skills

Design, redesign, or review real interfaces, documents, illustrations, and related visual systems from their content, audience, intended action, and existing project direction. Use when creating UI, improving visual hierarchy or coherence, reviewing a rendered artifact, or when "the page works but feels generic/inconsistent". Also use to establish a continuing project's visual direction from selected references when none exists, or to turn an ambiguous style cue into provisional guidance for later design. Triggers include "design this interface", "redesign this page", "review the UI", "make these pages feel unified", "the direction is right but the components feel generic", "polish/refine the interface details", "align this logo or illustration with the product", "art direction", and "审美/视觉设计/组件细节/插画或品牌视觉统一/确立风格". Do not use for a purely functional code fix, naming task, or automatic aesthetic acceptance. Never impose a portable fixed style.

Build or revise an evidence-linked capability profile for a model execution setup by running repeated, representative real tasks under matched conditions. Use when comparing models, providers, plans, coding harnesses, or prompt/tool profiles for task allocation; when asking "which model is good enough for this work?", "evaluate this model", "compare model capability", "模型评测/能力画像/模型适合什么任务", or whether a characterized setup may have degraded. Do not use for provider setup, public leaderboard summaries, one-off response review, automatic routing, or a degradation verdict without an accepted baseline.

Use this Skill, not a named task Skill, when that Skill or capability is the object of user-level setup, installation, migration, or configuration. An installed or runtime-discovered copy is target evidence, not a desired source. If the human has not supplied the selected capability's source, return `NEEDS_INPUT` before reading it, inventory, lookup, planning, or action; never inspect secret values. Use for "set up my agents on this machine", "migrate my AI coding setup", "新设备配置 Codex/Cursor/Claude Code", "update my global agent workflow", or reconstructing selected skills, harness guidance, plugins, MCP, hooks, permissions, runtimes, and authentication prerequisites. Setup does not imply marketplace discovery, CLI/provider installation, or full-toolbox adoption. Do not use for project-local agent workflow design, fleet policy, sessions/caches, or unrelated dotfiles.

Build, verify, or selectively refresh a source-linked working model of a substantial project when later agents or tasks need to reuse its architecture, responsibilities, authority, state, causal, evidence, or change relations. Use for "initialize project cognition", "map this project for future work", "建立项目认知", "更新项目认知", "what existing cognition is invalidated by this change?", or when repeated tasks keep reconstructing the same project model. Do not use for a one-off code review, ordinary repository orientation, context-delivery configuration, or as a mandatory project setup step.

Review a proposed code change, staged diff, commit, patch, or pull request for decision-changing defects before acceptance or merge. Use when asked "review this code", "review the diff/PR", "can this merge", "find regressions", or when a consequential implementation needs an impact-aware independent review. Do not use to implement the change, process already-filed PR comments, settle an unaccepted architecture, review visual design, or orchestrate reviewers.

Audit whether a project's artifact layout still expresses its accepted design, then apply one smallest safe organization transition when a material gap exists. Use for "organize the repo", "组织架构", "根据地", stale project structure, source/projection confusion, or campaign residue. Not for ordinary file cleanup, system-module design, Sequence change, or skill authoring.

Design, audit, and verify how decision-relevant project information reaches an agent through the actual runtime. Use when an agent misses a governing boundary, receives irrelevant context, cannot discover an instruction or skill, or when deciding what should be always available, activated for a task, or retrieved on demand. Do not use to author domain knowledge, organize its source artifacts, write a one-off prompt, configure vendor hooks, or build an agent runtime.

Lightweight behavioral discipline for any development task — ground decisions in evidence, choose the smallest valid change, test before claiming done, and analyze the specific situation before applying a pattern. Triggers on "be more disciplined", "professional habits", "stop overengineering", "check your work", "don't guess", "bad habits", "test strategy", "meaningful tests", or "avoid test bloat"; also when an agent shows overconfidence, untested claims, or repetitive overengineering across tasks.

Decide the smallest truthful form for a repeated problem before designing its implementation: no new artifact, local instruction, durable decision record, skill, runtime, projection, or bounded campaign. Use when asking "should this be a skill?", "what form should this take?", "how should this capability exist?", "is this another agent/runtime?", "should we add a command or document?", or when a generic workflow would hide an authority, inheritance, or recurrence decision. Do not use for ordinary implementation after the form is already accepted.

