emanuelrechsteiner/claude-rcode 已索引

源文件证据覆盖

已存储的包版本在这个仓库中引用的固定源文件的原始计数。它反映已记录了什么，不代表仓库有多完整。

引用了 69 个固定源文件

• 69 已知
• 0 提交中不存在
• 0 文件列表截断
• 0 不受支持
• 0 尚无记录
• 0 读取失败

按仓库、提交和路径去重；同一路径出现在两个提交中，按两个文件身份计数。不是组件组数。

读取失败的提交 0

尚无记录的文件没有对应的提交读取失败记录。

关联的包 69

按仓库的已验证身份关联。数量是历史登记记录，不是当前可用性。

第 1–20 条，共 69 条结果

• api-design技能

  REST API conventions — resource naming, methods and status codes, response and error envelopes, pagination, filtering, auth, rate limits, versioning. Use when designing or reviewing endpoints. Triggers on "API design", "REST endpoint", "HT…

  271480714e45

• audit-config技能

  Run a deterministic audit of ~/.claude configuration against known schema-drift patterns (invalid settings fields, stale model IDs, broken hook patterns, naming collisions). Triggers on "audit config", "check config", "verify configuration…

  271480714e45

• backend-development技能

  Firebase and state management specialist. Handles Firestore operations, Firebase Functions, Zustand stores, user-scoped security, and optimistic updates with rollback. Use when working with Firebase, Firestore, Cloud Functions, Zustand, st…

  271480714e45

• canary-watch技能

  Post-deploy smoke check of a URL — HTTP status, console errors, failed requests, assets, SSE streams, key content, web vitals against a baseline. Use after a deploy, risky merge, or upgrade. Triggers on "canary", "post-deploy check", "smok…

  271480714e45

• check-parallelizable技能

  Analyze whether a task can be parallelized into independent sub-agents. Returns a structured proposal with file claim-sets, agent assignments, and confirmation prompt — or a clear explanation why sequential is better. Auto-triggers BEFORE …

  271480714e45

• click-path-audit技能

  Trace each button through its full state-change sequence to find handlers whose calls cancel each other or leave the UI in the wrong state. Use when users report dead buttons but debugging found nothing. Triggers on "click path audit", "bu…

  271480714e45

• cloud-cli-discipline技能

  Guidance for inspecting cloud-CLI state before destructive or scope-changing operations (env rm, link --yes, --force) and avoiding team/account auto-pick; covers when --yes is safe, preferring the web UI for per-environment values, and the…

  271480714e45

• context-budget技能

  Audit what loads into the context window (rules, CLAUDE.md, skill and agent descriptions, MCP tool schemas) and rank token-saving cuts. Use when the window fills too fast or before adding components. Triggers on "context budget", "context …

  271480714e45

• council技能

  Four-voice council (Architect, Skeptic, Pragmatist, Critic) for ambiguous decisions and go/no-go calls, using fresh-context sub-agents against anchoring. Use when several paths are credible. Triggers on "council", "second opinions", "go or…

  271480714e45

• create-hook技能

  Create Claude Code hooks. Use when the user wants to create a hook, register a hook in settings.json, add lifecycle automation (SessionStart, PreToolUse, PostToolUse, Stop), gate or audit tool calls, or block specific commands. Asks for mi…

  271480714e45

• create-rule技能

  Create Claude Code rules for persistent agent guidance. Use when adding coding standards, project conventions, security policies, workflow rules, or any guidance you want auto-loaded every session. Asks for missing scope/purpose, then writ…

  271480714e45

• create-skill技能

  Create Claude Code Skills (SKILL.md files). Use when authoring a new skill, when the user asks about SKILL.md structure or skill frontmatter, when packaging reusable workflows or domain knowledge into a forked-context capability. Skills di…

  271480714e45

• create-subagent技能

  Create custom Claude Code subagents (specialized AI agents with focused system prompts and tool allowlists). Use when adding a new agent type like code-reviewer, debugger, doc-writer, or domain-specific assistant. Asks for missing scope/pu…

  271480714e45

• daily-docs技能

  Daily logbook entry — item counting runs exclusively through a reference script (never manually/by feel), aggregates signals/git/memory for the prose, writes markdown + syncs to Notion.

  271480714e45

• database-migrations技能

  Safe schema and data migrations — forward-only, expand-contract renames, concurrent indexes, batched backfills, per-tool workflows. Use when changing a live schema. Triggers on "database migration", "schema migration", "zero-downtime migra…

  271480714e45

• dependency-audit技能

  Audit npm dependencies for security vulnerabilities, outdated packages, and unused dependencies. Provides actionable upgrade recommendations. Use to maintain healthy dependencies. Triggers on "dependency audit", "npm audit", "outdated pack…

  271480714e45

• documentation技能

  Technical documentation specialist. Maintains API docs, architecture documentation, developer guides, JSDoc, README updates, and Storybook stories. Use when creating or updating documentation, writing guides, documenting APIs, or maintaini…

  271480714e45

• eval-harness技能

  Eval-driven development for agent work — define capability and regression evals before coding, grade with code, rule, model, or human graders, report pass@k. Use for measurable pass/fail criteria. Triggers on "eval harness", "pass@k", "def…

  271480714e45

• find-docs技能

  Retrieves authoritative, up-to-date technical documentation, API references, configuration details, and code examples for any developer technology.

  271480714e45

• fix-review技能

  Post-fix completeness checker. After making a code fix, this skill identifies the fix scope, searches for all related occurrences, verifies call sites are updated, and checks for cascading issues. Use after fixing bugs to ensure nothing wa…

  271480714e45

已保存的扫描说明 0

没有保存额外的扫描说明。

记录的别名 0

这些名称在上次记录时指向这个仓库。这是记录下来的解析结果，不是实时的 GitHub 检查；本站不会因此合并包或元数据。

没有记录到指向这个仓库的别名。

不支持的市场条目 0

这个仓库的市场清单里、本站暂不支持的条目。它们是原样保存的来源数据，不会被抓取或执行。

没有记录到不支持的条目。