Speckit.checker
Static Analysis Aggregator - Run static analysis on the codebase.From its SKILL.md
npx -y skills add wedabro/bro-skills --skill speckit.checkerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
- runs commandsInstructs the agent to run 1 command, including `docker compose ... config`.
SKILL.md
3.0 KB, 642 tokens by cl100k_base, as published. Nobody here has run it
π― Mission
Detect coding-standard violations, security issues, and performance anti-patterns using commands appropriate to the actual project stack. MUST run applicable checks β do not claim a check passed from visual review.
π₯ Input
- Source code and dependency manifests
.agent/memory/constitution.md(coding standards).agent/project.jsonand documented build/test commands- Docker files when the project is containerized
π Protocol
Phase 1: Capability Discovery
- Read project configuration and dependency manifests.
- Detect language, package manager, containerization, services, and available build/lint/type-check scripts.
- Build an applicability table. Mark unavailable checks
N/Awith a reason; never treatN/Aas a pass or failure.
Phase 2: Compile, Type, and Lint Checks
- Run the repository-defined compile, type-check, and lint commands.
- If the constitution requires container execution, run them in the matching service. Otherwise use the project's documented runtime.
- Compiler/type errors are π΄ CRITICAL. Lint severity follows project policy.
- Do not assume TypeScript, npm, a monorepo, or fixed service names.
Phase 3: Container Checks (When Applicable)
- Validate every discovered Compose file with
docker compose ... config. - Verify Dockerfile COPY sources, non-root production runtime, health checks, environment-driven published ports, and no production source shadowing.
- If the project is not containerized, record this phase as
N/A.
Phase 4: Configuration and Security
- Scan source and tracked files for likely secrets, unsafe URL/endpoint literals, injection sinks, unsafe HTML, dynamic evaluation, and SQL concatenation.
- Exclude generated/vendor directories and report redacted locations only.
- Treat intentional public URLs, documentation links, and schema identifiers
according to project policy rather than flagging every
https://literal.
Phase 5: Stack-Specific Integrity
- Apply framework checks only when that framework is detected.
- For monorepos, verify package exports and cross-package contracts.
- For server-rendered applications, inspect build-time data fetching and error behavior according to the framework and project requirements.
π€ Output
- File:
.agent/memory/checker-report.md - Format:
## π΄ CRITICAL (N issues) - `apps/web/src/app/page.tsx:65` β Property 'category' does not exist on type 'Article' ## π‘ WARNING (N issues) - `compose.prod.yml:40` β Source mount overrides the built production artifact ## π’ INFO (N issues) - ...
π« Guard Rails
- Report ONLY β DO NOT edit the code yourself.
- Each finding must have a specific file path + line number.
- MUST run every applicable configured check; visual scanning alone is not enough.
- If there is π΄ CRITICAL β FAIL conclusion, deployment is NOT allowed.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.