Trim dotnet-msbuild skill-menu under 15K char limit

[YuliiaKovalova]

Problem

The plugin loader rejects the dotnet-msbuild plugin:

❌ [plugin:dotnet-msbuild] Plugin 'dotnet-msbuild' rendered skill-menu size is 16,679 characters — maximum is 15,000.

Change

Trim two categories of content from all 18 skill descriptions that do not help an agent decide when to invoke a skill:

1. INVOKES: clauses — these enumerate which MCP tools / fallback shell commands a skill runs internally. That's implementation mechanics, not routing signal.
2. The boilerplate Only activate in MSBuild/.NET build context. repeated verbatim in all 18 skills — redundant, since every description is already saturated with MSBuild-specific terms and each DO NOT USE FOR still excludes non-MSBuild build systems.

The high-signal routing content — capability summary, USE FOR: triggers, and DO NOT USE FOR: cross-references — is fully preserved.

Result

	Before	After
Aggregate skill description chars	14,551	12,536
Rendered skill-menu	16,679	14,664

Now under the 15,000 limit. Per-skill descriptions remain within the 1,024-char spec limit (max 975).

[Copilot]

Pull request overview

Reduces the rendered dotnet-msbuild plugin skill-menu size to fit under the 15,000 character loader limit by trimming low-signal boilerplate from skill front-matter descriptions, while preserving the routing-relevant USE FOR: / DO NOT USE FOR: content.

Changes:

• Removed the repeated “Only activate in MSBuild/.NET build context.” sentence from all dotnet-msbuild skill description: front matter strings.
• Removed INVOKES: clauses from skill description: front matter strings to avoid leaking internal mechanics and reduce size.
• Kept per-skill routing signals (capability summary, triggers, and cross-skill references) intact.

Reviewed changes

Copilot reviewed 18 out of 18 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
plugins/dotnet-msbuild/skills/target-authoring/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/resolve-project-references/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/property-patterns/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/msbuild-server/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/msbuild-modernization/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/msbuild-antipatterns/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/item-management/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/incremental-build/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/including-generated-files/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/extension-points/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/eval-performance/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/directory-build-organization/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/check-bin-obj-clash/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/build-perf-diagnostics/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/build-perf-baseline/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/build-parallelism/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/binlog-generation/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.
plugins/dotnet-msbuild/skills/binlog-failure-analysis/SKILL.md	Trimmed front-matter description to reduce aggregated skill-menu size.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[YuliiaKovalova]

/evaluate

[github-actions]

