Claude Skills by wlsdks

Audit a finished frontend change by measuring rendered rects and computed styles before using screenshots as human-checkable evidence.

Build UI from this repository's primitives and ramps in a deterministic order, then prove the rendered result with the matching instruments and gates.

Review only the Atlas structural commitments selected by design routing, using relevant seats, built evidence, optional conflict rebuttal, and one accountable guardian.

When Atlas design routing finds a structural commitment, sketch three different directions in text before code, including the status quo, and let the owner choose one.

Audit whether the design system is enforced at all: off-ramp values, parallel token systems, syntax and path blind spots, warning-only rules, and missing probes.

Prove a gate before trusting it. Inventory violations, plant a defect, verify RED, restore GREEN, prevent idle scans, and confirm automatic wiring.

Measure topology-map drag, pan, and zoom with a deterministic harness that proves it grabbed a real node instead of silently panning the background.

Verify canvas and UI motion with a real macOS recording, uniform 30fps frames, a visual phase strip, and frame-to-frame pixel-diff statistics.

Read a wiki page through a user-registered third-party MCP, classify it with absorb_document dry-run, obtain approval, and land only approved candidates with the source URL cited.

Build a trustworthy first ontology from an empty or near-empty ontology-atlas vault using only Atlas MCP evidence. Use when the user asks to analyze a codebase, bootstrap/fill its ontology, extract product meaning from a repository, or when a requested ontology task finds only starter nodes. Separate observed implementation facts from proposed meanings, define and cite every domain/capability, answer competency questions, obtain independent source-hidden qualification and user approval, then ...

Extract a small, evidence-bound set of ontology candidates from prose, check the existing vault for duplicates, obtain user approval, and land only the approved nodes and relations.

Measure whether Atlas actually works on a repository nobody here knows, by building a vault with a real MCP agent and then handing that vault — without the source — to a second agent who must answer questions from it alone. Use when changing the construction rules, the MCP read/write contract, the bootstrap skill, or whenever someone asks "is this getting better?" and the honest answer is a number nobody has. Produces four measurements against a recorded baseline. Skip for UI work, copy edits...

After a code change, sync the project's ontology vault — read what's already there, identify new capabilities / elements / domains introduced by the change, and write them back via the MCP server (or fall back to the CLI). Use this at the end of any task that introduces a new feature, refactors a module, or renames a unit. Skip when the change is purely a typo, style nudge, or test fixture tweak.

Write a subagent brief that isolates ports, files, worktrees, scratch output, baselines, and primary evidence before parallel work begins.

Review a hard-to-reverse Atlas product decision with Evidence plus one risk specialist, testing whether it restores a named human ability.

Route Atlas product work from observable change facts and one human-recovery outcome; use a compact solo pass for reversible work.

Live-verify layout across tablet, laptop, and wide breakpoints by measuring rects, elementFromPoint occlusion, bottom-tab reserve, and screenshots.

Walk one complete journey against the running build with a declared knowledge state, name observable UX failure patterns, and refuse to invent whether a person would want the product.

Audit a finished frontend change by measuring rendered rects and computed styles before using screenshots as human-checkable evidence.

Build UI from this repository's primitives and ramps in a deterministic order, then prove the rendered result with the matching instruments and gates.

Review only the Atlas structural commitments selected by design routing, using relevant seats, built evidence, optional conflict rebuttal, and one accountable guardian.

When Atlas design routing finds a structural commitment, sketch three different directions in text before code, including the status quo, and let the owner choose one.

Audit whether the design system is enforced at all: off-ramp values, parallel token systems, syntax and path blind spots, warning-only rules, and missing probes.

Prove a gate before trusting it. Inventory violations, plant a defect, verify RED, restore GREEN, prevent idle scans, and confirm automatic wiring.

Measure topology-map drag, pan, and zoom with a deterministic harness that proves it grabbed a real node instead of silently panning the background.

Verify canvas and UI motion with a real macOS recording, uniform 30fps frames, a visual phase strip, and frame-to-frame pixel-diff statistics.

Read a wiki page through a user-registered third-party MCP, classify it with absorb_document dry-run, obtain approval, and land only approved candidates with the source URL cited.

Build a trustworthy first ontology from an empty or near-empty ontology-atlas vault using only Atlas MCP evidence. Use when the user asks to analyze a codebase, bootstrap/fill its ontology, extract product meaning from a repository, or when a requested ontology task finds only starter nodes. Separate observed implementation facts from proposed meanings, define and cite every domain/capability, answer competency questions, obtain independent source-hidden qualification and user approval, then ...

Extract a small, evidence-bound set of ontology candidates from prose, check the existing vault for duplicates, obtain user approval, and land only the approved nodes and relations.

Measure whether Atlas actually works on a repository nobody here knows, by building a vault with a real MCP agent and then handing that vault — without the source — to a second agent who must answer questions from it alone. Use when changing the construction rules, the MCP read/write contract, the bootstrap skill, or whenever someone asks "is this getting better?" and the honest answer is a number nobody has. Produces four measurements against a recorded baseline. Skip for UI work, copy edits...

After a code change, sync the project's ontology vault — read what's already there, identify new capabilities / elements / domains introduced by the change, and write them back via the MCP server (or fall back to the CLI). Use this at the end of any task that introduces a new feature, refactors a module, or renames a unit. Skip when the change is purely a typo, style nudge, or test fixture tweak.

Write a subagent brief that isolates ports, files, worktrees, scratch output, baselines, and primary evidence before parallel work begins.

Review a hard-to-reverse Atlas product decision with Evidence plus one risk specialist, testing whether it restores a named human ability.

Route Atlas product work from observable change facts and one human-recovery outcome; use a compact solo pass for reversible work.

Live-verify layout across tablet, laptop, and wide breakpoints by measuring rects, elementFromPoint occlusion, bottom-tab reserve, and screenshots.

Walk one complete journey against the running build with a declared knowledge state, name observable UX failure patterns, and refuse to invent whether a person would want the product.

글에서 개념 뽑기. 회의록·기획서·PR 설명에서 개념 후보를 뽑되 중복부터 먼저 확인한다. 사람이 고르기 전에는 쓰지 않는다. "이 글에서 뽑아줘" · "이 문서 반영해줘" 일 때 쓴다.

다음 한 걸음. 이 볼트에 무엇을 더하면 값이 가장 큰지 후보를 근거와 함께 뽑아 보여 준다. 사람이 고르기 전에는 한 글자도 쓰지 않는다. "다음에 뭐 채워" · "빈 곳 찾아줘" · "더 넣을 거 있어" 일 때 쓴다.

볼트 점검. 지금 어긋난 곳과 끊긴 곳을 찾아 사람 말로 정리하고, 각각을 고치는 정확한 호출을 함께 낸다. 아무것도 고치지 않는다. "어디가 문제야" · "점검해줘" · "성한지 봐줘" 일 때 쓴다.

Pull concepts out of prose (meeting notes, specs, PR descriptions), checking for duplicates first. Writes nothing until a person picks. Use for "extract from this" · "fold this document in".

The next step. Propose, with evidence, what would add the most to this vault. Writes nothing until a person picks. Use for "what should I fill in next" · "find the gaps" · "what's missing".

Review this vault. Find what is broken or disconnected, report it in plain language, and give the exact call that fixes each one. Writes nothing. Use for "what's wrong here" · "check the vault" · "is this healthy".