open-websearch-maintainer
Maintain and extend the open-websearch MCP server. Trigger when changing search engines, proxy or TLS behavior, tool registration, live parsing behavior, or compatibility and regression behavior inside this repository.
What this skill does
# Open WebSearch Maintainer Use this skill when modifying the `open-websearch` codebase itself. If this skill and the current repository behavior disagree, trust the repository code, tests, and intended change scope, then update the skill or docs before finishing. ## First classify the change - Engine change: new engine, engine parsing, engine pagination, anti-bot handling. - Network change: proxy, TLS, request builder, Playwright interaction, browser fallback. - Tool surface change: MCP tool registration, schema, engine normalization, config exposure. - Validation-only change: tests, docs, or release hygiene when no code-path behavior changes are intended. Use this classification as the execution entrypoint. Start by choosing one category, load only the checklist that matches it, and expand scope only when the changed code path actually crosses that boundary. ## Scope discipline - Keep fixes as local as the real failure surface allows. - Do not turn a parsing or engine-specific issue into a shared networking refactor without evidence. - Do not widen insecure or compatibility-relaxing behavior just to make one test pass. - Do not change tool contracts or global behavior unless the change is intentional, verified, and documented. ## Core rules - Keep MCP tool contracts stable unless the change explicitly requires a breaking change. - Route Axios-based networking through the shared HTTP request builder instead of ad hoc proxy handling. - Treat proxy, TLS, and Playwright behavior as cross-cutting concerns. Verify them explicitly after changes. - Update tests and README files when adding engines or changing behavior. ## Do not - Do not bypass the shared HTTP request builder for a one-off engine fix. - Do not silently fork proxy behavior in a single engine unless the repository explicitly adopts that policy. - Do not widen insecure TLS behavior beyond the narrow code path that requires it. - Do not change tool contracts without checking tests, config handling, and README files. - Do not touch shared networking code if the change is only about result parsing or docs. ## Change checklist When adding or changing a search engine: - update `src/config.ts` - update `src/tools/setupTools.ts` - add or update engine tests - update `README.md` and `README-zh.md` When changing network behavior: - prefer `src/utils/httpRequest.ts` - keep `proxy: false` behavior explicit for Axios - keep insecure TLS opt-in and scoped only where necessary ## Validation - Run TypeScript checks first. - Run targeted tests for the touched area. - Run live tests when the change depends on real network behavior. ## Review focus - pagination and empty-result handling - anti-bot / verification page detection - proxy interactions with `USE_PROXY` and `PROXY_URL` - request-mode versus Playwright-mode behavior - documentation drift Read [references/workflow.md](references/workflow.md) when implementing changes and [references/validation.md](references/validation.md) before finalizing a patch.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.