates the rule module and TOML entry, runs against all models, and handles viol…

Adds OneDrive for Business connector to a Power Apps code app. Use when uploading, downloading, listing, or managing files in OneDrive.

Fixes broken typing checks detected by ty, make typing, or make check-repo. Use when typing errors appear in local runs, CI, or PR logs.

Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams ch…

Adds Work IQ (M365 Copilot Search) to a Power Apps code app via the Work IQ Copilot MCP connector (shared_a365copilotchatmcp), then wires u…

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discip…

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metr…

Use this skill whenever the user wants to evaluate, test, or validate an AI agent, decide whether an agent is ready to ship or go live, cho…

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

Neutral arbiter for merge conflicts between two agents.

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

Use when an agent needs AgentMail CLI email inboxes.

Builds a scenario-driven content pack for a Microsoft 365 Copilot customer demo. From a customer name, line of business, and target persona…

Engineering operating model for teams where AI agents generate a large share of implementation output.

Facilitates a zero-based AI-first process redesign session that helps a team reimagine an existing work process as AI-first. Guides them th…

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check work…

When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user…

Use for exact backup names, lead times, synthetic qualification states, premiums, modeled diversification cost, and procurement-review lang…

Use when staff want to reduce status calls by drafting specific synthetic updates for every open applicant, prioritized by overdue and corr…

Use when a Environmental Counsel asks to track existing applications without filing or amendment.

Use when a department approver asks which authorization threshold applies to a request.

Use when a Reliability Engineer asks to triage condition scores without making a safety determination.

Use when a Assistance Coordinator asks to perform preliminary, non-binding program screening.

Use when a Internal Auditor asks to triage audit evidence without predicting outcomes.

Use when HR operations needs a concise fictional profile summary without estimating compensation or deciding eligibility.

Use when a Customer Service Representative asks to provide a read-only account explanation.

Use when a Finance Business Partner asks to prepare a non-binding maintenance budget estimate.

Use when a Sustainability Lead asks to prepare an offset due-diligence shortlist.

Use for who may trade, lapsed or upcoming certifications, supervisor escalation, and training-session planning.