mike-diff
- 46 skills
- 0 followers
- 4 hours ago last updated
- ▌ Dev 2 · mike-diff bundleImplement a feature end-to-end with external verification gates. Implements directly by default, delegates to subagents when work genuinely decomposes. Supports spec-backed runs, autonomous multi-phase sweeps, and an unattended mode (--unattended) for headless/CI runs.
- ▌ Ask 2 · mike-diffAsk numbered clarifying questions before proceeding with a task. Use when requirements are ambiguous or key details are missing.
- ▌ Dev 3 · mike-diff bundleImplement a feature end-to-end with external verification gates. Implements directly by default, delegates to subagents when work genuinely decomposes. Supports spec-backed runs, autonomous multi-phase sweeps, and /multitask parallelism.
- ▌ Spec 2 · mike-diff bundleGenerate a right-sized feature specification with acceptance criteria, self-contained phases, and transcript-verifiable goal conditions. Use when you know what to build.
- ▌ Spec 3 · mike-diff bundleGenerate a right-sized feature specification with acceptance criteria, self-contained phases, and safe parallelization guidance for Cursor. Use when you know what to build and need a spec ready to hand to /dev.
- ▌ Issue 2 · mike-diff bundleFetch a GitHub issue, explore the codebase, ask clarifying questions, and produce an implementation plan. Stops before building — hand off to /dev when ready. Use when planning implementation from a GitHub issue.
- ▌ Skill 2 · mike-diff bundleCreate a new Agent Skill in .cursor/skills/ following the agentskills.io specification. Use when creating skills, writing SKILL.md files, setting up skill directory structures, or validating skill frontmatter. Delegates to skill-author subagent using TDD methodology.
- ▌ Orient 2 · mike-diffBuild comprehensive understanding of a codebase. Maps tech stack, architecture, entry points, and patterns. Use when starting work on an unfamiliar codebase or onboarding to a new project.
- ▌ Ticket 2 · mike-diff bundleCreate a well-structured GitHub issue through a guided interview. Explores the codebase first, asks batched questions, previews the issue, then runs gh issue create. Use when creating new GitHub issues.
- ▌ To Dos 2 · mike-diffGenerate detailed, actionable developer tasks using TodoWrite with rich descriptions, dependency tracking, and verification steps. Use when breaking down a feature or change into implementation tasks.
- ▌ Discuss 2 · mike-diff bundleExplore a rough idea through conversation and parallel background research. Produces a validated plan with an adversarial check. Hands off to /spec or /dev.
- ▌ Discuss 3 · mike-diff bundleExplore a rough idea through conversation and background research. Produces a validated plan with an adversarial check and an ADLC handoff. Use when thinking through a feature before building or revisiting an existing implementation.
- ▌ Primitives 2 · mike-diffEnumerate all native Cursor tools, modes, and configuration primitives available in the current session. Use when verifying what tools are available before writing agents or hooks, or after a Cursor update.
- ▌ Dev 4 · mike-diff bundleImplement a feature end-to-end with external verification gates. Implements directly by default, delegates to subagents when work genuinely decomposes. Supports spec-backed runs, autonomous multi-phase sweeps, and an unattended mode (--unattended) for headless/CI runs.
- ▌ Spec 4 · mike-diff bundleGenerate a right-sized feature specification with acceptance criteria, self-contained phases, and transcript-verifiable goal conditions. Use when you know what to build.
- ▌ Issue 3 · mike-diffFetch a GitHub issue, explore the codebase, ask clarifying questions, and produce an implementation plan. Stops before building.
- ▌ Skill 3 · mike-diff bundleCreate a new Agent Skill in .claude/skills/ following the agentskills.io specification. Use when creating skills, writing SKILL.md files, setting up skill directory structures, or validating skill frontmatter. Delegates to skill-author teammate using TDD methodology.
- ▌ Ticket 3 · mike-diffCreate a GitHub issue through a guided interview. Explores the codebase first, asks batched questions, previews, then runs gh issue create.
- ▌ To Dos 3 · mike-diff bundleGenerate detailed, actionable developer tasks using TaskCreate with rich descriptions, dependency tracking, and owner assignment.
- ▌ Discuss 4 · mike-diff bundleExplore a rough idea through conversation and parallel background research. Produces a validated plan with an adversarial check. Hands off to /agent-team:spec or /agent-team:dev.
- ▌ Slop Check 2 · mike-diff bundleRun tool-driven code quality analysis then apply LLM judgment for cleanup. Use when cleaning up a codebase, removing slop, dead code, or improving code quality. Two-phase approach: static analysis tools find problems, agent judges what to fix.
- ▌ Loop Patterns 2 · mike-diffRecommended /loop patterns for the agents shipped in this repo (explorer, implementer, reviewer, qa, skill-author). Activates when the user asks about /loop, polling, watch-mode, periodic tasks, or autonomous iteration.
- ▌ Team Orchestration 2 · mike-diffDelegation and orchestration patterns for Claude Code — when to work directly vs delegate, subagents vs Workflow fan-outs, parallel write isolation, verification topology, and effort/model tiering. Use when coordinating subagents, running multi-agent work, or deciding whether to delegate at all.
- ▌ Dev · mike-diff bundleImplement and verify an approved feature, bug fix, or specification phase. Use when the user explicitly invokes $dev for ad hoc or spec-backed development, a named phase or multi-phase sweep, interactive or unattended local execution, with preflight, scoped implementation, reflection, independent review, QA, and a committed, pr-ready, blocked, or failed handoff.
