Claude Skills by duc01226

[Implementation] Use when implementing a feature step by step.

[Documentation] Use when synthesizing specs, PBIs, ideas, and mockups into one standalone HTML slide deck for stakeholders.

[Frontend] Use when extracting design context from Figma URLs via MCP, REST API, or screenshot fallback.

[Implementation] Use when analyzing and fixing issues. Flag: --target={ci|issue|logs|test|types|ui} scopes the fix.

[Git] Use when resolving git merge, cherry-pick, or rebase conflicts with backup and analysis.

[Git] Use when generating developer KPI, contribution, story-point, man-day, or code-quality reports from git history.

[Git] Use when merging code from one branch to another.

[Code Intelligence] Use when analyzing the blast radius of current code changes via the knowledge graph.

[Code Intelligence] Use when building, updating, or syncing the code knowledge graph. Flag: --scope={full|update|sync} (default auto-detect).

[Code Intelligence] Use when detecting frontend-to-backend API connections via the knowledge graph.

[Code Intelligence] Use when exporting the code knowledge graph. Flag: --format={json|mermaid} (default json).

[Code Intelligence] Use when querying code relationships and connections via the knowledge graph.

[Code Intelligence] Use when tracing what happens as code executes, blast radius, or frontend-to-backend flows.

[Planning] Use when starting a new project from scratch — idea, research, domain modeling, tech stack, implementation plan.

[Quality] Use when setting up an agent quality harness with feedforward guides and feedback sensors.

[Project Management] Use when capturing new ideas, feature requests, or concepts for later refinement.

[Code Quality] Use when reviewing integration tests for assertion quality, bug protection, and repeatability, and verifying changed code has spec-traceable coverage.

[Testing] Use when driving an integration-test suite to fully green — verify, adjudicate each failure, fix at the owning layer, re-verify, until 2 consecutive green runs.

[Testing] Use when verifying integration tests pass after writing and reviewing them.

[Testing] Use when generating or reviewing integration tests.

[Fix & Debug] Use when investigating and explaining how existing features or logic work. Flag: --mode=explain gives a developer-narrative walkthrough.

[Utilities] Use when recording an engineering journal entry — decisions, blockers, lessons, progress notes.

[Research] Use when reviewing knowledge artifacts for completeness, citation quality, confidence accuracy, and template compliance.

[Research] Use when synthesizing research findings into a structured report.

[Utilities] Use when teaching Claude a lesson that persists across sessions.

[Code Quality] Use when running linters and fixing issues on backend or frontend.

[Quality] Use when configuring code quality tooling for a tech stack — linters, formatters, static analysis, pre-commit hooks, CI gates.

[Decision Support] Use when pressure-testing an irreversible, high-stakes decision with adversarial AI advisors.

[Content] Use when serving markdown files in a calm, book-like reading view over local HTTP.

[Document Processing] Use when converting Markdown to Word DOCX with GFM and math rendering.

[Document Processing] Use when converting Markdown to PDF with syntax highlighting and custom CSS.

[Research] Use when analyzing the market landscape — competitors, TAM/SAM/SOM sizing, trends, SWOT, customer segments.

[Utilities] Use when saving or recovering task progress across sessions via file checkpoints, especially before compaction.

[Code Quality] Use when analyzing package upgrades, outdated dependencies, npm/NuGet update plans, or breaking changes.

[Code Quality] Use when running an AI-assisted Dev BA PIC review of PBI drafts.

[Project Management] Use when generating an HTML mockup report from PBI and story artifacts.

[Document Processing] Use when converting PDFs to Markdown, including scanned documents via OCR.

[Debugging] Use when analyzing or optimizing performance — slow queries, N+1, indexing, API latency, memory/GC, concurrency, algorithmic complexity, caching, frontend rendering and Core Web Vitals.

[Planning] Use when the user supplies a plan file and asks to analyze it, assess impact, or verify planned changes.

[Implementation] Use when coding and testing an existing plan. Flags: --approval=off, --tests=off, --parallel={auto|on|off} (default off).

[Planning] Use when auto-reviewing a plan for validity, correctness, and best practices — recursive until the severity exit bar clears.

[Planning] Use when validating a plan through a critical-questions interview.

[Planning] Use when creating an implementation plan. Flag: --mode={ci|cro} (default standard); ci plans a fix from a CI run, cro plans conversion-rate optimization.

[Git] Use when creating a pull request in the standard format.

[Project Management] Use when prioritizing backlog items with RICE, MoSCoW, or Value-Effort.

[Utilities] Use when applying structured problem-solving frameworks to complex, blocked, recurring, or uncertain decisions.

[Project Management] Use when capturing ideas, managing backlogs, applying prioritization frameworks, or facilitating stakeholder communication.

[Planning] Use ONLY when the user explicitly requests a product roadmap, roadmap update, or milestone selection — outcome milestones, MVP scope, non-goals, risks, evidence gates.

[Code Quality] Use when reviewing service-layer and API changes for production readiness.

[Utilities] Use when scanning the workspace to update docs/project-config.json to match current structure.