菜单
SkillsMP 已收集 Tzeusy/ai-bootstrap 中的 62 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 40 / 62 个已收集 Skill。
Use for project-level engineering governance in any repository — bootstrap or audit the knowledge architecture (doctrine, specs, topology, standards), concretize a feature request into a spec delta, amend a spec found wrong mid-implementation, reconcile specs…
原文语言：英语
Use when analyzing or bootstrapping the five-pillar knowledge architecture of a software project: about/heart-and-soul (doctrine), about/legends-and-lore (RFCs/design contracts), about/lay-and-land (topology), about/craft-and-care (execution-quality…
原文语言：英语
Use for engineering-quality work on any change or codebase — holding an implementation or review to the engineering quality bar, code readability, test-suite rigor, module boundaries and dependency chains, diagnosing hard bugs and flaky failures to root…
原文语言：英语
Use when judging or improving the quality of tests — whether they assert behavior, cover edge and failure paths, protect against regressions, and stay trustworthy — in a diff, test suite, or review; also suite-level health: tier structure…
原文语言：英语
Use when auditing or designing module boundaries and dependency chains — dependency direction, layering, cycles, public surface area, and third-party dependency admission or upgrades — in a codebase, package, or proposed change.
原文语言：英语
Use when implementing or reviewing any non-trivial change and you need the canonical engineering quality bar — default biases, definition of done, and reviewable expectations — or when authoring a project's about/craft-and-care pillar that should reference…
原文语言：英语
Use for hygiene of this machine's AI-tooling harness — the ~/.dotfiles repo, the ai-bootstrap skills tree, and the installed tool homes (~/.claude, ~/.codex, ~/.gemini): auditing real skill usage from transcripts, archiving unused skills, reviewing dotfiles…
原文语言：英语
Use to re-run the harness's snapshot/mirror flows so installed state matches version-controlled source — skill symlinks into ~/.claude, ~/.codex, ~/.gemini tool homes, git submodule pointers, and shell plugin checkouts. Use after restructuring skills, when…
原文语言：英语
Use when deciding what a project should work on next, comparing competing priorities, deriving a milestone from VISION, brainstorming new feature candidates that fit the project's doctrine, sequencing an approved specification into an execution graph, or…
原文语言：英语
Use for a recurring, generative pursuit run that closes the gap between what a project is today and the ideal its doctrine describes: fan-out audits of every surface against the applicable quality bar, vision-grounded ideation lenses, synthesis into a ranked…
原文语言：英语
This skill should be used when asked to create a dev.sh (or similar) bash script that launches an application's full stack in tmux. It guides research of the project's services, generates an idempotent tmux bootstrap script with named windows, pane-ID-based…
原文语言：英语
Use when you need to inspect a target repository and generate a repo-grounded prerequisite curriculum in `curriculum/` that teaches the fundamental technical concepts someone must know before the codebase will make sense or be safe to change.
原文语言：英语
Use for UI/UX design work on anything with a user surface — web UI, TUI, CLI ergonomics, dashboards, internal tools — holding a design, spec, mockup, or implementation to the owner's design bar, or building/styling distinctive production-grade frontends. The…
原文语言：英语
Use when designing or reviewing anything with a user surface and you need the canonical design quality bar — default UX biases, the UX walkthrough ritual, and the definition of done — or when resolving conflicts between design subdomain findings.
原文语言：英语
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components,…
原文语言：英语
Use when choosing or reviewing colors, typography, spacing, component styling, or motion/animation for a user surface — establishing consistent visual semantics, bootstrapping a project design system (tokens, scales, recorded meanings), judging whether an…
原文语言：英语
Use for any Beads (`bd`) issue workflow in a Beads-backed repository — coordinating unattended execution of ready issues across parallel workers, implementing a single dispatched issue in a worktree, handling PR-review follow-up tasks, reconciling stale…
原文语言：英语
Use for any work on a blog post — deep editorial review for publication readiness (narrative, structure, scannability, factual risk, tone) or mechanical publish-hardening (frontmatter normalization, MD/MDX safety fixes, structural scaffolding, asset hygiene).…
原文语言：英语
Deep editorial review for publication readiness — narrative, structure, scannability, factual risk, tone, and reader usefulness. No silent rewrites.
原文语言：英语
Auto-format and harden a blog post for build + publish — frontmatter normalization, MD/MDX safety fixes, structural scaffolding, and asset hygiene. Minimal editorial judgment.
