Skip to content

Convert Claude commands to skills format#8158

Merged
lucaspimentel merged 2 commits intomasterfrom
lpimentel/convert-claude-commands-to-skills
Feb 5, 2026
Merged

Convert Claude commands to skills format#8158
lucaspimentel merged 2 commits intomasterfrom
lpimentel/convert-claude-commands-to-skills

Conversation

@lucaspimentel
Copy link
Member

@lucaspimentel lucaspimentel commented Feb 5, 2026 •
edited
Loading

Summary of changes

Migrated Claude Code commands from the legacy .claude/commands/*.md format to the new .claude/skills/*/SKILL.md structure:

  • analyze-crash: Stack trace crash analysis tool
  • analyze-error: Error stack trace analysis with actionability assessment
  • review-pr: GitHub PR review automation

Reason for change

Claude Code has introduced a new skills format that provides enhanced capabilities. The old command format still works but is deprecated in favor of skills.

Implementation details

For each command:

  1. Created .claude/skills/{skill-name}/SKILL.md with YAML frontmatter
  2. Added appropriate frontmatter fields:
    • disable-model-invocation: true - These are manual workflows
    • context: fork + agent: general-purpose - Run in isolated subagent
    • allowed-tools (review-pr only) - Restrict to specific gh commands
  3. Deleted original .claude/commands/*.md files

The skill content remains identical to the original commands.

Test coverage

They show up as slash commands in Claude Code, and are listed under /skills, so :shipit:

Other details

These are developer productivity tools for the dd-trace-dotnet maintainers and do not affect the tracer runtime or customer-facing functionality.

References:

@lucaspimentel
Move Claude commands to skills format
f3b6021 
Converts legacy `.claude/commands/*.md` files to the new
`.claude/skills/*/SKILL.md` structure for analyze-crash,
analyze-error, and review-pr.

🤖 Co-Authored-By: Claude Code <noreply@anthropic.com>
@lucaspimentel lucaspimentel changed the title Move Claude commands to new skills format Convert Claude commands to skills format Feb 5, 2026
@lucaspimentel lucaspimentel marked this pull request as ready for review February 5, 2026 03:10
@lucaspimentel lucaspimentel requested a review from a team as a code owner February 5, 2026 03:10
@pr-commenter
Copy link

pr-commenter bot commented Feb 5, 2026 •
edited
Loading

Benchmarks

Benchmark execution time: 2026-02-05 18:52:02

Comparing candidate commit a4ccb8d in PR branch lpimentel/convert-claude-commands-to-skills with baseline commit 5d8d01b in branch master.

Found 9 performance improvements and 9 performance regressions! Performance is the same for 160 metrics, 14 unstable metrics.

scenario:Benchmarks.Trace.AgentWriterBenchmark.WriteAndFlushEnrichedTraces net6.0

  • 🟥 execution_time [+80.261ms; +82.065ms] or [+66.064%; +67.549%]

scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.AllCycleSimpleBody netcoreapp3.1

  • 🟥 execution_time [+17.382ms; +23.768ms] or [+8.876%; +12.137%]

scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.ObjectExtractorSimpleBody net6.0

  • 🟥 execution_time [+15.121ms; +21.213ms] or [+7.495%; +10.515%]

scenario:Benchmarks.Trace.Asm.AppSecBodyBenchmark.ObjectExtractorSimpleBody netcoreapp3.1

  • 🟩 execution_time [-18.397ms; -12.393ms] or [-8.568%; -5.772%]

scenario:Benchmarks.Trace.Asm.AppSecEncoderBenchmark.EncodeLegacyArgs netcoreapp3.1

  • 🟩 execution_time [-23.484ms; -22.647ms] or [-11.569%; -11.157%]

scenario:Benchmarks.Trace.Asm.AppSecWafBenchmark.RunWafRealisticBenchmarkWithAttack netcoreapp3.1

