listener-he/java-harness-agent
42 skills
$npx skills add listener-he/java-harness-agentSkillInstalls
ac-verifyVerifies each AC against implementation in a single pass before Archive. TRIGGER: Phase 5 QA with AC ≤ 3 AND risk ≠ HIGH.adversarial-reviewRuns one-round adversarial critique. TRIGGER: HIGH-risk STANDARD — Explorer (Cat A), Propose/Review (Cat B/C).ai-pipelineOrchestrate the repo-aligned AI engineering pipeline (plan → decisions → eval → improve → cleanup → verify → archive) with explicit approval gates.ai-slop-cleanerCleans AI code slop via deletion-first workflow. TRIGGER: 'deslop' / 'AI slop' / bloated code; AI pipeline Phase 5.architecture-decision-recordsCaptures architectural decisions as ADRs. TRIGGER: 'ADR this' / 'record decision'; HIGH-risk Propose with irreversible choice…authoring-standardsEnforces format rules + Pre-Creation Protocol for Skill, Sub-agent, Rule files. TRIGGER: create any of them.blueprintTurn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects.brainstormingTurns an idea into a design with alternatives + constraints. TRIGGER: Propose opener for STANDARD.code-review-checklistRuns inline self-review checklist after writing TRIVIAL/LOW (PATCH) code. TRIGGER: PATCH, after Implement, before finalize.cognitive-bias-checklistScans reasoning for hallucination, overconfidence, anchoring. TRIGGER: Propose/Review AFTER decision-frameworks produces options (Zone G).decision-frameworksBuilds options via SWOT / 5-Why / First Principles. TRIGGER: Explorer/Propose with ambiguous problem or unknown root cause.deepinitDeep codebase initialization. Two outputs: (1) hierarchical CLAUDE.md files for human navigation; (2) a machine-readable context_brief.md that other skills…dispatching-parallel-agentsDispatch specialized sub-agents for 2+ independent task domains that have no shared state or sequential blocking dependencies.eval-harnessFormal evaluation framework with two operating modes: (A) Early-phase AC Definition — usable at Explorer phase to translate requirements into executable…external-researchLarge-scale external research across four trigger modes: (1) Pipeline plateau — breaking optimization bottlenecks when self-improve stalls; (2) Security/CVE —…greenfield-scaffoldStarting-from-scratch protocol for projects with no existing codebase.impl-planDecomposes a spec into a checkpoint plan before coding. TRIGGER: Propose, after brainstorming picks a design.incident-responseProduction emergency triage and post-mortem protocol. Phase 1: rapid triage (classify severity, identify blast radius, issue immediate mitigation).input-classifierClassifies raw input as PRD/Idea/Bug/Signal/Perf/Security/Compliance/Feedback → [Intake] routing block. TRIGGER: input has no @shortcut, >1 line.java-architecture-standardsLayer 1 (Architecture) for Java backend. Daily decisions you can make WITHOUT opening SKILL.md: - Red Lines: NO @PathVariable (use query string / request…java-coding-styleLayer 2 (Coding style) for Java. Daily decisions without opening SKILL.md: - 4 spaces (never tabs); K&R braces; always braces for if/for/while (no…java-testing-standardsDefines Java test standards: isolation, mocks, 3-scenario coverage (Happy/Exception/Edge). TRIGGER: writing or reviewing Java tests.linter-severity-standardShared OK/WARN/FAIL severity contract for every gate script under .claude/scripts/gates/.local-code-intelligenceGathers zero-cost context via BM25 wiki search + Java symbol index + failure memory. TRIGGER: Explorer phase, before reading source or writing Allowed Scope.migration-plannerA→B system migration protocol where the core requirement is behavioral equivalence, not new features.mybatis-sql-standardLayer 3 (Persistence). TRIGGER when touching mapper XML, SQL fragment, or table schema.product-manager-expertHandles PRDs: Mode A ingests → ACs+deps; Mode B generates a draft. TRIGGER: input-classifier tags PRD, or user asks for one.releaseRelease workflow executor — reads repo release rules, validates pre-release gates (tests, changelog, version bump), then guides step-by-step release execution.rememberClassifies session knowledge into project memory / notepad / docs. TRIGGER: Archive, after uncovering a non-obvious constraint or decision.root-cause-debugInvestigates root cause before any fix via Hierarchical Localization. TRIGGER: bug / test failure / runtime exception.security-review-checklistReviews Java backend for secrets, input validation, authZ, IDOR, data exposure, dependency safety. TRIGGER: HIGH-risk delivery or auth/data changes.self-improve“Repo-aligned evolutionary improvement loop with tournament selection.skill-authorDecides whether to author a SKILL.md. TRIGGER: 'create a skill', recurring workflow without one, broken trigger.skill-graph-managerManages the Skill Knowledge Graph + central index. TRIGGER: a skill's purpose/trigger/phase changes.skill-indexSkill navigator. List active skills, locate archived ones, choose the right sequence per scenario.spec-quality-checklistVerifies AI-generated docs (task_brief, specs, WAL) for clarity + actionability. TRIGGER: manually after drafting, before submit/gate.stakeholder-conflict-resolverResolves cross-stakeholder requirement conflicts → map + decision. TRIGGER: parties in conflict; adversarial-review Cat A CRITICAL; PRD contradictions.task-decomposition-guideDecomposes PRDs / EPICs into INVEST subtasks via Vertical Slicing. TRIGGER: Explorer/Propose with EPIC/PRD or multi-task scope.test-driven-developmentTDD discipline for STANDARD-profile Implement phase. Daily protocol without opening SKILL.md: - RED first: write the test from an AC, RUN it, confirm it fails.ultraqaCycles QA test → verify → fix until all ACs pass, with an Evidence Mapping Table (AC ↔ Test ↔ Result). TRIGGER: Phase 5 with AC ≥ 4 OR HIGH risk.using-git-worktreesCreate isolated git worktrees for parallel or risky implementation work.wal-documentation-rulesGoverns WAL fragment writes (domain/api/rules/data/architecture) at Archive. TRIGGER: STANDARD Archive, dimensions elected via h-archive.