Diagnose and improve how coding agents work in an existing project: project skills, AGENTS instructions, prompt and context delivery, tools or CLI surfaces, hooks, verification, handoffs, and agent-facing workflow. Use when an agent repeatedly misses scope or instructions, the owning agent-facing surface is unclear, several surfaces interact, agent experience is costly or confusing, or a user asks Codex to improve how agents work in a company repository. Start from observed project evidence, change the smallest owning surface, and verify behavior through the ordinary agent entry path. If the issue is already localized to a skill's trigger, prompt, context layering, or behavior evaluation and a dedicated skill-engineering method is available, use that method directly. Do not use for ordinary product features, generic CI or business workflows, one-off prompt wording, or a process redesign with no observed agent-action gap.

Choose and place a project, product, or concept name with its smallest useful definition and explanation. Use when naming a project or shared concept, defining terminology, clarifying status words, deciding where documentation belongs, or asking "what should we call this?" / "how should this be explained?" / "命名" / "术语" / "定义" / "说明". Do not use for branding, ordinary copyediting, one-off prose, or a Sequence change.

Move a non-trivial task through practice, observation, reflection, and the next smallest test without forcing a generic plan or feedback artifact. Use when a phase ends, an implementation or investigation must inform its next move, a prior attempt failed or produced ambiguous evidence, work is being resumed, or the user asks to turn results into the next bounded action. Do not use as a mandatory preflight for routine one-step work or when a more specific methodology already owns the live judgment.

Steward a project's fallible principle lineage: preserve source-bound research, turn only gate-passing inquiries into candidates, convene selective P-ID reviews, clarify interpretations, trial human-nominated alternates, and prepare human-only Sequence decisions. Use for reusable-principle research, candidate proposals, principle reviews, interpretation drift, alternate trials, or maintaining a principle-centered skill collection.

Design, rewrite, review, and test agent skills that improve a repeated agent action or judgment. Use when creating a skill, rewriting a SKILL.md, improving a known skill trigger or action layer, reducing skill-context bloat, or checking whether a skill instruction actually changes behavior. Triggers include "create a skill", "rewrite this skill", "review this SKILL.md", "improve this project skill", "skill design", and "test this skill prompt". If an agent-work failure has not yet been localized to a skill, let an agent-workflow diagnostic method identify the owning surface first.

Prepare an evidence-backed strategic recommendation when a project phase has settled, material conditions changed, or a human asks for short-, medium-, and long-horizon direction. Synthesizes verified phase evidence into a proposed Strategy Case with a principal contradiction, strongest preservation case, rolling horizons, mission candidates, and replan signals. It advises only: humans approve commitments, and Work Cells or other owners execute them. Do not use for ordinary task planning, implementation sequencing, or automatic portfolio management.

Analyze, plan, execute, and verify behavior-preserving structural code changes. Use when asked to refactor code across meaningful boundaries: split a large file or module, extract responsibilities, untangle dependencies, reorganize a package, migrate callers, or assess the impact of a consequential refactor. Do not use for routine local cleanup, feature work that intentionally changes behavior, project artifact organization, or an unsettled architecture choice.

Estimate the necessary work before converting it into agent tokens, time, or money. Use when comparing implementation options, setting an agent budget, choosing estimate granularity or error tolerance, planning a discovery probe, or asking "how much work is this really?" / "预算怎么估？" / "工作量评估" / "误差容忍度". Do not use to invent a token price, approve spend, or replace strategic choice, execution, or calibration evidence.

Operational deployer for the lidessen skills collection — wires harness config (CLAUDE.md / AGENTS.md / .cursor/) in a target project, injects an L1 expression of selected sequence principles, and reconciles when lidessen evolves. Triggers on "/setup-lidessen-skills", "set up lidessen skills", "wire lidessen into this project", "sync lidessen principles", "install lidessen skills". Use after cloning or symlinking lidessen skills into a project, when adopting the collection, or when lidessen has new content the project hasn't picked up. Args — `init` to scaffold, `sync` to re-align with current lidessen, `audit` to check drift without writing. Pairs with harness (portable methodology); this is the lidessen-specific application layer.

Refactoring existing articles or drafts using a code-refactoring metaphor — extract information units (facts, claims, examples, metaphors) into a neutral inventory, rewrite the skeleton for a new thesis or audience, then inline units with expansion, compression, or transformation. Triggers on "重构这篇文章", "把这几篇合并改写", "用这些素材重写一篇", "这篇骨架我想换但素材想保留", "把旧博客整理重写", "refactor this article", "restructure this draft". Use to restructure existing pieces, merge drafts, repurpose for a different audience, or salvage old writing. Do NOT trigger for writing from scratch (use technical-article-writing) or light polish (use technical-article-writing's `revise`).

