搜索

PythonReactSEOPDF

doodledood AI Skills

GitHub ↗

浏览 doodledood 维护的已发布 AI 技能,比较用途与说明,并通过来源仓库了解安装方式。

作者统计

已收录技能

69

收录技能的仓库 Stars 合计

446

仓库 Forks

0

平均每个技能的仓库 Stars

6

同一仓库中的多个技能可能共享 Stars,合计包含重复仓库数据。

69 个技能

全部技能

GitHub

done

doodledood

Completion marker. Outputs hierarchical execution summary showing Global Invariants respected and all Deliverables completed.

GitHub

bugfix

doodledood

Investigates and fixes bugs systematically with root cause analysis. Use when asked to debug, troubleshoot, fix a bug, investigate an issue, or find why something is broken. Creates reproduction tests and verif...

GitHub

explore-codebase

doodledood

Find all files relevant to a query with orthogonal exploration for comprehensive coverage. Returns topic-specific overview + file list with line ranges. Uses parallel agents for thorough+ levels to ensure nothi...

GitHub

escalate

doodledood

Structured escalation with evidence. Surfaces blocking issues for human decision, referencing the Manifest hierarchy.

GitHub

learn-from-session

doodledood

Analyze Claude Code sessions to learn what went right/wrong and suggest high-confidence improvements to skills. Use when asked to analyze a session, learn from a session, or review workflow effectiveness.

GitHub

ask-council

doodledood

Multi-model ensemble consultation. Runs 3 models in parallel for diverse perspectives.

GitHub

review-bugs

doodledood

Audit code for logical bugs, race conditions, edge cases, and error handling issues.

GitHub

define-seo-strategy

doodledood

Create a comprehensive SEO_STRATEGY.md covering both traditional SEO and Generative Engine Optimization (GEO) for AI platforms. Requires CUSTOMER.md to exist first. Includes platform-specific tactics for Google...

GitHub

define

doodledood

Manifest builder with verification criteria. Converts known requirements into Deliverables + Invariants. Use when you need done criteria, acceptance tests, quality gates—not for requirements discovery. Outputs...

GitHub

review-testability

doodledood

Audit code for testability design patterns. Identifies business logic entangled with IO and suggests functional core / imperative shell separation.

GitHub

analyze-code

doodledood

Deep code analysis using consultant agent. Identifies technical debt, risks, and improvement opportunities.

GitHub

plan

doodledood

Create implementation plans from spec via iterative codebase research and strategic questions. Produces mini-PR plans optimized for iterative development.

GitHub

web-research

doodledood

Research external topics via web search with structured hypothesis tracking and source evaluation.

GitHub

spec

doodledood

Requirements discovery through structured interview. Use when WHAT is unclear—scope needs definition, requirements need gathering, or starting from scratch. Outputs spec document, not executable manifest.

GitHub

ask

doodledood

Single-model consultation using consultant agent. Defaults to gpt-5.2-pro.

GitHub

compress-prompt

doodledood

Compresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action space. Use when asked to compress, condense, or minimize a prompt.

GitHub

review-docs

doodledood

Audit documentation accuracy against code changes. Reports discrepancies without modifying files.

GitHub

implement

doodledood

Executes implementation plans via subagents with automated verification and fix loops. Use after /plan for complex features. Each chunk gets dedicated Implementor + Verifier agents with up to 5 fix attempts.

GitHub

bugfix

doodledood

Systematic bug investigation and fix workflow. Gathers symptoms, forms hypotheses, investigates root cause, implements fix, and verifies. Use for debugging, fixing errors, or troubleshooting. Triggers: debug, f...

默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。