Build Fix

What it does

When your agent uses it

• Says fix the build
• Build is broken
• Make it compile
• Make the tests pass

Example prompts

• “fix the build”
• “build is broken”
• “make it compile”
• “/build-fix”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Bounded iteration, always — Default max 5 iterations, hard cap 10
2. 2Progress or exit — Each iteration must reduce the error/failure count.
3. 3Categorize before fixing — Group errors by root cause and fix the
4. 4Transparency per iteration — Report what changed and why
5. 5Atomicity — Each iteration leaves the codebase no worse than before.

What it can do on your machine

Read from SKILL.md and the folder at commit 2330089. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • dotnet

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Build Fix loads about 1.8k tokens when it runs. Until then it costs about 156 tokens; SKILL.md has 772 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~156

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from codewithmukesh/dotnet-claude-kit at commit 2330089, republished under its MIT licence (© codewithmukesh). 772 words, ~1,803 tokens.

name

build-fix

description

Autonomous iteration loops for .NET: drive a broken build or failing test suite to green with bounded iterations, progress detection, and fail-safe guards that prevent infinite retries and wasted tokens. The build-fix loop (dotnet build, parse, categorize, fix, rebuild) is the primary flow; the test-fix loop is a first-class variant. Invoke when the build is broken, after a major refactor or dependency update, or when the user says "fix the build", "build is broken", "make it compile", "make the tests pass", "fix failing tests", "keep going until it works", "autonomous", "loop", "auto-fix", or "keep fixing".

User: /build-fix

Claude: Running dotnet build...
  Found 12 errors across 4 files.

  Iteration 1/5:
  - 6 errors: Missing namespace (CS0246) — adding using directives
  - 3 errors: Type mismatch (CS1503) — updating method signatures
  - 3 errors: Interface not implemented (CS0738) — package API changed

  Rebuilding... 3 errors remaining.

  Iteration 2/5:
  - 3 errors: CS0738 after xunit.v3 upgrade
    - IAsyncLifetime.InitializeAsync now returns ValueTask (was Task in v2),
      and DisposeAsync comes from IAsyncDisposable
    - Updating 3 test fixtures to the ValueTask signatures

  Rebuilding... 0 errors. Build is green.

  Running dotnet test... All 47 tests passed.
  Added to Memory > Packages: "xunit.v3 IAsyncLifetime uses ValueTask signatures"

© codewithmukesh, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/build-fix of codewithmukesh/dotnet-claude-kit.

Open the folder on GitHubat commit 2330089