Dotnet Techne Code Review
Structured .NET PR review with adversarial mode and heuristic risk-grep scripts.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 15, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · d9af90f
Ran its review-context.sh script against a throwaway git repo with a deliberately broken feature branch (blocking .Result, string-built SQL, static mutable cache, swallowed exception) and the built-in heuristic grep flagged all four risk lines by number before the model even started reasoning, then the output-contract format forced severity/evidence/fix/confidence per finding — more rigorous and faster to audit than an unguided review.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 5/5
What Dotnet Techne Code Review does
Reviews .NET diffs/branches/commit-ranges for correctness, performance, security, DB and messaging issues using a fixed output contract (severity/evidence/fix/confidence). Triggers on code-review requests, including an adversarial 'cynical mode' for skeptical review language, and ships bundled bash/PowerShell scripts that grep diffs for known risk patterns (blocking .Result, raw SQL, swallowed exceptions).
How to install Dotnet Techne Code Review
git clone https://github.com/Metalnib/dotnet-episteme-skills.git
mkdir -p ~/.claude/skills
cp -r dotnet-episteme-skills/skills/dotnet-techne-code-review ~/.claude/skills/dotnet-techne-code-review
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Dotnet Techne Code Review
-
/dotnet-techne-code-reviewStructured .NET PR review with adversarial mode and heuristic risk-grep scripts.
It also activates on plain-language prompts like these:
-
review this C# pull request for blocking calls and raw SQL injection -
be brutally skeptical reviewing my .NET branch before I open the PR -
check my ASP.NET diff for swallowed exceptions and unsafe raw SQL
Frequently asked questions
- Is the Dotnet Techne Code Review skill free?
- Yes. The skill itself is free from Metalnib/dotnet-episteme-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Dotnet Techne Code Review work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Ran its review-context.sh script against a throwaway git repo with a deliberately broken feature branch (blocking .Result, string-built SQL, static mutable cache, swallowed exception) and the built-in heuristic grep flagged all four risk lines by number before the model even started reasoning, then the output-contract format forced severity/evidence/fix/confidence per finding — more rigorous and faster to audit than an unguided review.
- What is the Dotnet Techne Code Review SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install Dotnet Techne Code Review?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Dotnet Techne Code Review with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.