原文语言：英语
Use when creating, updating, reviewing, or auditing a skill or superskill and you need a concrete quality bar for triggers, project grounding, metadata, authorship, routing, context efficiency, scripts, and validation.
原文语言：英语
Use when a coordinator dispatches a dedicated `pr-review-task` bead for an open GitHub PR that needs review follow-up, thread triage, merge assessment, or retry handling in an isolated worktree.
原文语言：英语
Use when implementing exactly one Beads issue in a dedicated worker worktree after a coordinator or operator provides ISSUE_ID and WORKTREE_PATH.
原文语言：英语
Use when a Beads coordinator needs to reconcile stale worker state, PR-review bookkeeping, or orphaned worktrees before dispatching new work.
原文语言：英语
Coordinate Beads issue execution by continuously selecting the highest-priority ready issue from `bd ready`, claiming it atomically with `bd update --claim`, and dispatching a fresh worker in an isolated beads worktree. Use for unattended parallel issue…
原文语言：英语
Use when creating or decomposing Beads issues for a project backlog, including new features, bugs, epics, backlog grooming, or converting vague asks into actionable Beads work in a Beads-backed repository.
原文语言：英语
Use when one concrete feature or project request is still fuzzy and needs a signed-off behavior specification before planning or implementation, or when implementation reveals its governing spec is wrong, ambiguous, or incomplete. Triggers: "I want to add X",…
原文语言：英语
Use when auditing a repository's overall health, tech debt, maintainability, or architecture quality; processing a third-party repo-wide audit; or exhaustively reconciling OpenSpec specs against implementation. Triggers include "review this project", "audit…
原文语言：英语
Use when building or reviewing any user surface for accessibility — keyboard operability, focus management, contrast ratios, semantic markup and screen reader support, hit-target sizing, reduced motion — or when auditing an existing UI against WCAG-level…
原文语言：英语
Use when users can't find a feature, when adding a command palette or launcher (Spotlight/Rofi-style), when designing keyboard shortcuts and power paths, or when reviewing whether a product's features are findable and its frequent actions have fast routes.
原文语言：英语
Use when deciding what a screen, page, dashboard, table, or output says and in what order — calibrating information density, establishing visual hierarchy, tightening copy and labels, organizing layout, or laying out forms and their validation timing —…
原文语言：英语
Use when a user surface feels sluggish, when designing the responsiveness of a new interaction, or when reviewing perceived performance — latency budgets, preloading and caching strategy, optimistic rendering, loading states, notification and interruption…
原文语言：英语
Use when judging or improving how readable and maintainable code is — naming, function shape, abstraction altitude, comment discipline, and simplicity-over-cleverness — in a diff, module, or review, especially when code works but is hard to follow.
原文语言：英语
Use when reviewing or writing refactors, renames, or migrations where old interfaces may linger as aliases, re-exports, wrappers, fallback branches, deprecated flags, or other compatibility cruft. Especially relevant when changed code keeps both old and new…
原文语言：英语
Use when diagnosing a hard bug, intermittent/flaky failure, or performance regression and you need the evidence bar for the diagnosis itself — a repeatable feedback loop, ranked falsifiable hypotheses before instrumentation, tagged debug logging that gets…
原文语言：英语
Use when creating, reviewing, or auditing a codebase's documentation — README and docs/ trees, architecture/workflow diagrams, API references, formal doc sites (OpenAPI, MkDocs, Sphinx, ReadTheDocs) — and you need the bar for accessibility (concise synthesis,…
原文语言：英语
Use when the user wants a workflow, architecture, protocol, concept, or Mermaid diagram converted into or out of Excalidraw, especially when the result should teach through structure, flow, and concrete evidence.
原文语言：英语
Use to measure which installed skills are actually used, from Claude Code and Codex session transcripts, and to recommend archiving the ones that are not. Produces per-skill invocation counts over a window (default 30 days), exempts newly added skills, and…
原文语言：英语
Use to audit the non-skill recurring context surfaces of the AI tools — configured MCP servers (tool schemas load every session), permission allowlists, and hooks in settings.json / config.toml — against actual usage from transcripts, and recommend removing…
原文语言：英语
Use to compact agent memory stores that grow append-only and rot — AGENTS.md "Notes to self" sections, bd memories, CLAUDE.md instruction drift — by deduplicating, merging superseded entries, and retiring notes whose subject no longer exists. Triggers:…
原文语言：英语