The catalog
608,253 rows, by stacks then stars
Async context manager retry pattern
Ed3Design/ed3design-skill-bundles/async-forensik/skills/async-context-manager-retry-pattern Skill
0★ repoUse when implementing retry-logic around an `async with X:` block where `X.__aenter__()` or `X.__aexit__()` performs network-IO that can fail transiently (python-telegram-bot, asyncpg pools, httpx, websockets). Iron-Law: every `async with` whose enter/exit does network-IO must sit INSIDE the retry-loop, not around it — otherwise enter-failures bypass the inner `try/except` and get caught as "Unexpected" with zero retries actually attempted. Trigger on phrases like "retry around async with", "TimedOut from __aenter__", "I implemented retry but it doesn't trigger", "context manager exception bypasses retry". Do NOT load for sync context-managers, async-with where __aenter__ does only local work (file-open, in-memory state), retry around async-iterators, or first-time-design of an async-context-manager class itself.
dhk/skill-map/plugins/skill-doctor/skills/skill-doctor Skill
0★ repoReview an existing Claude Agent Skill and bring it up to best-practice standard. Use this when you have a SKILL.md to audit, harden, or improve — it interviews about allowed-tools scoping, data sensitivity (PHI/PII/HIPAA), high-stakes actions, triggering, and install scope, then recommends fixes and applies them on your confirmation. Do NOT use this to write a brand-new skill from scratch (use skill-creator) or to grade a whole repo at once (use the skill-map auditor / skill-audit Action).
isanthoshgandhi/santhoshstack/skills/arch-map Skill
0★ repoGenerates a human-readable architecture document for any codebase. Use when onboarding contributors, presenting to stakeholders, explaining how a system works to non-technical collaborators, or after a major architectural change. Outputs docs/ARCHITECTURE.md with a Mermaid system diagram, plain English narrative, data flow walkthrough, and tech stack rationale. Trigger on: "map the architecture", "explain how this works", "architecture doc", "system map", "explain to non-technical", "onboard contributor", "document the system", "draw the architecture".
ORBWEVA/founder-ops/skills/hiring Skill
no license0★ repoHiring skill for startups. Use when user needs job descriptions, interview scorecards, structured interview questions, or offer letter templates. Triggers on "job description", "hiring", "interview questions", "scorecard", "offer letter", "JD", or /hire commands.
Timelnapp/skills/skills/consulting-os/consult-acceptance Skill
0★ repoTrigger on "acceptance criteria", "consult acceptance", "success criteria", "signoff matrix", "deliverables per phase", "primary path fallback", "definition of done". Per-phase deliverables, measurable criteria (tech + business/ops), owner, primary path + fallback. NOT commercial terms (use consult-commercial), NOT gate questions (use consult-gates).
TheBitcoinBreakdown-95/frontier-prompter/skills/frontier-prompter Skill
0★ repoReformats a raw prompt, task, or goal into a hand-off prompt optimized for a top-tier autonomous model, using Anthropic's prompting best practices for strong autonomous models. Use this whenever the user wants to hand a task to a frontier/premium model or any top-tier autonomous agent — phrases like "make a frontier prompt", "format this for my frontier model", "turn this into a hand-off prompt", "write a hand-off / planning prompt", "prep this for a strong model", or any time the user is authoring a prompt that asks a powerful model to plan or execute autonomously. Encodes intent-first framing, lead-with-outcome brevity, act-when-you-have-enough, effort/tier matching, prove-it verification, and a small set of rationalized negative guardrails placed at anticipated failure points. Reach for it any time the user is hand-drafting a multi-paragraph Intent/Success/Read-first hand-off or seat prompt for a strong model.
robmcquade/claude-skills/evaluate-ai-merits Skill
0★ repoEvaluate the merits of external content about Claude, Anthropic products, Claude Code, MCP servers, AI agents, prompt engineering, or AI tooling broadly. Adds AI-specific verification on top of evaluate-merits — routes to primary sources, applies heightened date-of-recording sensitivity (AI tooling ships weekly), flags AI-specific conflations (built-in vs custom add-ons, model-version vs universal guidance, surface differences between claude.ai/Code/API, deprecated features, opinion vs Anthropic guidance, preview vs GA). Use whenever the user shares content on Claude or AI tooling. Composes with evaluate-merits when both apply. Do NOT use for direct AI questions not referencing external content — those are web search and answer.
gmarmat/claude-pm-kit/.claude/skills/metrics Skill
0★ repo[PM Twin] Define, track, and review product KPIs — success metrics, funnels, health indicators.
