其他技能

Explore a flow or layout with 3+ disposable lo-fi greyscale wireframes on a named axis. Use when the user wants to sketch directions or explore structure.

中文简介正在准备中。当前显示原文说明。

Use when balancing eng-team velocity vs quality vs burnout — on-call load, focus fragmentation, reorg shock. Triggers on 'team is burning out', 'why is velocity dropping'.

中文简介正在准备中。当前显示原文说明。

Use when stakeholders pull a decision in different directions — frames each lens, builds a trade-off matrix, surfaces the cost of every choice — even if the user just says 'PO and ops disagree'.

中文简介正在准备中。当前显示原文说明。

Use when orchestrating implementer/judge subagents — form gate + nine modes (do-and-judge ±two-stage, steps/parallel/worktrees, competitively, debate, live-app-judge, adversarial-council).

中文简介正在准备中。当前显示原文说明。

Use when modeling CAC, LTV, payback, contribution margin, or burn-multiple per customer — SaaS, marketplace, or transactional. Triggers on 'are we unit-economic', 'what is our LTV/CAC'.

中文简介正在准备中。当前显示原文说明。

Use when claiming 'done', suggesting a commit, push, or PR — runs the evidence gate so completion claims come from fresh output in this message, not memory or earlier runs.

中文简介正在准备中。当前显示原文说明。

Use when articulating internal vision — where we're going / why now / why us, founder-mode anchor, distinct from fundraising pitch. Triggers on 'what's our vision', 'why are we doing this'.

中文简介正在准备中。当前显示原文说明。

Use when extracting Voice-of-Customer themes from existing artefacts — GH issues, PR threads, Sentry patterns. Triggers on 'what are users saying', 'recurring complaints', 'top themes'.

中文简介正在准备中。当前显示原文说明。

Before adding/installing any dependency the agent named — verify the package exists (slopsquatting: ~1 in 5 AI suggestions are hallucinated), isn't typo-adjacent, is pinned + locked, and CVE-scanned

中文简介正在准备中。当前显示原文说明。

Use when a cross-workspace import will not resolve — cannot find module @org/*, TS2307 — to link the packages properly with the workspace: protocol instead of patching tsconfig paths.

中文简介正在准备中。当前显示原文说明。

Use when deciding 'should this be a skill or a rule?', creating/improving/reviewing agent skills, SKILL.md frontmatter, or procedure sections — even without saying 'skill-writing'.

中文简介正在准备中。当前显示原文说明。

Use when the user says "write a spec", "create RFC", "write a PRD", or "document this decision". Writes technical specifications, PRDs, RFCs, and ADRs with clear structure.

中文简介正在准备中。当前显示原文说明。

Use when authoring or rewriting a roadmap in agents/roadmaps/ — phases, goal, acceptance criteria, council notes; fires even on 'write a plan for X' / 'draft a roadmap'.

中文简介正在准备中。当前显示原文说明。

Turn a shipped changelog into a release narrative — value-not-feature framing, audience-segmented surfaces. Triggers on 'announce the release', 'write changelog post'.

中文简介正在准备中。当前显示原文说明。

Use when the user says "create roadmap", "show roadmap", or "execute roadmap". Creates, reads, and manages roadmap files with phase tracking.

中文简介正在准备中。当前显示原文说明。

Use when preparing a PR description, suggesting reviewers, or flagging risk — produces owner-mapped roles plus historical bug-pattern matches from project-local YAML.

中文简介正在准备中。当前显示原文说明。

Use before committing to a heavy or irreversible plan — imagine it's 6 months later and this failed; enumerate why, score each mode, derive early-warning signals and preventive guardrails.

中文简介正在准备中。当前显示原文说明。

Use when reviewing a README for accuracy, usability, and alignment with the actual repository. Detects invented content, broken setup steps, and structural issues.

中文简介正在准备中。当前显示原文说明。

Raw discovery primitives — project discovery, version resolution, docs loading, architecture mapping, execution flow. Called by `universal-project-analysis`. Single-pass scan → `project-analyzer`.

中文简介正在准备中。当前显示原文说明。

Use when reviewing a migration diff or schema change for scale hazards — indexes, unsafe migrations, unbounded growth, N+1. Triggers on 'review this migration', 'will this scale'.

中文简介正在准备中。当前显示原文说明。

Use when creating or rewriting a README for a reusable package or library. Focus on installability, minimal usage example, compatibility, and developer onboarding.

中文简介正在准备中。当前显示原文说明。

Use when constructing base / upside / downside scenarios — three-statement modeling, sensitivity analysis, optionality reasoning. Triggers on 'model the scenarios', 'what if growth halves'.

中文简介正在准备中。当前显示原文说明。

Use when creating, rewriting, or significantly improving a README based on the actual repository structure, commands, and intended audience.

中文简介正在准备中。当前显示原文说明。

Use when surfacing and prioritising risk before commit — blast-radius framing, mitigations, residual-risk verdict — even if the user just says 'what could go wrong here?'.

中文简介正在准备中。当前显示原文说明。