Explorar skills

Relentless delivery mode for complex, multi-step tasks. Use when: multi-file features, unclear root cause debugging, multi-angle research, architecture decisions with trade-offs. Activates parallel subagent dispatch and strict verification.

Internal Auto-Harness evaluator skill for sprint contract review before implementation. Use only inside the Evaluator subagent during review mode.

Internal Auto-Harness evaluator skill for final QA report aggregation. Use only inside the Evaluator subagent during final mode.

Internal Auto-Harness evaluator skill for sprint retest and retest report writing. Use only inside the Evaluator subagent during retest mode.

Use when predicting Threads post performance, analyzing post history patterns, estimating engagement ceiling for a draft, or deciding what content type to write next. Works with or without personal data — uses darkseoking benchmark as fallback.

Persistent vector memory for Claude Code via LanceDB. Use when: remembering across sessions, storing lessons, recalling past decisions, maintaining context continuity. Tools: memory_store, memory_recall, memory_update, memory_forget, memory_merge.

Internal Auto-Harness planning skill for parallel clarification intake. Use only inside the Planner subagent when it is producing .harness-parallel/intake.md and .harness-parallel/status.md.

Test skill for verifying installation. Triggers on the phrases 'hello, test' and 'привет, тест'.

Internal Auto-Harness evaluator skill for sprint QA and QA report writing. Use only inside the Evaluator subagent during qa mode.

Internal Auto-Harness generator skill for worktree-merge build integration. Use only inside the parallel Generator integrator during build mode.

Internal Auto-Harness generator skill for one temporary fix bug batch in a dedicated worktree.

Harness Engineering 設計模式 — 基於 Claude Code 原始碼逆向分析的 12 條可遷移原則。Use when: 設計 agent 系統架構、實作 tool orchestration、設計 context 管理策略、建構 agent loop。