Topic: ai-coding
5,076 skills in this topic.
-
review-pr
Review a PR or branch diff using the knowledge graph for full structural context. Outputs a structured review with blast-radius analysis.
tirth8205/code-review-graph 8,887
-
build-graph
Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.
tirth8205/code-review-graph 8,887
-
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
tirth8205/code-review-graph 8,887
-
ccpm
CCPM - spec-driven project management: PRD → Epic → GitHub Issues → parallel agents → shipped code. Use this skill for anything in the software delivery lifecycle: writing a PRD ('write a PRD for X', 'let's plan X', 'scope this out'), parsing a PRD into an epic, decomposing an epic into tasks, syncing to GitHub ('sync the X epic', 'push tasks to github'), starting work on an issue ('start working on issue N', 'let's work on issue N'), analyzing parallel work streams, running standups ('standup', 'run the standup'), checking status ('what's next', 'what's blocked', 'what are we working on'), closing issues, or merging an epic. Use ccpm any time the user is talking about shipping a feature, managing work, or tracking progress — even if they don't say 'ccpm' or 'PRD'. Do NOT use for: debugging code, writing tests, reviewing PRs, or raw GitHub issue/PR operations with no delivery context.
automazeio/ccpm 7,950
-
gh-merge
将当前分支合并到 GitHub 目标分支（通常是 main）。
自动处理代码提交、创建 PR、监控 CI Checks、处理错误直到合并成功。
AgentsMesh/AgentsMesh 1,428
-
worktree
创建 Git worktree 用于隔离开发新功能或修复 bug。
自动处理分支创建、worktree 设置、目录切换和开发环境初始化。
AgentsMesh/AgentsMesh 1,428
-
e2e
执行 E2E 测试用例。
根据测试用例的验证类型（ui/api/database）选择正确的工具执行验证。
AgentsMesh/AgentsMesh 1,428
-
gl-gh-sync
在 GitLab（内部）和 GitHub（开源）之间双向同步代码。
自动检测哪边有新提交，fast-forward 场景直接推送，分叉场景走 PR/MR 流程。
AgentsMesh/AgentsMesh 1,428
-
am-delegate
AgentsMesh/AgentsMesh 1,428
-
merge
将当前分支合并到目标分支（通常是 main）。
自动处理代码提交、创建 MR、监控 Pipeline、处理错误直到合并成功。
AgentsMesh/AgentsMesh 1,428
-
cost-mode
Cost-conscious Claude Code mode. Reduces output tokens 40-70% and overall costs 30-60% by enforcing concise responses, smart model routing, and efficient workflow patterns. Keeps full technical accuracy. Activate with /cost-mode or "enable cost mode". Auto-triggers on mentions of budget, cost, tokens, or spending.
Sagargupta16/claude-cost-optimizer 16
-
cost-mode
Cost-conscious Claude Code mode. Reduces output tokens 40-70% and overall costs 30-60% by enforcing concise responses, smart model routing, and efficient workflow patterns. Keeps full technical accuracy. Activate with /cost-mode or "enable cost mode". Auto-triggers on mentions of budget, cost, tokens, or spending.
Sagargupta16/claude-cost-optimizer 16
-
q-reason
Think before building. Use when the user asks to reason about, analyze, evaluate, compare options, make an architecture decision, choose between approaches, think through a problem, or assess trade-offs. Also use when the user asks 'why did we...', 'should we...', 'what are our options', 'is this the right approach', or wants to frame/reframe a problem.
m0n0x41d/quint-code 1,266
-
orchestrate
Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.
rohitg00/pro-workflow 1,865
-
file-watcher
Configure file watching hooks to auto-react to config changes, env file updates, and dependency modifications. Use to set up reactive workflows.
rohitg00/pro-workflow 1,865
-
deslop
Remove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up boilerplate, simplifies abstractions, and strips defensive code. Use when cleaning up code, simplifying, removing boilerplate, or before committing.
rohitg00/pro-workflow 1,865
-
wrap-up
End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying "wrap up", "done for the day", "finish coding", or ending a coding session.
rohitg00/pro-workflow 1,865
-
sprint-status
Track parallel work sessions and prevent confusion across multiple Claude Code instances. Every major step ends with a status line. Every question re-states project, branch, and task.
rohitg00/pro-workflow 1,865
-
parallel-worktrees
Create and manage git worktrees for parallel coding sessions with zero dead time. Use when blocked on tests, builds, wanting to work on multiple branches, context switching, or exploring multiple approaches simultaneously.
rohitg00/pro-workflow 1,865
-
thoroughness-scoring
Score every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things properly near-zero — pick the higher-rated option every time. Includes scope checks to distinguish contained vs unbounded work.
rohitg00/pro-workflow 1,865
-
permission-tuner
Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are slowing you down or after sessions with many denials.
rohitg00/pro-workflow 1,865
-
context-optimizer
Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.
rohitg00/pro-workflow 1,865
-
pro-workflow
Complete AI coding workflow system. Orchestration patterns, 18 hook events, 5 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.
rohitg00/pro-workflow 1,865
-
cost-tracker
Track session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits.
rohitg00/pro-workflow 1,865