Skill Validation Results

Skill	Scenario	Quality	Skills Loaded	Overfit	Verdict
msbuild-antipatterns	Review MSBuild files for anti-patterns and style issues	4.7/5 → 4.3/5 🔴	✅ msbuild-antipatterns; tools: skill, glob / ⚠️ NOT ACTIVATED	✅ 0.09	❌
msbuild-antipatterns	Add a module to an F# project	5.0/5 → 5.0/5	⚠️ NOT ACTIVATED	✅ 0.09	❌ [1]
msbuild-antipatterns	Fix broken file order causing FS0039	4.0/5 → 4.0/5	⚠️ NOT ACTIVATED	✅ 0.09	❌ [2]
msbuild-antipatterns	Add a signature file to define public API	5.0/5 → 5.0/5	⚠️ NOT ACTIVATED	✅ 0.09	❌ [3]
eval-performance	Analyze MSBuild evaluation performance issues	5.0/5 → 5.0/5	✅ eval-performance; tools: skill	✅ 0.11	❌ [4]
item-management	Diagnose item group and batching issues	5.0/5 → 5.0/5	✅ item-management; tools: skill	✅ 0.11	❌ [5]
item-management	Diagnose cascading item and batching bugs in code generation pipeline	4.3/5 → 5.0/5 🟢	✅ item-management; tools: skill, glob, bash / ✅ item-management; tools: skill, bash	✅ 0.11	❌ [6]
item-management	Fix item management anti-patterns	3.7/5 → 4.7/5 🟢	✅ item-management; tools: skill, bash / ⚠️ NOT ACTIVATED	✅ 0.11	✅ [7]
directory-build-organization	Organize build infrastructure for a multi-project repo	3.7/5 → 4.7/5 🟢	✅ directory-build-organization; tools: skill, create, edit, bash / ✅ directory-build-organization; tools: skill, create, edit, bash, task, read_agent	🟡 0.20	✅ [8]
incremental-build	Analyze incremental build issues	3.0/5 → 3.0/5	⚠️ NOT ACTIVATED	✅ 0.13	❌ [9]
target-authoring	Diagnose custom target build regression	3.3/5 → 5.0/5 🟢	✅ target-authoring; tools: skill / ✅ target-authoring; tools: skill, bash	🟡 0.23	✅ [10]
target-authoring	Diagnose broken SDK target chain across files	3.0/5 → 3.3/5 🟢	✅ target-authoring; tools: skill / ✅ target-authoring; tools: skill, glob	🟡 0.23	❌ [11]
target-authoring	Fix custom target anti-patterns	4.0/5 → 4.0/5	✅ target-authoring; tools: skill, bash / ⚠️ NOT ACTIVATED	🟡 0.23	✅ [12]
msbuild-server	Recommend MSBuild Server for slow CLI incremental builds	2.7/5 → 4.7/5 🟢	✅ msbuild-server; tools: skill	✅ 0.15	✅ [13]
build-perf-baseline	Establish build performance baseline and recommend optimizations	3.0/5 → 2.7/5 ⏰ 🔴	✅ build-perf-baseline; tools: skill, binlog-binlog_overview, binlog-binlog_diagnose, binlog-binlog_incremental_analysis, binlog-binlog_expensive_targets, binlog-binlog_expensive_tasks, binlog-binlog_build_graph, binlog-binlog_target_reasons, binlog-binlog_analyzer_summary, binlog-binlog_search, binlog-binlog_expensive_projects, binlog-binlog_double_writes, binlog-binlog_explain_property, binlog-binlog_imports, binlog-binlog_search_files, binlog-binlog_files, binlog-binlog_evaluations, binlog-binlog_evaluation_global_properties, binlog-binlog_evaluation_properties / ⚠️ NOT ACTIVATED	🟡 0.37	❌ [14]
property-patterns	Diagnose shared build property issues	5.0/5 → 5.0/5	✅ property-patterns; tools: skill, glob	✅ 0.13	❌ [15]
property-patterns	Diagnose multi-level property hierarchy bugs	4.3/5 → 4.3/5	✅ property-patterns; tools: glob, skill / ✅ property-patterns; tools: skill, glob	✅ 0.13	✅ [16]
property-patterns	Fix shared property configuration	5.0/5 → 5.0/5	✅ property-patterns; tools: glob, skill / ⚠️ NOT ACTIVATED	✅ 0.13	❌ [17]
binlog-generation	Build project with /bl flag	1.3/5 → 5.0/5 🟢	✅ binlog-generation; tools: skill / ⚠️ NOT ACTIVATED	🟡 0.32	✅ [18]
binlog-generation	Build with /bl in PowerShell	3.3/5 → 5.0/5 🟢	✅ binlog-generation; tools: skill, glob / ⚠️ NOT ACTIVATED	🟡 0.32	❌ [19]
binlog-generation	Build multiple configurations with unique binlogs	3.7/5 → 3.7/5	✅ binlog-generation; tools: skill / ⚠️ NOT ACTIVATED	🟡 0.32	❌ [20]
resolve-project-references	Explain misleading ResolveProjectReferences time	3.7/5 → 5.0/5 🟢	✅ resolve-project-references; tools: skill	✅ 0.14	✅ [21]
extension-points	Diagnose build extension point failures	3.0/5 → 5.0/5 🟢	✅ extension-points; tools: skill, edit / ✅ extension-points; tools: glob, skill, edit	✅ 0.11	✅ [22]
extension-points	Diagnose NuGet package and repo extension conflicts	3.0/5 → 3.0/5	✅ extension-points; tools: skill, edit	✅ 0.11	❌ [23]
extension-points	Fix extension point anti-patterns	4.7/5 → 5.0/5 🟢	✅ extension-points; tools: skill / ⚠️ NOT ACTIVATED	✅ 0.11	❌ [24]
build-perf-diagnostics	Diagnose slow build for a small project	4.0/5 → 4.0/5	⚠️ NOT ACTIVATED	🟡 0.21	❌ [25]
check-bin-obj-clash	Diagnose bin/obj output path clashes	4.3/5 → 4.7/5 🟢	✅ check-bin-obj-clash; tools: skill, binlog-binlog_overview, binlog-binlog_evaluations, binlog-binlog_double_writes, binlog-binlog_evaluation_properties, binlog-binlog_evaluation_global_properties, binlog-binlog_properties / ✅ check-bin-obj-clash; tools: glob, skill, binlog-binlog_double_writes, binlog-binlog_evaluations, binlog-binlog_properties, binlog-binlog_evaluation_global_properties, binlog-binlog_evaluation_properties, binlog-binlog_overview	✅ 0.14	✅ [26]
binlog-failure-analysis	Diagnose build failures from binlog only (no source files)	4.0/5 → 4.0/5	⚠️ NOT ACTIVATED	✅ 0.11	❌ [27]
msbuild-modernization	Modernize legacy project to SDK-style	5.0/5 → 5.0/5	✅ msbuild-modernization; tools: skill	✅ 0.06	❌ [28]
including-generated-files	Diagnose generated file inclusion failure	3.0/5 → 4.7/5 🟢	✅ including-generated-files; tools: skill	🟡 0.23	✅
build-parallelism	Analyze build parallelism bottlenecks	4.0/5 → 4.3/5 🟢	✅ build-parallelism; tools: glob, binlog-binlog_build_graph, binlog-binlog_overview, binlog-binlog_errors, edit, binlog-binlog_expensive_projects, binlog-binlog_diagnose, skill / ⚠️ NOT ACTIVATED	✅ 0.20	✅ [29]

