Convert PDF/EPUB library to Markdown and generate Obsidian MOC notes
原文语言:英语
菜单
SkillsMP 已收集 andrem-sec/psc-comet 中的 66 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 40 / 66 个已收集 Skill。
Convert PDF/EPUB library to Markdown and generate Obsidian MOC notes
原文语言:英语
Hook-based compaction suggestions at logical task boundaries
原文语言:英语
Context window management — track spend, decide when to compact, preserve state
原文语言:英语
Session-start orientation — loads context, surfaces learnings, confirms registry
原文语言:英语
Quality and semantic review — catches what automated tools miss
原文语言:英语
Planner → Architect → Critic deliberation loop — produces a formally validated ADR
原文语言:英语
Dual-dimension document quality gate — presentation rubric + hallucination grounding check
原文语言:英语
Model selection guidance — match task complexity to model capability
原文语言:英语
Scan task for high-cost branch points, confirm which get deep reasoning, execute with gates active
原文语言:英语
Resume an interrupted mid-task session — reconstructs state from context files and picks up at the right step
原文语言:英语
Full feature workflow — deep-interview → prd → consensus-plan → tdd → code-review → security-gate
原文语言:英语
Plan-mode enforcement — required before edits affecting 3+ files, cross-domain work, or security-sensitive changes
原文语言:英语
Session-end protocol — collect learnings, update context, commit session state
原文语言:英语
Framework for decomposing agent-driven tasks into independently verifiable units
原文语言:英语
Extract instinct candidates from the current session and add confirmed ones to the instinct store
原文语言:英语
Eval-driven development with pass@k metrics and three grader types
原文语言:英语
Capture codebase-specific knowledge as a reusable skill — passes 3-point quality gate before writing
原文语言:英语
Mid-session quick capture — save an insight before the context moves on
原文语言:英语
Auto-populate context/project.md by reading the current codebase
原文语言:英语
In-session memory tagging — mark content for recall later in the same session
原文语言:英语
Rules of Engagement authorization gate — required before any security operation, autonomous scanning, or action with real-world effects outside the local codebase
原文语言:英语
Pre-deploy security assessment — validates against OWASP Top 10 and project standards
原文语言:英语
Prevent algorithm confusion attacks when validating JWTs — RS256 tokens accepted as HS256
原文语言:英语
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,…
原文语言:英语
Framework for designing quality agents with proper action space and contracts
原文语言:英语
Test specifically for AI-introduced regressions that repeat without tests
原文语言:英语
Audit animations and transitions for motion accessibility, performance safety, and design intent. Enforces prefers-reduced-motion compliance and blocks layout-triggering transitions.
原文语言:英语
Parallel agent swarm — decomposes work into independent units, spawns isolated workers, tracks PRs via fan-in
原文语言:英语
Performance measurement with Core Web Vitals thresholds — baseline capture, regression detection, optional PageSpeed Insights
原文语言:英语
Load and validate brand assets before any design work — logo, colors, typography, voice. Gates UI and marketing work behind confirmed brand context.
原文语言:英语
Post-deploy production monitoring — watches live app for errors, regressions, and failures after deployment
原文语言:英语
Named decision point for long-running tasks — PIVOT, REFINE, or PROCEED
原文语言:英语
4-phase systematic codebase onboarding with reconnaissance and artifact generation
原文语言:英语
Define component API, states, variants, and ARIA requirements before writing a line of implementation code. Gates component work behind a confirmed spec.
原文语言:英语
Token audit across agents, skills, and MCP with cost optimization guidance
原文语言:英语
Cross-session instinct learning with confidence-based promotion and global scope
原文语言:英语
Chief Security Officer mode — multi-phase security audit covering OWASP, STRIDE, secrets, CI/CD, and LLM attack surfaces
原文语言:英语
Structured debugging protocol — hypothesis-driven investigation with evidence tracking
原文语言:英语
Socratic problem exploration — identifies critical unknowns and gates on ≤20% ambiguity before proceeding
原文语言:英语
6-step multi-source research workflow with inline citations and synthesis
原文语言:英语