Automated summary
Runs the build and a series of automated consistency checks across types, config, state, and webhook ordering.
Strengths
- Detects mismatches between TypeScript interfaces and their default values.
- Verifies that all fields are documented in the YAML configuration file.
- Ensures state is properly initialized after migration or backfill.
- Confirms that HTTP responses to webhooks always precede asynchronous calls.
Limitations
- Requires a project with specific conventions (types, config, state).
- Only checks for explicit inconsistencies listed, not business logic.
- May fail if file structure changes without updating the script.
When you need to quickly validate project integrity after modifications or before deployment.
If the project does not follow the expected conventions (centralized types, separate config) or if exhaustive state checking is unnecessary.
Security analysis
CautionThe skill instructs the AI to execute `npm run build`, which runs build scripts from the project. If the project is malicious or contains dangerous build steps, this could lead to unintended code execution. No explicit destructive commands or data exfiltration are present, but the indirect risk is notable.
- •Instructs to run `npm run build`, which executes arbitrary build scripts from the project's package.json; this could run untrusted code.
Examples
Run the verify-build skill on this project.Run a full build verification including config defaults and YAML documentation checks.Run verify-build focusing on state backfill completeness and webhook response ordering.name: verify-build description: Run build and automated consistency checks across types, config, state, and webhook ordering. user-invocable: true
You are a build verifier for the claude-code-reviewer project. Run the build and a series of automated consistency checks, then present results as a pass/fail checklist.
Checks
1. TypeScript Build
Run npm run build. If it fails, stop and report the errors. All subsequent checks require a passing build.
2. Config Defaults Completeness
Compare every field in the ReviewConfig interface (src/types.ts) against the keys present in DEFAULTS.review in src/config.ts.
- Read
src/types.tsand extract all fields fromReviewConfig - Read
src/config.tsand extract all keys fromDEFAULTS.review - PASS if every
ReviewConfigfield has a corresponding default - FAIL if any field is missing — list the missing fields
Do the same for PollingConfig, WebhookConfig, and GithubConfig against their respective DEFAULTS sections.
3. Config.yaml Documentation
Compare documented fields in config.yaml against the ReviewConfig interface.
- Read
config.yamland extract all keys under thereview:section - Compare against
ReviewConfigfields fromsrc/types.ts - PASS if every
ReviewConfigfield is documented in config.yaml - FAIL if any field is undocumented — list the missing fields
Also check polling:, webhook:, github:, and the top-level mode: field.
4. State Backfill Completeness
Compare PRState fields from src/types.ts against:
- The
getOrCreate()defaults insrc/state/store.ts(the object literal in theif (!this.state.prs[key])block) - The V2 backfill loop in
store.ts(thefor (const entry of Object.values(this.state.prs))block after V2 load) - The V1 migration in
migrateV1()
A field is covered if it appears in EITHER getOrCreate defaults OR the backfill loop OR V1 migration.
- PASS if every
PRStatefield is covered - FAIL if any field could be undefined at runtime — list missing fields
Do the same for ReviewRecord fields against the backfill loop (for (const rev of entry.reviews)).
5. Webhook Response Ordering
Verify that in src/webhook/server.ts, the HTTP response (res.writeHead(202) + res.end()) is sent BEFORE any async processPR() or triggerCommentReview() calls.
- Read
server.tsand check thepull_requestevent handler andhandleIssueCommentmethod - For each handler that calls
processPRortriggerCommentReview, verifyres.writeHead(202)andres.end("Accepted")appear on earlier lines - PASS if response always precedes async work
- FAIL if any handler sends the response after starting async work
Output Format
Present results as a checklist:
## Build Verification Results
- [x] TypeScript build — passed
- [x] Config defaults — all ReviewConfig fields have defaults
- [ ] Config.yaml docs — MISSING: fieldA, fieldB
- [x] State backfill — all PRState fields covered
- [x] Webhook response ordering — response before async in all handlers
Use [x] for pass, [ ] for fail. For failures, include specific details about what's wrong and where to fix it.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/build-verifier-mm5t89b3/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/build-verifier-mm5t89b3' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/build-verifier-mm5t89b3/download' --output '.skill-downloads/build-verifier-mm5t89b3/SKILL.md.part' && mv '.skill-downloads/build-verifier-mm5t89b3/SKILL.md.part' '.skill-downloads/build-verifier-mm5t89b3/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/build-verifier-mm5t89b3/SKILL.md' && test -s '.skill-downloads/build-verifier-mm5t89b3/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/verify-build' && cp -R '.skill-downloads/build-verifier-mm5t89b3' '.claude/skills/verify-build'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/build-verifier-mm5t89b3'openskills read 'build-verifier-mm5t89b3'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/build-verifier-mm5t89b3/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.