eval-performance
Guide for diagnosing and improving MSBuild project evaluation performance. Only activate in MSBuild/.NET build context. USE FOR: builds slow before any compilation starts, high evaluation time in binlog analysis, expensive glob patterns walking large directories (node_modules, .git, bin/obj), deep import chains (>20 levels), preprocessed output >10K lines indicating heavy evaluation, property functions with file I/O ($([System.IO.File]::ReadAllText(...))), multiple evaluations per project. Covers the 5 MSBuild evaluation phases, glob optimization via DefaultItemExcludes, import chain analysis with /pp preprocessing. DO NOT USE FOR: compilation-time slowness (use build-perf-diagnostics), incremental build issues (use incremental-build), non-MSBuild build systems. INVOKES: binlog MCP server tools (evaluations, evaluation_global_properties, evaluation_properties, imports, properties); falls back to dotnet msbuild -pp:full.xml for preprocessing, /clp:PerformanceSummary.
What this skill does
## MSBuild Evaluation Phases For a comprehensive overview of MSBuild's evaluation and execution model, see [Build process overview](https://learn.microsoft.com/en-us/visualstudio/msbuild/build-process-overview). 1. **Initial properties**: environment variables, global properties, reserved properties 2. **Imports and property evaluation**: process `<Import>`, evaluate `<PropertyGroup>` top-to-bottom 3. **Item definition evaluation**: `<ItemDefinitionGroup>` metadata defaults 4. **Item evaluation**: `<ItemGroup>` with `Include`, `Remove`, `Update`, glob expansion 5. **UsingTask evaluation**: register custom tasks Key insight: evaluation happens BEFORE any targets run. Slow evaluation = slow build start even when nothing needs compiling. ## Diagnosing Evaluation Performance ### Primary: binlog MCP (preferred) Use the **binlog MCP server** (`Microsoft.AITools.BinlogMcp`, exposed under the `binlog` MCP namespace) to analyze evaluation performance: 1. Use the evaluations tool to list all evaluations and their durations 2. Use evaluation_global_properties to check for multiple evaluations with differing global properties 3. Use evaluation_properties to inspect evaluated properties for a specific project+TFM 4. Use imports tool to analyze the import chain depth and structure 5. Use properties tool to check for expensive property function evaluations ### Fallback: text-log replay and preprocessing (when MCP is unavailable) ### Using binlog 1. Replay the binlog: `dotnet msbuild build.binlog -noconlog -fl -flp:v=diag;logfile=full.log` 2. Search for evaluation events: `grep -i 'Evaluation started\|Evaluation finished' full.log` 3. Multiple evaluations for the same project = overbuilding 4. Look for "Project evaluation started/finished" messages and their timestamps ### Using /pp (preprocess) - `dotnet msbuild -pp:full.xml MyProject.csproj` - Shows the fully expanded project with ALL imports inlined - Use to understand: what's imported, import depth, total content volume - Large preprocessed output (>10K lines) = heavy evaluation ### Using /clp:PerformanceSummary - Add to build command for timing breakdown - Shows evaluation time separately from target/task execution ## Expensive Glob Patterns - Globs like `**/*.cs` walk the entire directory tree - Default SDK globs are optimized, but custom globs may not be - Problem: globbing over `node_modules/`, `.git/`, `bin/`, `obj/` — millions of files - Fix: use `<DefaultItemExcludes>` to exclude large directories - Fix: be specific with glob paths: `src/**/*.cs` instead of `**/*.cs` - Fix: use `<EnableDefaultItems>false</EnableDefaultItems>` only as last resort (lose SDK defaults) - Check: grep for Compile items in the diagnostic log → if Compile items include unexpected files, globs are too broad ## Import Chain Analysis - Deep import chains (>20 levels) slow evaluation - Each import: file I/O + parse + evaluate - Common causes: NuGet packages adding .props/.targets, framework SDK imports, Directory.Build chains - Diagnosis: `/pp` output → search for `<!-- Importing` comments to see import tree - Fix: reduce transitive package imports where possible, consolidate imports ## Multiple Evaluations - A project evaluated multiple times = wasted work - Common causes: referenced from multiple other projects with different global properties - Each unique set of global properties = separate evaluation - Diagnosis: `grep 'Evaluation started.*ProjectName' full.log` → if count > 1, check for differing global properties - Fix: normalize global properties, use graph build (`/graph`) ## TreatAsLocalProperty - Prevents property values from flowing to child projects via MSBuild task - Overuse: declaring many TreatAsLocalProperty entries adds evaluation overhead - Correct use: only when you genuinely need to override an inherited property ## Property Function Cost - Property functions execute during evaluation - Most are cheap (string operations) - Expensive: `$([System.IO.File]::ReadAllText(...))` during evaluation — reads file on every evaluation - Expensive: network calls, heavy computation - Rule: property functions should be fast and side-effect-free ## Optimization Checklist - [ ] Check preprocessed output size: `dotnet msbuild -pp:full.xml` - [ ] Verify evaluation count: should be 1 per project per TFM - [ ] Exclude large directories from globs - [ ] Avoid file I/O in property functions during evaluation - [ ] Minimize import depth - [ ] Use graph build to reduce redundant evaluations - [ ] Check for unnecessary UsingTask declarations
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.