Results for “spec”

General implementation only when no narrower task or ecosystem skill fits. Do not combine with a clear specialist skill.

Write a 5-part mini spec (goal, constraints, acceptance criteria, verification, done gate) before starting any multi-step, externally-delivered, or risky task. Triggers when: a request has 3+ steps, touches external delivery, or is easy to declare done too early. NOT for: single lookups, one-line edits, routine acks, or simple factual answers.

Hierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.

Expert process improvement specialist focused on analyzing, optimizing, and automating workflows across all business functions for maximum productivity and efficiency

Open a GitHub PR dashboard in the browser for a specified date range and role filter.

Routes users to specialized business tools based on their current context: onboarding, pre-task routing, or post-task navigation.

Loads one or more predefined role files to focus work on a specific task, activated by commands like "role [name]".

Captures desktop screenshots on macOS, Linux, and Windows with support for full screen, specific apps, windows, and pixel regions.

Archives a completed change in the OpenSpec workflow, checking artifact and task completion, assessing spec sync, and moving the change directory.

Remove AI writing patterns from prose by cutting filler phrases, breaking formulaic structures, and enforcing active voice and specificity.

Generates CNC toolpaths, selects machining strategies and tools, optimizes cutting parameters, simulates operations, and post-processes to machine-specific formats.

Routes marketing questions to the right specialist skill, orchestrates multi-skill campaigns, and runs cross-functional marketing audits.

Runs a structured five-round brainstorm to capture actors, features, scope, constraints, and business rules before writing a spec.

Automatically log daily development progress, archive project-specific diaries locally, and sync a fused global diary to Notion or Obsidian.

Clarify requirements before implementing by asking targeted questions when a request has multiple plausible interpretations or key details are unclear.

Build and query AI-powered knowledge bases from claude-mem observations, enabling focused conversational sessions on specific topics.

Use when you have a spec or requirements for a multi-step task. Creates comprehensive implementation plans with bite-sized tasks, exact file paths, and complete code examples.

Archives a completed change in the OpenSpec workflow, checking artifact and task completion, assessing spec sync, and moving the change directory to the archive.

Defines a time-bounded, focused work session to produce a specific creative or productive output, tracking progress and completion.

当用户已有确认过的技术设计（理想来自 make-design），要在编码前把它拆成可独立验收、带依赖与验证方式的开发任务清单时使用——如"拆任务、把技术方案拆成开发任务、生成 tasks、列实现任务清单、把设计落地成可执行任务"。不要用于：技术方案还没定（先 make-design）、行为还没钉死（先 write-spec）、想法还模糊（先 refine-idea）、写具体实现代码或逐行施工单、调试、代码评审。

Implement chat-based user interface with selectable options, progressive disclosure, and workflow guidance for discipline-specific operations including procurement, civil engineering, and other domain workflows

Runs a structured, multi-round brainstorm to capture actors, features, scope, constraints, and business rules for a project before writing a spec.

Scaffolds a new ClawBio skill from a JSON/YAML spec or interactively, generating SKILL.md, Python skeleton, tests, and updating the catalog.

Provides a structured methodology for solving nontrivial, ambiguous problems by framing outcomes, selecting evidence, routing specialists, choosing options, and verifying results.

Orchestrate the full MoonSpec lifecycle from a preselected single-story feature request or active feature directory through specification, planning, TDD task generation, artifact alignment, implementation, and final verification. Use when the user asks for an end-to-end MoonSpec run and the input has already been routed to one independently testable story, or when Codex needs to coordinate `moonspec-specify`, `moonspec-plan`, `moonspec-tasks`, `moonspec-align`, `moonspec-implement`, and `moonspec-verify` without manual analyze/remediation prompts.

Restructure an academic paper's title and section structure to match a target journal's house style. Asks the user to specify the target journal first, then adjusts main.tex accordingly (title wording and case, section skeleton, heading case, numbering scheme, merging/splitting sections). Trigger when user says "paper style" / "paper-style" / "期刊风格" / "按目标期刊调整" / "调整为XX风格" / "JFE风格" / "convert to journal style" / "restructure for [journal]", or wants a paper's title/sections reformatted for a specific journal submission.

Delegates tasks to specialized AI agents running in parallel via the Box0 platform, enabling code review, security checks, research, and documentation.

Routes tasks to specialized agent offices and applies behavioral science frameworks to every output, with confidence tagging and session memory.

Scaffolds new agent skills conforming to the Agent Skills specification and dotnet/skills repository conventions, generating SKILL.md files with proper frontmatter and directory structures.

Fetch unread GitHub notifications for open PRs where review is requested from a specified team or opened by a team member.

Simulates multi-expert panel discussions by recommending or accepting specified experts, generating parallel dialogues, and providing a judge summary for each round.

Diagnoses whether a draft will resonate with its audience using a five-dimension communication psychology framework, identifies structural problems, and gives specific fixes.

Crafts concise, specific investor emails—outreach, warm intros, follow-ups, updates, and closing notes—with a clear single ask and strong proof points.

Surface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals. Recommends one specific action with rationale. Triggers on "/next", "what should I do", "what's next".

Orchestrates building a new feature end-to-end by delegating research, planning, TDD implementation, review, and gated commit to specialized agents.

Provides jurisdiction-specific legal context and contract scaffolding for the US, EU, and Canada, grounding agents in verified government references to reduce legal hallucinations.