Menu
SkillsMP a collecté 12 skills depuis microsoft/MCS-Agent-Builder. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 12 skills collectés sur 12.
Use this skill when the user asks Claude to autonomously test, fix, review, and merge a change end-to-end. Detects which lane(s) changed (frontend / backend / framework / agentspec), spawns relevant verifiers (agentic-test-loop with --require-oracle for…
Langue du texte source : anglais
Use this skill to build an agent in Copilot Studio from a researched agentspec.json. Runs pre-build validation (auth, env, connections, tools, model), then creates the agent, configures instructions, knowledge, tools, model, topics, and publishes. Supports…
Langue du texte source : anglais
Use this skill to test an agent's quality after building or fixing it. Runs eval test sets against a published agent via Direct Line API (default, auto), CopilotStudio SDK, Power CAT Kit, or MCS Native Eval (for MCP agents). Results are written per-test to…
Langue du texte source : anglais
Use this skill to fix an agent after eval failures. Classifies root causes (instruction gaps, boundary violations, routing failures, knowledge gaps, scoring issues, decision mismatches), applies targeted fixes via PE and TE, then re-evaluates. Use after…
Langue du texte source : anglais
Use this skill to start a new MCS agent project. Creates the folder structure in Build-Guides/, copies template files, and detects the intake path (SDR documents, wizard, or manual). Use when the user says 'new project', 'start a build', or provides intake…
Langue du texte source : anglais
Use this skill to autonomously build, evaluate, and fix an MCS agent until it reaches SHIP verdict. Composite of /mcs-build → /mcs-eval → /mcs-fix → re-eval, max 3 fix cycles per agent. Reuses the iterate-orchestrator audit + verdict primitives. Use after…
Langue du texte source : anglais
Use this skill to run the MCS build pipeline verify-fix harness against the canonical kitchen-sink agent. The harness reads back every component from MCS via API, classifies any drift against a fixed taxonomy, and auto-applies fixes for confirmed…
Langue du texte source : anglais
Use this skill to generate an export from agentspec.json without running a build. Produces a single self-contained HTML file with three tabs: Brief (design state), Evaluations (test sets and results), and How-To Guide (step-by-step MCS build instructions).…
Langue du texte source : anglais
Use this skill to research and design an agent before building it. Reads project documents, identifies agents, researches MCS components, scores architecture, writes instructions, and generates eval sets. Use after /mcs-init, when documents change, when the…
Langue du texte source : anglais
Use this skill to detect changes across all external dependencies (knowledge cache, upstream repos, Elevate, eval-guide plugin, MCP servers, om-cli binary, MS Learn docs, Claude Code plugins) and produce a triage board so a human can decide TAKE or REJECT per…
Langue du texte source : anglais
File a bug report or feature suggestion on GitHub via gh CLI. Gathers details conversationally, previews, and creates an issue. Use when the user wants to report a bug or suggest a feature.
Langue du texte source : anglais
Use this skill to pull M365 history about a customer or company before research. Searches emails, meetings, documents, Teams, and people via WorkIQ MCP to compile a customer context file. Use when starting a new project, when the user mentions a customer…
Langue du texte source : anglais