ClydeShen/harness-skill/skills/engineering/context-handover Skill
0★ repoEnd-of-context-window session transition that saves memory, writes a handoff doc, posts a GitHub progress comment, and instructs the user to /compact for a clean next session. Use when context usage approaches 80%, when remaining tokens are insufficient for the current phase's remaining work, or when user says "handover", "context is full", "save progress", "end session". Distinct from /handoff (lightweight subagent briefing — no GitHub, no /compact).
paidaxing1234/latency-hunter-toolkit/skills/backtest-guard Skill
0★ repo量化回测代码的"照妖镜"——逐项审查会让回测虚高、实盘亏钱的工程陷阱(未来函数/前视偏差、过拟合/数据窥探、成交真实性/成本、收益口径错误),按严重度(致命/高危/中/低)输出一张"回测体检报告"。 何时触发:用户把量化策略/回测代码、信号生成、数据加载、参数寻优脚本丢过来让你审查可信度;或问"这个回测能信吗/为什么实盘对不上回测/帮我查未来函数/有没有过拟合"。 触发词(中):回测审查、回测照妖镜、回测体检、未来函数、前视偏差、数据泄漏、过拟合、数据窥探、幸存者偏差、回测陷阱、回测可信度、实盘对不上回测。 触发词(英):backtest audit、backtest review、look-ahead bias、lookahead、data leakage、overfitting、survivorship bias、curve fitting、backtest-guard。 不适用场景:实时实盘下单/风控逻辑本身的 bug、单纯策略调参或求 alpha、行情数据源运维、非量化的通用代码审查、要你"预测收益/荐股/给买卖建议"——这些都不在本 skill 范围。
The same file is in 1 other repository
RedAvocado22/claude-code-mentoring/.claude/skills/init-mentoring Skill
no license0★ repoInstall the self-updating memory automation for this mentoring setup. Copies the hook scripts into the current project and registers them in .claude/settings.json. Run once, right after cloning/copying claude-code-mentoring into a project.
Cadasto/go-coding-plugin/skills/go-coding Skill
0★ repoGo coding-standards router and entry point for idiomatic Go (Go 1.26, works with 1.25+; golangci-lint v2). This skill should be used when a Go task spans multiple areas, is unspecified, or the question is which tool or standard applies — it routes each topic to the deterministic tool (gofmt/gofumpt, go vet, go fix / golangci-lint v2 modernize, go test -race), to the gopls-lsp plugin for code intelligence, and then to the focused go-* skill that owns it. For a single, already-identified topic prefer that skill directly (errors → go-errors, concurrency → go-concurrency, testing → go-testing, idioms/modernization → go-idioms, linter config → go-linting, layout → go-layout). Not for non-Go languages or domain/business rules.
TomerAberbach/claude-config/skills/adversarialize Skill
0★ repo🤖 My Claude Code config!
outreachmagic/lead-enrich Skill
0★Research anyone by name and company. Pulls back their LinkedIn, job title, bio, company domain, and website. Works standalone with a Serper API key, no heavy setup. With Outreach Magic, it checks your pipeline so you never pay twice for the same lead data.
jpoindexter/reward-seeking-safety-skills/skills/contrastive-authority-eval Skill
0★ repoDesign or review paired evaluations that test whether an AI agent follows a grader over a user, operator, developer, policy, or honesty constraint. Use for authority conflicts, reward-seeking detection, contrastive belief tests, grader-vs-user behavior, promise-breaking evals, or honesty-vs-task-completion experiments.
tarangdeep-goel-by/claude-harness/claude/skills/debug-escalation Skill
0★ repoUse when encountering any bug, test failure, unexpected behavior, or error during development, before proposing or attempting fixes.
Threads Research Scraper Skill
KarlYu130/Threads-Research-Scraper-Skill Skill
no license0★Conduct live topic, keyword, account, and comment research & web scraping on Meta Threads (threads.net) using Playwright headless browser automation, post page navigation, and reply thread extraction.
evnchn-agentic/rich-render Skill
0★Use when a turn produces a multi-item synthesis (>=5 discrete items that benefit from cross-comparison) — triage, audit, survey, bug-sweep, design-alternatives, research findings, scorecards — and pasting it as raw Markdown in chat would be lower-bandwidth than a glanceable dashboard. Also when the operator says "rich render", "dashboard", "make it a dashboard", or asks to defer a long synthesis out of chat. Produces a single self-contained dark HTML file saved to ~/rich-renders/.
tawfeeq234/llm-coding-collaboration Skill
no license0★Optimizes Claude's coding collaboration by countering known LLM weaknesses (over-complication, hidden assumptions, sycophancy) and leveraging strengths (tenacity, iteration). Use for any coding task, code review, architecture discussion, or software development conversation. Triggers on code requests, debugging, refactoring, or technical implementation discussions.
twisker/ipman/src/ipman/templates/ipman-update Skill
0★ repoUpdate the IpMan CLI to the latest version and keep the companion skills in lockstep. Use when asked to "update ipman", "upgrade ipman", "get the latest ipman", "ipman 有新版本吗", "更新 ipman". Detects the install method (pipx / uv tool / pip), upgrades from PyPI, then regenerates the skills.
