본문으로 건너뛰기
cccskills
무료GitHub에 공개

project-workspace

Create and manage topic-specific project workspaces for validation, investigation, PoC, comparison, or workstreams, including meeting notes in an existing project. Use for a project workspace, cost comparison workspace, or project meeting notes. Triggers on プロジェクトワークスペース, 検証フォルダ, PoC ワークスペース, トピック別作業フォルダ, プロジェクトの議事メモ. Not for ongoing customer account operations or book manuscripts.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

연동 도구Azure
설치 방법 보기

포함된 파일(2)

  • SKILL.md8.0 KB
  • LICENSE.txt5.2 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Project Workspace Skill

Use this skill when the user asks to create, open, prepare, or organize a topic-specific project workspace, or to record a meeting in an existing project. Use a customer-specific workflow for customer account operations, and a transcription workflow when the source media still needs transcription.

Default location

  • When an active VS Code workspace is provided and the user is adding or organizing assets for the current task, use that workspace as the default target even without repo markers. Do not redirect it to an external project root.
  • When that workspace already manages a customer's ongoing work, add requested validation evidence under the confirmed topic and link to its existing status and actions. Do not create a second project workspace or parallel task ledger unless a separate workspace is explicitly requested.
  • Use the configured project root only when the user requests a separate project workspace or no active workspace target is available.
  • In CLI / Scout without active-workspace context, ask for a target folder when CWD does not identify a workspace. Do not infer an external project location.
  • Use Windows-style paths with backslashes.

Folder naming

  • Prefer concise kebab-case English folder names, for example:
    • azure-monitor-workspace-validation
    • joule-validation
    • customer-meeting-prep
  • If the user provides a Japanese or informal topic name, convert it to a clear English folder slug.
  • If a folder already exists, reuse it instead of creating a duplicate. If the requested name is ambiguous or would collide with an unrelated folder, ask before proceeding.

Creation flow

  1. Determine the intended project topic and folder slug.
  2. Resolve the target using Default location. Reuse an active workspace for in-place work; create a new folder under the configured project root only when a separate project workspace is requested.
  3. Default to creating a lightweight project package, not just an empty folder, when the request is for validation, investigation, PoC, comparison, customer explanation, screenshot collection, or when the user asks for viewpoints/criteria.
  4. If the user explicitly asks for only a folder, create the folder only and report the path.
  5. For large moves, renames, or destructive cleanup, follow dry-run -> confirmation -> execution.

Meeting notes in an existing project

  • Locate the project's existing meeting note or retrospective and update it; otherwise use a dated note in its notes folder if one exists, or alongside its existing records. Do not initialize a new project, create a customer workspace, or add meeting folders to the default package just for one meeting.
  • Record the meeting date, source (link to the original transcript or attachment when available), confirmed discussion and decisions, open questions, and follow-up actions. Assign owners and deadlines only when explicitly agreed; mark uncertain names, figures, and speech-recognition output as unverified.
  • Keep restricted source material in its existing authorized location. Do not copy confidential slides or raw transcripts into a shareable summary; distinguish what a participant proposed from an agreed commitment or outcome.
  • Verify that the note exists in the owning project and that unresolved questions and next actions are visible there or linked to an existing action record. Avoid a parallel task ledger.

Default project package

When creating a validation, investigation, PoC, or comparison workspace, create these artifacts by default unless the user asks otherwise:

README.md
validation-plan.md
notes\findings.md
screenshots\README.md
screenshots\01-source-or-baseline
screenshots\02-validation
screenshots\03-customer-story
exports

Adapt folder names to the topic when obvious. For example, a two-product comparison can use product-specific screenshot folders plus a comparison/customer-story folder.

If the user mentions cost, pricing, TCO, FinOps, billing, or comparing the cost of multiple options, also create cost-comparison.md with assumptions, measured usage, unit prices, formulas, screenshots/evidence, and final comparison notes.

Validation plan quality bar

validation-plan.md should be useful immediately, even before the user provides detailed requirements. Include:

  • Purpose and expected output.
  • Key questions or hypotheses to validate.
  • Scope and explicit non-goals.
  • Environment and prerequisites to prepare.
  • Step-by-step validation scenarios.
  • Evidence plan, including screenshot targets and naming convention.
  • Provenance for source material and screenshots; keep originals distinct from edited or shareable copies.
  • Comparison or decision criteria when there are multiple options.
  • Customer value story: what benefit the customer should understand from the validation.
  • Actual measurement scenarios for claims that require evidence. Do not stop at conceptual comparison when the user asks to "actually compare", "verify", "measure", or "cost compare".
  • Risks, caveats, and open questions.
  • Official references for Microsoft/Azure topics.

