build-check
Auto-detects the project's build system and runs compile/type-check after file changes, auto-fixing straightforward errors (max 3 attempts).
Skill by TheophilusChinomona
Chalk Labs
Need help deploying build-check?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/theophiluschinomona-build-check
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/build-check
What's inside
- Skill name
build-check- Description
- Auto-detects the project's build system and runs compile/type-check after file changes, auto-fixing straightforward errors (max 3 attempts). Use after completing a multi-file feature or when asked to build or check compilation.
- License
- MIT
- Instructions
- 228 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Build Check Skill
## Purpose
Auto-detect the project's build system and run compilation/type-checking after creating or modifying files. Catches errors (missing imports, type mismatches, DI failures) before the user discovers them at runtime.
## Activation
Run once per logical change set — after completing a multi-file feature or a self-contained modification, NOT after each individual file:
- After completing a multi-file feature (run once at the end)
- After a single-file change that could affect compilation (run once for that change)
- When the user asks to build or check compilation
---
## How It Works
This skill does NOT hardcode build commands. It detects them from the project.
Results cached in `.claude/idev/build-check/cache.json` after first detection.
---
## Phase 1: Detect Build System
Scan for build configuration files. Check ALL — do not assume any stack:
```
.NET:
Glob for *.sln → dotnet build {solution.sln}
Glob for *.csproj (if no .sln) → dotnet build {project.csproj}
Check for specific project to build (API project .csproj for faster builds)
Node.js/TypeScript:
Read package.json → check scripts section:
"build" → npm run build / yarn build / pnpm build
"typecheck" or "tsc" → npm run typecheck (preferred — faster than full build)
"check" → npm run check (Svelte)
Detect package manager: look for yarn.lock, pnpm-lock.yaml, or package-lock.json
Python:
Glob for pyproject.toml → check for build tool (poetry, setuptools, hatch)
Check for mypy.ini or pyproject.toml [tool.mypy] → mypy for type checking
Check for ruff.toml or pyproject.toml [tool.ruff] → ruff check
Java:
Glob for pom.xml → mvn compile
Glob for build.gradle → gradle compileJava / ./gradlew compileJava
Go:
Glob for go.mod → go build ./...
Rust:
Glob for Cargo.toml → cargo check (faster than cargo build)
Ruby:
Glob for Gemfile → bundle exec ruby -c (syntax check)
Check for sorbet → srb tc (type check)
PHP:
Glob for composer.json → check for phpstan or psalm → phpstan analyse / psalm
```
---
## Phase 2: Generate Cache
Write detected build commands to `.claude/idev/build-check/cache.json`:
```json
{
"generated": "YYYY-MM-DD",
"projects": [
{
"name": "ProjectName",
"root": "relative/path/to/project",
"layer": "backend|frontend",
"buildCommand": "dotnet build path/to/project.csproj",
"typeCheckCommand": "npm run typecheck (if different from build)",
"lintCommand": "npm run lint (if available)",
"workingDirectory": "relative/path (if command must run from specific dir)",
"timeout": 120000
}
],
"quickChecks": {
"backend": "dotnet build path/to/api.csproj --no-restore",
"frontend": "npx tsc --noEmit"
}
}
```
---
## Phase 3: When to Run
### Pre-flight: DBScripts check
Before running any build, check for unapplied database migrations:
```
1. Scan for DBScripts/ folder in the project
2. Compare scripts against .claude/idev/db-preflight/applied.json
3. If unapplied scripts exist:
→ WARN: "N unapplied DBScripts found — builds may fail with 'Invalid object name' errors"
→ List the unapplied scripts
→ Ask user: apply first, or proceed with build anyway?
4. This prevents the recurring 500 errors from missing schema changes
```
The db-preflight skill provides the full scanning and error-mapping logic.
build-check invokes it as a lightweight pre-flight, not a full replacement.
