feat: improve azure-ai-projects-dotnet skill score#329
Open
yogesh-tessl wants to merge 1 commit into
Open
Conversation
Hey @thegovind 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements for the `azure-ai-projects-dotnet` skill. Here's the before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | azure-ai-projects-dotnet | 86% | 90% | +4% | <details> <summary>Changes summary</summary> **azure-ai-projects-dotnet (86% → 90%)**: - Fixed frontmatter description format from literal block (`|`) to standard quoted string - Added validation checkpoints to evaluation workflow — polling for completion status and failure detection before proceeding - Added verification step after dataset upload to confirm success - Added confirmation output after index creation - Removed redundant "Key Types Reference" table (all types already visible in Client Hierarchy diagram and code examples) - Removed redundant "Related SDKs" table (duplicated the Installation section) - Removed generic "Error Handling" section — consolidated the `RequestFailedException` pattern into Best Practices as a single actionable line - Trimmed Best Practices to 5 high-value, Azure AI Projects-specific items with reasoning (removed generic Azure SDK advice Claude already knows) - Tightened authentication section by removing inline comments that restated what the code shows - Cleaned up environment variable annotations for consistency Net result: 27 lines added, 64 removed — tighter, more actionable, with proper workflow validation patterns. </details> **Note:** I noticed the plugin skills are synced from GitHub-Copilot-for-Azure — if these improvements look good, it might be worth applying similar patterns to the sync source so they carry forward on the next sync. I also stress-tested your `azure-ai-projects-dotnet` skill against a few real-world task evals and it held up really well on versioned agent creation with web search tools and evaluation orchestration with status polling. Kudos for that. Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch — just saw room for improvement and wanted to contribute. Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at [this Tessl guide](https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices) and ask it to optimize your skill. Ping me — [@yogesh-tessl](https://github.com/yogesh-tessl) — if you hit any snags. Thanks in advance 🙏
Author
@microsoft-github-policy-service agree company="tessl.io" |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hey @thegovind 👋
great work. 181 skills covering Azure SDKs in five languages, plus standalone skills for KQL, MCP building, and even podcast generation. The Skill Explorer at skills.sh is a really nice touch for discoverability, and the nightly evaluation pipeline shows you're serious about keeping these accurate as the SDKs evolve. Impressive scope.
ran your skills through
tessl skill reviewat work and found some targeted improvements for theazure-ai-projects-dotnetskill. Here's the before/after:Changes summary
azure-ai-projects-dotnet (86% → 90%):
|) to standard quoted stringRequestFailedExceptionpattern into Best Practices as a single actionable linealso stress-tested your
azure-ai-projects-dotnetskill against a few real-world task evals and it held up really well on versioned agent creation with web search tools and evaluation orchestration with status polling. Kudos for that.quick honest disclosure. I work at https://github.com/tesslio where we build tooling around skills like these. Not a pitch, just saw room for improvement and wanted to contribute.
If you want to self-improve your skills, or define your own scenarios to pressure test, just ask your agent (Claude Code, Codex, etc.) to evaluate and optimize your skill with Tessl. Ping me @yogesh-tessl, if you hit any snags.