Convert PDF/EPUB library to Markdown and generate Obsidian MOC notes
原文の言語: 英語
メニュー
SkillsMP は andrem-sec/psc-comet から 66 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
収集済み skill 66 件中 40 件を表示しています。
Convert PDF/EPUB library to Markdown and generate Obsidian MOC notes
原文の言語: 英語
Hook-based compaction suggestions at logical task boundaries
原文の言語: 英語
Context window management — track spend, decide when to compact, preserve state
原文の言語: 英語
Session-start orientation — loads context, surfaces learnings, confirms registry
原文の言語: 英語
Quality and semantic review — catches what automated tools miss
原文の言語: 英語
Planner → Architect → Critic deliberation loop — produces a formally validated ADR
原文の言語: 英語
Dual-dimension document quality gate — presentation rubric + hallucination grounding check
原文の言語: 英語
Model selection guidance — match task complexity to model capability
原文の言語: 英語
Scan task for high-cost branch points, confirm which get deep reasoning, execute with gates active
原文の言語: 英語
Resume an interrupted mid-task session — reconstructs state from context files and picks up at the right step
原文の言語: 英語
Full feature workflow — deep-interview → prd → consensus-plan → tdd → code-review → security-gate
原文の言語: 英語
Plan-mode enforcement — required before edits affecting 3+ files, cross-domain work, or security-sensitive changes
原文の言語: 英語
Session-end protocol — collect learnings, update context, commit session state
原文の言語: 英語
Framework for decomposing agent-driven tasks into independently verifiable units
原文の言語: 英語
Extract instinct candidates from the current session and add confirmed ones to the instinct store
原文の言語: 英語
Eval-driven development with pass@k metrics and three grader types
原文の言語: 英語
Capture codebase-specific knowledge as a reusable skill — passes 3-point quality gate before writing
原文の言語: 英語
Mid-session quick capture — save an insight before the context moves on
原文の言語: 英語
Auto-populate context/project.md by reading the current codebase
原文の言語: 英語
In-session memory tagging — mark content for recall later in the same session
原文の言語: 英語
Rules of Engagement authorization gate — required before any security operation, autonomous scanning, or action with real-world effects outside the local codebase
原文の言語: 英語
Pre-deploy security assessment — validates against OWASP Top 10 and project standards
原文の言語: 英語
Prevent algorithm confusion attacks when validating JWTs — RS256 tokens accepted as HS256
原文の言語: 英語
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind,…
原文の言語: 英語
Framework for designing quality agents with proper action space and contracts
原文の言語: 英語
Test specifically for AI-introduced regressions that repeat without tests
原文の言語: 英語
Audit animations and transitions for motion accessibility, performance safety, and design intent. Enforces prefers-reduced-motion compliance and blocks layout-triggering transitions.
原文の言語: 英語
Parallel agent swarm — decomposes work into independent units, spawns isolated workers, tracks PRs via fan-in
原文の言語: 英語
Performance measurement with Core Web Vitals thresholds — baseline capture, regression detection, optional PageSpeed Insights
原文の言語: 英語
Load and validate brand assets before any design work — logo, colors, typography, voice. Gates UI and marketing work behind confirmed brand context.
原文の言語: 英語
Post-deploy production monitoring — watches live app for errors, regressions, and failures after deployment
原文の言語: 英語
Named decision point for long-running tasks — PIVOT, REFINE, or PROCEED
原文の言語: 英語
4-phase systematic codebase onboarding with reconnaissance and artifact generation
原文の言語: 英語
Define component API, states, variants, and ARIA requirements before writing a line of implementation code. Gates component work behind a confirmed spec.
原文の言語: 英語
Token audit across agents, skills, and MCP with cost optimization guidance
原文の言語: 英語
Cross-session instinct learning with confidence-based promotion and global scope
原文の言語: 英語
Chief Security Officer mode — multi-phase security audit covering OWASP, STRIDE, secrets, CI/CD, and LLM attack surfaces
原文の言語: 英語
Structured debugging protocol — hypothesis-driven investigation with evidence tracking
原文の言語: 英語
Socratic problem exploration — identifies critical unknowns and gates on ≤20% ambiguity before proceeding
原文の言語: 英語
6-step multi-source research workflow with inline citations and synthesis
原文の言語: 英語