hunter-party-go/party-hunter-go/SKILL.md
Run all 10 Go code quality hunters in parallel as subagents and write each report to a timestamped reports folder. Covers boundary, doc, invariant, security, simplicity, slop, smell, solid, test, and type hunters. Use when: running a full Go codebase audit, scanning all quality dimensions at once, preparing for a code review, or generating a comprehensive findings report.
npx skillsauth add skyosev/agent-skills party-hunter-goInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Orchestrate a full audit of a Go codebase by running all 10 hunter skills as independent subagents, each producing a focused report. Results land in a single timestamped folder for easy review and sharing.
If the user has not specified a target (file, package path, or directory), ask before proceeding. Do not guess — the hunters need a concrete scope to be useful.
reports/party-hunter-go/YYYY-MM-DDTHHMM/
Use the current timestamp. Create the folder before launching any subagents.
Run all 10 subagents in parallel. Pass the same target scope to each. Each subagent must load its hunter skill and return findings as a Markdown report.
| Hunter | Skill to load | Output file |
|--------------|-------------------------|-------------------|
| Boundary | boundary-hunter-go | boundary.md |
| Doc | doc-hunter-go | doc.md |
| Invariant | invariant-hunter-go | invariant.md |
| Security | security-hunter-go | security.md |
| Simplicity | simplicity-hunter-go | simplicity.md |
| Slop | slop-hunter-go | slop.md |
| Smell | smell-hunter-go | smell.md |
| SOLID | solid-hunter-go | solid.md |
| Test | test-hunter-go | test.md |
| Type | type-hunter-go | type.md |
Subagent prompt template (adapt per hunter):
Load and apply the {skill-name} skill to the Go code at {target_scope}.
Produce a structured Markdown report with:
- An executive summary (2-3 sentences)
- Findings grouped by severity (Critical / High / Medium / Low)
- For each finding: location, description, and a concrete fix suggestion
Return only the Markdown report — no commentary outside the report.
As each subagent completes, write its output to the corresponding file inside the reports folder. Do not wait for all subagents before writing — write as results arrive.
After all 10 subagents have finished, write summary.md to the same folder:
# Party Hunter Report — Go
**Target**: {target_scope}
**Date**: {timestamp}
## Hunter Results
| Hunter | Critical | High | Medium | Low | Total |
|------------|----------|------|--------|-----|-------|
| Boundary | … | … | … | … | … |
| … | | | | | |
## Cross-cutting Themes
{2-4 recurring patterns observed across multiple hunters}
## Top 5 Priority Issues
{Ranked list of the most impactful findings regardless of hunter}
Every report file must be valid Markdown. Finding counts in summary.md must match
the findings in individual reports. If a hunter finds nothing, write a one-line note
(No findings.) rather than an empty file.
development
Transforms vague feature ideas into precise, codebase-grounded technical requirements. Use when requirements are ambiguous/incomplete, the user struggles to describe behavior, terminology is unclear, or multiple concepts are mixed. Output is a requirements spec—NOT an implementation plan.
tools
Audit TypeScript type definitions for design debt — duplicated shapes, missing derivations, over-engineered generics, under-constrained type parameters, reinvented utility types, and disorganized type architecture. Type structure and maintainability, not type enforcement. Use when: reviewing type definitions for maintainability, reducing type duplication, simplifying over-engineered type-level logic, or reorganizing type architecture after growth.
development
Audit TypeScript test code for quality gaps — missing coverage on critical paths, brittle tests coupled to implementation, over-mocking, assertion-free tests, missing edge cases, and duplicated test setup. Focuses on test effectiveness, not production code structure. Use when: reviewing TypeScript test suites for reliability, reducing false-positive test failures, improving coverage of critical business logic, or cleaning up test debt.
tools
Audit TypeScript class and interface design for SOLID violations — god classes, rigid extension points, broken substitutability, fat interfaces, and concrete dependency chains. Focuses on responsibility assignment and abstraction fitness. Use when: reviewing class hierarchies, preparing for extension with new variants, reducing coupling between services, or improving testability of class-heavy code.