[1] (Plugin) Quality unchanged but weighted score is -2.6% due to: tokens (107352 → 186307)
[2] (Plugin) Quality unchanged but weighted score is -3.2% due to: tokens (72719 → 117342)
[3] (Plugin) Quality unchanged but weighted score is -5.4% due to: quality, tokens (80469 → 123994)
[4] ⚠️ High run-to-run variance (CV=93%) — consider re-running with --runs 5
[5] (Plugin) Quality unchanged but weighted score is -5.4% due to: tokens (40368 → 80472)
[6] ⚠️ High run-to-run variance (CV=494%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -21.1% due to: judgment, quality, tokens (141917 → 180401)
[7] ⚠️ High run-to-run variance (CV=147%) — consider re-running with --runs 5
[8] ⚠️ High run-to-run variance (CV=95%) — consider re-running with --runs 5. (Plugin) Quality dropped but weighted score is +2.7% due to: efficiency metrics
[9] ⚠️ High run-to-run variance (CV=91%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -5.9% due to: quality, tokens (26205 → 38657)
[10] ⚠️ High run-to-run variance (CV=57%) — consider re-running with --runs 5
[11] ⚠️ High run-to-run variance (CV=1119%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -5.3% due to: tokens (73700 → 137451), time (55.9s → 71.8s)
[12] ⚠️ High run-to-run variance (CV=3154%) — consider re-running with --runs 5
[13] ⚠️ High run-to-run variance (CV=54%) — consider re-running with --runs 5
[14] ⚠️ High run-to-run variance (CV=100%) — consider re-running with --runs 5
[15] (Plugin) Quality unchanged but weighted score is -3.5% due to: tokens (146903 → 254524)
[16] ⚠️ High run-to-run variance (CV=134%) — consider re-running with --runs 5
[17] ⚠️ High run-to-run variance (CV=94%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -1.9% due to: tokens (172758 → 240940)
[18] ⚠️ High run-to-run variance (CV=71%) — consider re-running with --runs 5
[19] ⚠️ High run-to-run variance (CV=231%) — consider re-running with --runs 5
[20] ⚠️ High run-to-run variance (CV=176%) — consider re-running with --runs 5
[21] ⚠️ High run-to-run variance (CV=55%) — consider re-running with --runs 5
[22] ⚠️ High run-to-run variance (CV=189%) — consider re-running with --runs 5
[23] ⚠️ High run-to-run variance (CV=76%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -5.8% due to: tokens (73505 → 163640), time (66.6s → 82.6s)
[24] ⚠️ High run-to-run variance (CV=702%) — consider re-running with --runs 5
[25] ⚠️ High run-to-run variance (CV=95%) — consider re-running with --runs 5
[26] ⚠️ High run-to-run variance (CV=196%) — consider re-running with --runs 5
[27] ⚠️ High run-to-run variance (CV=604%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -11.3% due to: judgment, quality
[28] (Plugin) Quality unchanged but weighted score is -3.4% due to: tokens (81698 → 142225), time (37.5s → 47.2s)
[29] ⚠️ High run-to-run variance (CV=497%) — consider re-running with --runs 5

⏰ timeout — run(s) hit the (360s) scenario timeout limit; scoring may be impacted by aborting model execution before it could produce its full output (increase via timeout in eval.yaml)

Model: claude-opus-4.6 | Judge: claude-opus-4.6

🔍 Full Results - additional metrics and failure investigation steps

To investigate failures, paste this to your AI coding agent:

For PR 809 in dotnet/skills, download eval artifacts with gh run download 28043132362 --repo dotnet/skills --pattern "skill-validator-results-*" --dir ./eval-results, then fetch https://raw.githubusercontent.com/dotnet/skills/5385ef282e6c4e31da8f46676f473f8f5f1a6e07/eng/skill-validator/src/docs/InvestigatingResults.md and follow it to analyze the results.json files. Diagnose each failure, suggest fixes to the eval.yaml and skill content, and tell me what to fix first.

▶ Sessions Visualisation -- interactive replay of all evaluation sessions
📊 Session Analytics (preview) -- aggregated metrics across evaluation sessions

[github-actions]

✅ Evaluation passed for 5385ef2. cc @ViktorHofer @JanKrivanek @dotnet/skills-msbuild-reviewers — please review.