Design-driven development methodology — the design/ directory is the single source of architectural truth; read it before coding, stay within its boundaries, and update it first when the system's shape changes. Use whenever starting development on this project, or when the user asks to create/update architecture docs, add a feature that may cross existing boundaries, refactor system structure, or understand the codebase architecture. Triggers on "design first", "update the design", "does this change the architecture", "write a design for", "what's the current design", or onboarding to a codebase's shape. Args — `/design-driven init` to configure a project, `bootstrap` to generate design from existing code, `audit` to reconcile design/ against current code.

Evidence-driven methodology for the execution layer — every claim of progress requires a falsifiable observation; "looks right to me" is rejected. Use for production code, regression-prone systems, or any task where build-time discipline materially affects outcome quality. Triggers on "set up TDD", "build discipline", "no progress without evidence", "test-first", "verify rigorously", "production code workflow". Do NOT trigger for prototypes, exploratory spikes, throwaway scripts, or doc-only changes. Pairs with design-driven (which defines what to verify; evidence-driven defines how) — each works alone. Args — `/evidence-driven init` to wire up agent configs and optional pre-commit hooks. No periodic-audit command; it's an always-on overlay.

Goal-driven methodology for multi-week initiatives where the destination is clearer than the path — GOAL.md as stable compass (General Line plus falsifiable success criteria), record captures what was tried and observed. Triggers on "set a goal", "track my progress on X", "this is exploratory", "I know the goal but not the path", or starting a months-long initiative without a clear technical shape. Use for research, exploratory features, learning projects with a shippable output, book/article series, job search, side-business launches. Do NOT trigger for single-task work, bug fixes, week-long features with a clear plan, vague aspirations ("be healthier"), habit tracking, or general life management. Pairs with design-driven (why/how-far vs what-shape) and runs parallel to reframe. Args — `/goal-driven set`, `review`, `close`.

Restructure a repository or workspace carrier when accepted design has moved ahead of legacy layout — inventory concrete state, derive a functional map, plan minimal retire/merge/regenerate waves, and verify hard constraints after each slice. Triggers on "整理项目", "清理旧内容", "restructure the repo", "retire legacy paths", "repo cleanup", "carrier refactor", "保留新设计清理旧的", "project housekeeping after regeneration". Use after target architecture or design truth exists; not for unsettled paradigm exploration or Sequence change. Args — inventory, plan, execute, verify.

Designing in territory where the industry is still groping for shape — AI-native systems, agent-first interfaces, any domain whose category is forming. Triggers on "AI native X", "agent-first X", "redefine X", "rebuild X from scratch under Y", "reframe X for Y", "what should X look like in the new paradigm", "design a system with no precedent", or the tension between "new shoes on the old path" and "a skeleton that holds on its own". Method — strip to 3-5 abstract functions, redraw the load-bearing skeleton from the new paradigm's primitives, stress-test without traditional crutches, then add familiar flesh as projection. Do NOT trigger for incremental redesigns within an existing paradigm (use design-driven), explanatory writing (use technical-article-writing), or vague "make it AI" requests. Pairs with design-driven (upstream) and goal-driven (parallel). Args — `/reframe init`, `close`, `explain [for <audience>]`.

Methodology for writing argumentative technical articles — pieces that convince the reader of a specific claim through a chain of reasoning. Use when the user wants a technical article, essay, or book chapter that takes a position — introducing a new idea, challenging an accepted one, or arguing for a particular approach. Triggers on phrases like "write an article/essay/chapter about X," "make the case for X," "argue that Y," or structuring a multi-chapter argument about agents, architectures, systems design, or methodology. Do NOT trigger for tutorials ("how to do X"), reference or API documentation, release notes, changelogs, or pure explainers where no claim is being argued — those need a different framework.

Writer voice profile — an MBTI-inspired adaptive assessment that captures a person's cross-genre writing taste and style preferences. Use when the user wants to build or update their writing profile, calibrate AI writing tools to their voice, or find out "what kind of writer am I". Triggers on phrases like "写作画像", "writing profile", "writer type", "我是什么类型的作者", "测一下我的写作风格偏好", "calibrate my writing voice", or any explicit mention of building a writer profile. Produces a file at `~/.claude/writing-profile/profile.md` that downstream writing skills (technical-article-writing, future blog/diary skills) read to adapt AI output to the user's voice.

Restructure and organize a repository through a staged campaign.