### After creating a NEW feature (multi-file):
```
1. Wait until ALL files are created (entity, DTOs, service, controller, etc.)
2. Run db-preflight pre-flight (check for unapplied DBScripts)
3. Run the backend build command
4. If frontend files were also created, run frontend type-check
5. Report results: success or list of errors
```
### After modifying a SINGLE file:
```
1. Determine which project the file belongs to (check file path against project roots)From TheophilusChinomona/idev, MIT.
More from TheophilusChinomona/idev
- 0.521score
branch-sync
TheophilusChinomona
Syncs the current feature branch with the team base branch (merge base into feature) before creating a PR, resolving merge conflicts safely with build/test…
SkillBFreshness: BClaude Code +9 - 0.517score
browse
TheophilusChinomona
Interactive browser QA using xd://browser or (optionally) the gstack browse binary for headed mode.
SkillBFreshness: BClaude Code +9 - 0.516score
continuous-learning
TheophilusChinomona
Automatically extracts reusable patterns from sessions and saves them as learned skills.
SkillBFreshness: BClaude Code +9 - 0.516score
env-preflight
TheophilusChinomona
Session environment sanity check — verifies cwd is the repo root, git auth is live, DB env vars are present, and reports active sandbox constraints.
SkillBFreshness: BClaude Code +9 - 0.516score
eval-harness
TheophilusChinomona
Evaluation framework for capability and regression evals with pass@k metrics.
SkillBFreshness: BClaude Code +9 - 0.516score
db-preflight
TheophilusChinomona
Scans DBScripts/ folder for unapplied database migrations and surfaces them before builds or at session start.
SkillBFreshness: BClaude Code +9 - 0.516score
context-switching
TheophilusChinomona
Switches between development modes (dev, review, research) by loading the appropriate context.
SkillBFreshness: BClaude Code +9 - 0.513score
api-contract-validation
TheophilusChinomona
Discovers and validates API endpoints between frontend and backend.
SkillBFreshness: BClaude Code +9 - 0.508score
architecture-scanner
TheophilusChinomona
DEPRECATED — Use project-map, backend-patterns, and frontend-patterns instead.
SkillBFreshness: BClaude Code +9 - 0.508score
file-index
TheophilusChinomona
DEPRECATED — Use smart-context for feature-to-file lookups.
SkillBFreshness: BClaude Code +9 - 0.472score
auto-learning
TheophilusChinomona
Instinct-based learning system that observes sessions via hooks and evolves patterns into skills/commands/agents.
SkillCFreshness: CClaude Code +9 - 0.467score
codebase-explainer
TheophilusChinomona
Turn a codebase into an onboarding playlist — Claude-authored analysis docs plus NotebookLM explainer videos (one overview + one per subsystem).
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 29, 2026 (3 months ago)
- Last release
- Jun 25, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/TheophilusChinomona/idev
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from TheophilusChinomona
- 0.521score
branch-sync
TheophilusChinomona
Syncs the current feature branch with the team base branch (merge base into feature) before creating a PR, resolving merge conflicts safely with build/test…
SkillBFreshness: BClaude Code +9 - 0.517score
browse
TheophilusChinomona
Interactive browser QA using xd://browser or (optionally) the gstack browse binary for headed mode.
SkillBFreshness: BClaude Code +9 - 0.516score
context-switching
TheophilusChinomona
Switches between development modes (dev, review, research) by loading the appropriate context.
SkillBFreshness: BClaude Code +9 - 0.516score
continuous-learning
TheophilusChinomona
Automatically extracts reusable patterns from sessions and saves them as learned skills.
SkillBFreshness: BClaude Code +9 - 0.516score
db-preflight
TheophilusChinomona
Scans DBScripts/ folder for unapplied database migrations and surfaces them before builds or at session start.
SkillBFreshness: BClaude Code +9 - 0.516score
env-preflight
TheophilusChinomona
Session environment sanity check — verifies cwd is the repo root, git auth is live, DB env vars are present, and reports active sandbox constraints.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get build-check running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
build-check skill. Agent Mart. https://agentmart.dev/skills/theophiluschinomona-build-check (last updated 2026-10-24)