TimothyVang/claude-code-qc Skill
0★Quick commit + auto-push. Stages changes, drafts a Conventional Commit message from the diff, commits, and pushes. `/qc` pushes the current branch to its origin upstream; `/qc main` switches to main first and pushes there (solo-speed flow — skips PR review). Bootstraps `gh` (install + browser auth) if not already configured. Never bypasses hooks (`--no-verify`), signing (`--no-gpg-sign`), or rewrites commits (`--amend`). No AI attribution lines in commit messages.
ccronca/dotfiles/claude/skills/Journaling Skill
0★ repoGenerates a detailed summary of a development session by analyzing the session transcript. Can be invoked manually or automatically from hooks.
izahamyatim/claude-plugin-fizzy/plugins/fizzy/skills/fizzy-workflow Skill
0★ repoUse for guided Fizzy.do workflows: "set up Fizzy", "configure Fizzy for this project", "sync my work to Fizzy", "review my Fizzy progress", "end of session cleanup". Provides step-by-step guidance for common operations.
The same file is in 1 other repository
xltang/hotspots_xwlb Skill
0★用于拉取并展示「新闻联播」热点(接口为 https://hotspot.api4claw.com/hotspots/platform/新闻联播?timestamp=$TIME_STEMP,返回 JSON 数组)。按 source_name 分组展示标题,无 Top Hot。默认会提示用户是否创建定时任务(不自动执行),在用户确认后提供 cron 注册命令。适用于新闻联播热点、服务状态、按 source_name 分组标题,或由已存在的定时消息触发。触发词:"新闻联播"
anhtuan23004/langgraph-agent-skill Skill
no license0★Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents with LLM-tool loops, branching workflows, conversation memory, human-in-the-loop oversight, and production monitoring. Use when - (1) building agents that use tools and loop until task complete, (2) creating multi-step workflows with conditional branches, (3) adding persistence/memory across turns with checkpointers, (4) implementing human approval with interrupt(), (5) debugging via time-travel or LangSmith. Covers StateGraph, nodes, edges, add_conditional_edges, MessagesState, thread_id, Command objects, and ToolMessage handling. Examples include chatbots, calculator agents, and structured workflows.
chenwei791129/agent-skills/hermes-skills/superpowers/brainstorming Skill
0★ repoUse before creative or product work: creating features, building components, adding functionality, or changing behavior. Refines intent, requirements, and design before implementation, then hands off to Hermes writing-plans.
Layton2617/devpilot-tui Skill
0★Multi-agent context bridge — seamlessly switch between AI coding agents without losing context
cukas/claude-workflow-skills/skills/build-guard Skill
0★ repoUse when implementing features, refactors, or multi-file changes. Orchestrated plan-then-execute with subagent dispatch and regression checkpoints.
pengqianhan/NZ-life-skills/skills/nz-skill-creator Skill
0★ repoCreate or update skills inside the NZ Life Skills repository while keeping package docs, manifests, and bundle-level agent indexes in sync. Use when Codex needs to add a new repository skill, update an existing skill's package metadata, register a skill in docs/skills.json and docs/bundles.json, refresh docs/.well-known/agent-skills/*, or keep README and docs pages aligned with the repository's bundle structure. Triggers include requests like "add a new skill to this repo", "update all affected indexes and manifests", "register this skill in NZ-life-skills", or "use the add-skill-template workflow".
diptiman-mohanta/CodeGuard Skill
0★Senior Staff Engineer protocol. Forces deep reasoning, prevents over-engineering, ensures code integrity with diff-aware changes, and validates library usage via web search. Never hallucinates APIs.
givepro91/cc-skills/plugins/claude-md/skills/claude-md Skill
0★ repoGenerate or refresh a project's agent rules — a tailored preamble plus an idempotent managed block (working discipline, verification, adaptive parallel-git workflow, self-learning rules). Writes to the repo's canonical agent file (CLAUDE.md by default, or AGENTS.md when it is canonical, e.g. CLAUDE.md imports @AGENTS.md). Works on new and existing projects; only ever rewrites its own managed block. Use when setting up a repo, standardizing AI working rules, or adopting the parallel-git + self-learning workflow.
Mrbaeksang/ai-project-audit/skills/karpathy-discipline Skill
0★ repoEnforces Karpathy's 4 LLM-coding principles (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution). Auto-fires whenever the user requests writing, editing, refactoring, fixing, or adding code. Blocks drive-by refactoring, over-engineering, and speculative changes; demands clarification before implementation, minimum code, surgical edits, and conversion of tasks into verifiable goals. Respond in the user's language.
web3at50/skills/skills/remotion-setup Skill
0★ repoInstall Remotion, set up Remotion, add Remotion to a project, install Remotion AI skills, update Remotion, upgrade Remotion packages, check Remotion version, set up video project with Remotion, remotion skills, remotion rules
chris-peterson/sextant/skills/impl-new Skill
0★ repoScaffold a new candidate implementation in the spec-driven `implementations/<version>/<n>-<name>/` tree, to stress-test the spec against a fresh stack.
agency-shift/agency-shift-skills/agency-brief-from-call Skill
0★ repoTurn a raw sales, discovery, or kickoff call transcript into a structured project brief with scope, deliverables, deadlines, decision-makers, and open questions. Use whenever the user pastes a call transcript (Otter, