最近新增
刚加入收藏的新技能，抢先试用。
qa-review
ToanMobile
Chất vấn một thay đổi code trước khi tạo PR (hỗ trợ cả Web, Mobile Android/iOS/Flutter, Unity Game). Dùng khi cần đọc diff (branch, commit, hoặc PR số) rồi đặt câu hỏi làm rõ tính năng, sinh acceptance criteria kiểm chứng được, và dựng ma trận test scenario theo vai trò × trạng thái dữ liệu × luồng lỗi. Kích hoạt khi người dùng nói "review diff trước khi tạo PR", "chất vấn tính năng này", "viết acceptance criteria", "liệt kê test case cho thay đổi này", "QA cái PR này". Đây là bước hỏi và lập kế hoạch test, không phải bước tìm bug trong code hay chạy test.
parallel-lanes
ToanMobile
"Dùng khi một việc được chia cho từ hai agent/lane trở lên chạy song song (fixer, reviewer, lane test, đợt merge): xếp lane đường găng và lane nặng chạy trước, giới hạn số lane theo CPU còn trống, brief sẵn các bẫy lặp lại, mỗi lane một worktree, review theo mức rủi ro nhưng không bỏ vòng nào, một gate full cho cả đợt. Lệnh: agent-kit lanes plan slots record."
open-code-review
ToanMobile
Dùng khi cần review code tự động, kiểm tra chất lượng git diff trước khi commit/PR, hoặc audit toàn bộ file bằng OpenCodeReview CLI (Alibaba Group). Hỗ trợ cả chế độ OCR-managed và Delegation mode.
repowise-intelligence
strikersam
Implements codebase intelligence layers similar to repowise-dev/repowise. Provides dependency graph, git history, auto-generated documentation, and architectural decisions intelligence for AI agents.
repo-memory-updater
strikersam
Keep CLAUDE.md files and .claude/state/ in sync with the current repo reality. Use after significant structural changes, after adding risky modules, or when CLAUDE.md feels stale.
release-readiness
strikersam
Gate check before tagging and releasing a new version. Run this skill before any git tag vX.Y.Z operation.
platform-setup
strikersam
Full autonomous AI agency setup for https://local-llm-server.strikersam.workers.dev. Uses browse CLI (Browserbase remote mode) to log in as admin, onboard the platform itself as a company, configure all specialists, verify agents are running, and fix any issues found. Run this skill to go from "deployed" to "fully autonomous."
perplexity
strikersam
Deep web research using the Perplexity API — get cited, up-to-date answers to research questions without burning context on raw web pages. Use when you need current information, competitive analysis, library docs, CVE lookups, or any factual query that requires web sources.
obsidian-knowledge-graph
strikersam
Obsidian-compatible knowledge graph with bidirectional links and graph-based retrieval
multi-agent
strikersam
Multi-agent team coordination — task delegation, shared state, and inter-agent communication
modularity-review
strikersam
Review codebase or design for modularity problems and produce actionable improvement recommendations. Also guides design of new modular boundaries from functional requirements. Inspired by Vlad Khononov's balanced-coupling model and golden-age-of-modularity principles. NOTE: Full upstream plugin at https://github.com/vladikk/modularity Install it for the complete experience: follow instructions at that URL. This skill is a clean-room local adaptation for this repo.
model-catalogue-update
strikersam
Add, change or retire a model id in the routing catalogue. Use whenever a task touches config/models.yaml, config/llm/models.yaml, packages/ai/brain_config.py PROVIDER_CANDIDATES or presets, or packages/ai/cost_tracker.py prices — including the daily "new models" automation.
memory-consolidation
strikersam
Dream Memory Consolidation for clustering session artifacts into structured, queryable memories with tag-based similarity.
managed-agents-dreams
strikersam
Session memory recording and dream consolidation for managed agents — offline experience replay
karpathy-guidelines
strikersam
Andrej Karpathy's coding guidelines for AI agents — concise, correct, and well-tested code
implementation-planner
strikersam
Plan a multi-file or multi-step implementation before writing any code. Use before any change touching more than two files, adding a new feature, or changing a module interface.
hybrid-reasoning
strikersam
Hybrid AI combining deterministic rule engines with LLM reasoning for efficient, auditable, and reliable decision-making.
graphiti-temporal
strikersam
Temporal context graph for agent memory — track entity relationships and state changes over time
graphify
strikersam
Converts this codebase into a queryable knowledge graph so AI sessions query graph.json (71.5x fewer tokens) instead of reading raw source files. Integrates with Claude Code and Codex via repo hooks that auto-refresh on session start and after turns.
financial-analyst
strikersam
Agentic CFO for autonomous financial analysis of AI infrastructure spend. Computes burn rate, runway, gross margin, and ROI-based budget reallocation.
fabric-patterns
strikersam
Implements a Fabric-like reusable prompt pattern system. Allows storing, retrieving, and composing prompt patterns for consistent AI interactions.
ecc-harness-patterns
strikersam
Cross-harness agent patterns — standardize agent execution across different coding assistants
docs-sync
strikersam
Keep documentation in sync after code changes. Run after any change that alters module behaviour, APIs, env vars, or architecture.
dependency-audit
strikersam
Review, validate, and update Python dependencies safely. Use when adding a new package, upgrading an existing one, or reviewing the dependency surface.