For Microsoft/Azure topics, verify important product facts with official Microsoft Learn, Azure pricing, or other Microsoft official sources before writing them into the artifact, and include source URLs.

Cost comparison plans

When the task includes cost comparison, the plan must define how cost will be measured or estimated, not only list pricing pages. Include:

  • The comparable workload or scenario.
  • What data each option actually stores or processes. If the services are not same-data alternatives, state that explicitly.
  • Usage drivers and units for each option, such as GB ingested, GB retained, metric samples, time series, queries, exports, or add-on services.
  • Baseline unit prices from official pricing sources or Azure Retail Prices API, with region, currency, and retrieval date.
  • Test runs that separate baseline, high-volume, and high-cardinality or high-retention cases where relevant.
  • Formulas for converting measured usage into daily/monthly estimates.
  • Evidence to collect, such as Cost Management screenshots, usage queries, pricing calculator/API output, and portal screenshots.
  • A note that actual billing can lag and should be reconciled with Cost Management after charges are reflected.

For Azure Monitor workspace versus Log Analytics workspace specifically, do not frame the comparison as putting identical data into both. Use the same monitored workload, send logs to Log Analytics workspace and Prometheus metrics to Azure Monitor workspace, then compare the actual cost drivers: log ingestion/retention for Log Analytics workspace versus metric samples/cardinality/query behavior for Azure Monitor workspace.

Reporting

  • Report the final path first.
  • Mention if an existing folder was reused.
  • Keep the response concise in Japanese.

Guardrails

  • Do not move or delete existing files unless explicitly requested or needed to fix a mistaken placement made in the current task.
  • Do not store secrets or credentials in project files.
  • Do not store user-machine-specific absolute paths in this private repo skill; keep those in local configuration or local installed skill copies.
  • For Microsoft/Azure validation plans, verify important facts with official Microsoft Learn/Azure pricing information and include source URLs in artifacts when applicable.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Design, review, and debug agent workflows, and decide when a request should use a prompt, instruction, skill, agent, or hook before escalating to multi-agent design. Use for .agent.md / .instructions.md / .prompt.md / AGENTS.md work, workflow architecture, orchestration planning, scheduled automation model allocation, or when agent workflows may be overkill. Triggers on 'agent workflow', 'create agent', 'automation models', 'ワークフロー設計', 'orchestrator'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aktsmm/Agent-Skills262026년 10월 19일 업데이트

Design, run, and review fair performance, token, and cost comparisons across GitHub Copilot CLI, Codex CLI, and direct model APIs. Use for AI CLI benchmark, Copilot vs Codex, prompt-cache diagnosis, cache read/write analysis, fresh-process latency measurement, token-cost comparison, or when a benchmark must separate provider caching from local CLI caches.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aktsmm/Agent-Skills262026년 10월 19일 업데이트

Analyze historical VS Code GitHub Copilot Chat sessions by model, reasoning effort, AIU, time, reliability, workflow behavior, and external quality evidence, or safely prune workspace-scoped local chat history by age. Use for session analysis, repeated-task retrospectives, model evaluation, cost/performance analysis, and old session cleanup.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aktsmm/Agent-Skills262026년 10월 19일 업데이트

Create reproducible animated infographic GIFs from structured data or measured results, with audience-language labels, explicit timing semantics, representative-frame QA, and a static fallback. Use when asked for GIF生成, animated infographic, 動的インフォグラフィック, 結果が流れる図, animated benchmark, or a blog/SNS animation whose displayed metrics must remain traceable to source data.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aktsmm/Agent-Skills262026년 10월 19일 업데이트

archify

무료

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and stateDiagram input; inspect repository evidence when the diagram must reflect real code. Use when the user asks to visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid. Also use for Archify, interactive or animated HTML diagrams, インタラクティブ図, 動く構成図. When an editable .drawio file is required, use the draw.io workflow instead and treat Archify HTML only as a supplement.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aktsmm/Agent-Skills262026년 10월 19일 업데이트

Generate ASCII-art text banners for terminals, READMEs, and CLI startup messages. Use when a user asks for an ASCII banner, text art, バナー, アスキーアート, or a decorative header for a script/README.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aktsmm/Agent-Skills262026년 10월 19일 업데이트

aktsmm의 스킬 모두 보기

이 스킬의 문제 신고