Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Run ApiChief in the EF Core repo to emit baselines, summaries, deltas, review files, or breaking-change checks. Use when refreshing `*.baseline.json`, preparing API review artifacts, or validating API changes.
.claude/skills/run-apichief/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | — | — |
| case-06 | ✗→✓ | ▲ Improved | — | — |
| case-04 | ✗→✓ | ▲ Improved | — | — |
| case-08 | ✗→✓ | ▲ Improved | — | — |
| case-05 | ✗→✓ | ▲ Improved | — | — |
Use the ApiChief tool to inspect or refresh EF Core public API baselines for projects under src/.
ApiChief can run against either a compiled assembly or a previously emitted baseline JSON file. Prefer the repo-local .dotnet SDK and the checked-in build scripts in this repo.
| Command | Description | Extra arguments | | --- | --- | --- | | emit baseline | Emit a JSON API baseline | -o <file> | | emit summary | Emit a human-readable API summary | -o <file>, -x | | emit review | Emit API review files | -o <dir>, -n | | emit delta | Emit a delta against an existing baseline, or markdown diff review files | <baseline-path>, -o <file-or-dir>, --diff | | check breaking | Fail if breaking changes exist vs. a baseline | <baseline-path> |
Default to emit baseline if the user only asks to "run ApiChief".
src/.src/<ProjectName>/<ProjectName>.baseline.json.Always initialize the repo environment before building or running the tool:
powershell.\restore.cmd . .\activate.ps1 dotnet build .\eng\Tools\ApiChief\ApiChief.csproj --nologo --verbosity q
On Bash:
bash./restore.sh . ./activate.sh dotnet build ./eng/Tools/ApiChief/ApiChief.csproj --nologo --verbosity q
ApiChief operates on built assemblies. If the target project has not been built yet, build it first.
Preferred options:
powershell# Refreshes checked-in baselines after the normal build .\build.cmd -c Debug # Or build a single project when working narrowly dotnet build .\src\<ProjectName>\<ProjectName>.csproj --nologo --verbosity q
Use the highest available net* TFM under artifacts/bin/<ProjectName>/<Configuration>/ by default. Avoid netstandard* and net4* targets unless the user explicitly asks for them.
powershell$dotnet = ".\\.dotnet\\dotnet" $apiChiefProject = ".\\eng\\Tools\\ApiChief\\ApiChief.csproj" $apiChief = (& $dotnet msbuild $apiChiefProject --getProperty:TargetPath -p:Configuration=Debug --nologo).Trim() $name = "<ProjectName>" $tfm = Get-ChildItem ".\\artifacts\\bin\\$name\\Debug" -Directory | Where-Object { $_.Name -match '^net\d+\.\d+$' } | Sort-Object { [version]($_.Name -replace '^net', '') } -Descending | Select-Object -First 1 -ExpandProperty Name $assemblyName = (& $dotnet msbuild ".\\src\\$name\\$name.csproj" --getProperty:AssemblyName -p:Configuration=Debug --nologo).Trim() if ([string]::IsNullOrWhiteSpace($assemblyName)) { $assemblyName = $name } $assemblyPath = ".\\artifacts\\bin\\$name\\Debug\\$tfm\\$assemblyName.dll"
Before running, report the selected TFM if it matters for the task.
powershell# Emit a baseline & $dotnet $apiChief $assemblyPath emit baseline -o ".\\src\\$name\\$name.baseline.json" # Emit a summary & $dotnet $apiChief $assemblyPath emit summary # Emit a delta & $dotnet $apiChief $assemblyPath emit delta ".\\src\\$name\\$name.baseline.json" -o ".\\artifacts\\tmp\\$name.delta.json" # Check for breaking changes & $dotnet $apiChief $assemblyPath check breaking ".\\src\\$name\\$name.baseline.json" # Emit API review artifacts & $dotnet $apiChief $assemblyPath emit review -o ".\\artifacts\\tmp\\API.$name" # Emit GitHub-friendly markdown diff files against a baseline & $dotnet $apiChief $assemblyPath emit delta ".\\src\\$name\\$name.baseline.json" --diff -o ".\\artifacts\\tmp\\API.$name.Diff"
emit delta also supports passing a .json file as the current input instead of a DLL.
After emit baseline:
"Name" field// instruction comments in previous baselines and carry forward any still-needed manual editscheck breaking, state pass/failemit delta and emit delta --diff, mention that exit code 0 means changes, 2 means no changes, and -1 means an erroremit delta --diff output because it generates ready-to-post diff fenced markdown split across per-type .md files| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 16 counted toward the lift figure. The other 6 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +59 percentage points is the difference between those two pass rates over the 16 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.