  • 🟩 throughput [+158.714op/s; +405.583op/s] or [+5.632%; +14.391%]

scenario:Benchmarks.Trace.CIVisibilityProtocolWriterBenchmark.WriteAndFlushEnrichedTraces netcoreapp3.1

  • 🟥 throughput [-314.451op/s; -214.926op/s] or [-19.707%; -13.470%]

scenario:Benchmarks.Trace.CharSliceBenchmark.OptimizedCharSlice net472

  • 🟩 execution_time [-193.665µs; -187.202µs] or [-8.870%; -8.574%]
  • 🟩 throughput [+43.041op/s; +44.483op/s] or [+9.398%; +9.712%]

scenario:Benchmarks.Trace.CharSliceBenchmark.OriginalCharSlice net472

  • 🟩 execution_time [-240.553µs; -233.673µs] or [-8.581%; -8.336%]
  • 🟩 throughput [+32.509op/s; +33.416op/s] or [+9.113%; +9.367%]

scenario:Benchmarks.Trace.ElasticsearchBenchmark.CallElasticsearchAsync netcoreapp3.1

  • 🟩 throughput [+24630.891op/s; +30605.709op/s] or [+5.994%; +7.448%]

scenario:Benchmarks.Trace.Iast.StringAspectsBenchmark.StringConcatAspectBenchmark netcoreapp3.1

  • 🟥 throughput [-415.667op/s; -230.097op/s] or [-19.144%; -10.597%]

scenario:Benchmarks.Trace.Iast.StringAspectsBenchmark.StringConcatBenchmark net6.0

  • 🟥 execution_time [+2.642µs; +7.060µs] or [+5.974%; +15.961%]

scenario:Benchmarks.Trace.SingleSpanAspNetCoreBenchmark.SingleSpanAspNetCore net6.0

  • 🟩 execution_time [-24.425ms; -22.739ms] or [-21.354%; -19.880%]

scenario:Benchmarks.Trace.SingleSpanAspNetCoreBenchmark.SingleSpanAspNetCore netcoreapp3.1

  • 🟥 throughput [-16125792.224op/s; -14908509.570op/s] or [-6.695%; -6.190%]

scenario:Benchmarks.Trace.SpanBenchmark.StartFinishTwoScopes net6.0

  • 🟥 execution_time [+12.389ms; +17.941ms] or [+6.278%; +9.092%]

scenario:Benchmarks.Trace.SpanBenchmark.StartFinishTwoScopes netcoreapp3.1

  • 🟥 execution_time [+17.997ms; +22.224ms] or [+9.151%; +11.301%]

andrewlock
andrewlock approved these changes Feb 5, 2026
View reviewed changes
bouwkast
bouwkast approved these changes Feb 5, 2026
View reviewed changes
Copy link
Collaborator

@bouwkast bouwkast left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks!

This actually produces somewhat nicer outputs in the terminal for /analyze-error which is nice

@lucaspimentel @andrewlock
Update .claude/skills/review-pr/SKILL.md
a4ccb8d 
Co-authored-by: Andrew Lock <andrew.lock@datadoghq.com>
@lucaspimentel lucaspimentel enabled auto-merge (squash) February 5, 2026 18:09
@lucaspimentel lucaspimentel merged commit 1953712 into master Feb 5, 2026
98 of 101 checks passed
@lucaspimentel lucaspimentel deleted the lpimentel/convert-claude-commands-to-skills branch February 5, 2026 18:53
@github-actions github-actions bot added this to the vNext-v3 milestone Feb 5, 2026
@lucaspimentel lucaspimentel mentioned this pull request Feb 6, 2026
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@bouwkast bouwkast bouwkast approved these changes

@andrewlock andrewlock andrewlock approved these changes

Assignees

No one assigned

Labels

area:docs

Projects

None yet

Milestone

3.37.0

Development

Successfully merging this pull request may close these issues.

3 participants

@lucaspimentel @bouwkast @andrewlock