Menu
SkillsMP has collected 24 skills from Mrlyk/superharness. Open a skill to review its source and details.
Showing 24 of 24 collected skills.
Set up superharness in a project: scan the codebase to discover conventions and tech stack, write findings into .superharness/spec/, then distill them into AGENTS.md and CLAUDE.md. Use when the user asks to set up superharness, to scan or re-scan the codebase…
Session start guide: explains how to use superharness skills and conventions. Injected by SessionStart hook.
Generate a developer-facing efficiency and focus-area report for a completed Superharness task. Use when the user asks to "生成开发者报告", "开发交接报告", "to-coder", "developer report", or when /superharness:to-coder is invoked.
Generate a tester-facing change impact handoff for a completed Superharness task or a standalone current Git change without task artifacts. Use when superharness:finishing-a-development-branch offers the tester handoff, when the user asks to "生成影响范围",…
Use when an approved implementation plan will be executed inline in a separate session with batch checkpoints
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Main entry point for end-to-end feature work. Start a full task with /superharness:go 'requirement', a lite task with /superharness:go [lite] 'requirement', or resume with /superharness:go --task {task-id}.
Reopen a completed Superharness task to fix a post-delivery bug so the fix time keeps accruing to the same requirement. Use when the user reports a bug in work delivered by a completed task ("上次那个功能有 bug", "修一下之前任务的问题", "fix the bug from the last task"),…
Use when executing implementation plans with independent tasks in the current session
Use when implementing any feature or bugfix, before writing implementation code
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Use when you have a spec or requirements for a multi-step task, before touching code. Creates detailed, seam-first implementation plans with vertical TDD steps for superharness workflows.
Persist durable project learnings into a topic wiki. Use when the user asks "总结一下经验", "沉淀一下", or "记住这个"; when the user states a convention to persist ("保存为项目规范", "from now on use X"); when the user is correcting an answer or plan; when a verified belief…
Infrastructure skill: start a local visualization server that renders Mermaid diagrams in the browser. Write .mmd files with pure Mermaid code, and the browser updates in real-time via WebSocket. Use when the user requests a visualization during requirement…
Run an on-demand adversarial review of an already-written PRD or Plan with an available local provider.
Two-stage E2E skill: a gate check that decides whether the change has browser-verifiable UI behavior (writes e2e:gate-passed or e2e:skipped trace events, generates nothing), and a generation stage entered only after the user confirms generation. Generates…
Run E2E case verification via CLI. Parses cases, starts app, drives agent-browser, produces qa-issues.json + issues/ + process/. Called by QA after tasks pass review.
Fix QA issues from the current implementation revision using TDD, then automatically re-runs authorized QA.
Source text: Mixed languages
Single entry point for all verification. Auto-detects E2E cases and runs e2e-verify internally via CLI.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
A relentless interview that asks every frontier question at once, round by round. Invoked by superharness:go for new tasks.
Interview engine that grills the user about a requirement, plan, or design through relentless, structured questioning, asking 1-2 focused questions per turn until every branch of the decision tree is resolved. Use directly when the user explicitly asks to be…
Synthesis only, no interview: solidify an already-resolved requirement discussion into task artifacts (prd.md + task.json + contract.md), self-review, commit, and get user sign-off. Use after batch-grill-me, grill-me, or another discussion has resolved all…