fsharp
Debug, review, and ship F# compiler changes with AI agents
All Skills in This Repository (11)
Pure Emerald Level Indicatorscreating-skills
Create standardized GitHub Copilot Agent Skills with YAML frontmatter and Markdown bodies.
postmortem
Draft structured postmortems for production bugs with root causes and preventive measures.
hypothesis-driven-debugging
Guide hypothesis-driven debugging of F# compiler failures with minimal reproductions.
code-compaction
Detects and reduces bloated code diffs using cross-model adversarial review rounds.
vsintegration-ide-debugging
Diagnose F# debugging issues involving breakpoints, PDB files, and sequence points.
binlog-analysis
Diagnoses MSBuild failures by fetching binlogs and analyzing them via the binlog-mcp MCP server.
flaky-test-detector
Detect flaky tests by aggregating test failures across Azure DevOps CI builds from distinct pull requests.
release-notes
Write changelog entries for F# compiler pull requests in Keep A Changelog format.
pr-description
Writes concise GitHub PR descriptions, issue bodies, and review comments for dotnet/fsharp.
reviewing-compiler-prs
Reviews F# compiler pull requests across 19 dimensions using parallel subagents.
realsig-codegen
Diagnose and fix --realsig+ codegen bugs causing runtime access exceptions in F# IlxGen.
Frequently Asked Questions
FAQPage SchemaHow to install dotnet/fsharp skills?โผ
Run `npx skills add dotnet/fsharp --all -g -y` in your terminal to install all skills in this suite globally.
How to debug F# compiler CI failures with AI?โผ
The pr-build-status and binlog-analysis skills fetch failed Azure DevOps builds, collect every error across Linux, Windows, and macOS, and pinpoint root causes from the MSBuild binary log.
Can AI typecheck F# compiler code without a full build?โผ
Yes. The fsharp-diagnostics skill runs a background server that parses, typechecks, finds symbol references, and shows inferred types in seconds instead of waiting for dotnet build.
How to detect flaky tests in dotnet/fsharp?โผ
The flaky-test-detector skill scans recent CI builds and flags tests that fail across three or more unrelated pull requests, so you can quarantine them confidently.
Do these skills work with GitHub Copilot and Claude Code?โผ
Yes. Every skill follows the standard SKILL.md format and runs in GitHub Copilot, Claude Code, and other agents that support the open Agent Skills standard.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core