- ▌
- ▌ Spec · mike-diff bundleCreate a right-sized, implementation-ready feature specification from a clear request or validated ADLC handoff. Use when the user explicitly invokes $spec to define acceptance criteria, boundaries, self-contained phases, and optional native Codex /goal prompts before development.
- ▌ Issue · mike-diffFetch a GitHub issue, explore the codebase, ask clarifying questions, and produce an implementation plan. Stops before building.
- ▌ Skill · mike-diff bundleCreate a new Agent Skill in .claude/skills/ following the agentskills.io specification. Use when creating skills, writing SKILL.md files, setting up skill directory structures, or validating skill frontmatter. Delegates to skill-author teammate using TDD methodology.
- ▌ Orient · mike-diffBuild a comprehensive understanding of the codebase. Maps tech stack, architecture, and patterns. Findings persist through project memory.
- ▌ Ticket · mike-diffCreate a GitHub issue through a guided interview. Explores the codebase first, asks batched questions, previews, then runs gh issue create.
- ▌ To Dos · mike-diff bundleGenerate detailed, actionable developer tasks using TaskCreate with rich descriptions, dependency tracking, and owner assignment.
- ▌ Discuss · mike-diff bundleExplore and validate a rough product or technical idea before implementation. Use when the user explicitly invokes $discuss to examine a new idea, revisit an existing implementation, study supplied references, compare approaches, surface risks, and produce an ADLC handoff for $spec or $dev.
- ▌ Debug Ops · mike-diffOperational guidance for Cursor's /debug command. Activates during root-cause-first troubleshooting and hypothesis-driven debugging.
- ▌ Primitives · mike-diffEnumerate all native Claude Code tools, modes, and configuration primitives available in the current session
- ▌ Slop Check · mike-diff bundleRun tool-driven code quality analysis then apply LLM judgment for cleanup. Use when cleaning up a codebase, removing slop, dead code, or improving code quality. Two-phase approach: static analysis tools find problems, agent judges what to fix.
- ▌ Canvas Ops · mike-diffOperational guidance for Cursor's Canvas artifacts. Activates when producing data-heavy, structured, or analytical outputs that benefit from rich formatting.
- ▌ Agent Team Dev · mike-diffRun the Agent Team dev workflow in pi for this repo. Use when implementing a validated feature or spec-backed phase end-to-end with an external verify gate and a committed, pr-ready, blocked, or failed handoff.
- ▌ Agent Team Spec · mike-diffRun the Agent Team spec workflow in pi for this repo. Use when turning a validated idea or ADLC handoff into a local, uncommitted, right-sized spec with acceptance criteria, self-contained phases and goal conditions.
- ▌ Goal Or Loop · mike-diff bundleDecides between the Claude Code /goal and /loop commands for a rough task, then emits a copy-paste-ready command block. Use when the mechanism is NOT yet chosen, for asks like should I use /goal or /loop, is this a goal or a loop, what is the best way to run this until it is done, set this up to run autonomously until X, or keep working on this unattended until it converges. Picks /goal (verifiable end-state provable from the transcript), /loop (cadence or waiting on an external clock), BOTH in sequence (terminal deliverable plus ongoing watch), or NEITHER (one-shot, needs human judgment, or unobservable). Triggers on keywords goal, loop, autonomously, until done, unattended, converge. Does NOT claim plain set up a recurring task / cron / poll every N minutes (that is loop-patterns) or schedule work that survives the session (that is schedule); and does NOT fire once the user has already typed /loop or /goal.
- ▌ Worktree Ops · mike-diffOperational guidance for Cursor's /worktree command. Activates when deciding whether to isolate a task in a dedicated worktree for parallel or risky work.
- ▌ Loop Patterns · mike-diffRecommended /loop patterns for the agents shipped in this repo (explorer, implementer, reviewer, qa, skill-author). Activates when the user asks about /loop, polling, watch-mode, periodic tasks, or autonomous iteration.
- ▌ Best Of N Ops · mike-diffOperational guidance for Cursor's /best-of-n command. Activates when running parallel model attempts and selecting the strongest result.
- ▌ Agent Team Discuss · mike-diffRun the Agent Team discuss workflow in pi for this repo. Use when exploring a feature idea before writing a spec or implementation plan, validating assumptions, or preparing an ADLC handoff for /skill:agent-team-spec or /skill:agent-team-dev.
- ▌ Review Patterns · mike-diffCode review patterns for spec compliance, quality verification, and reference integrity. Use when reviewing code changes, verifying implementation against requirements, or assessing code quality. Covers three-pass review method, severity levels, scope creep detection, security checks, and stale reference detection.
- ▌ Testing Patterns · mike-diffTesting patterns for running and writing tests across project types. Use when running lint, typecheck, or tests, writing new tests, setting up test infrastructure, or diagnosing test failures. Covers auto-detection of test frameworks, error categorization, and structured reporting.
- ▌ Team Orchestration · mike-diffDelegation and orchestration patterns for Claude Code — when to work directly vs delegate, subagents vs Workflow fan-outs, parallel write isolation, verification topology, and effort/model tiering. Use when coordinating subagents, running multi-agent work, or deciding whether to delegate at all.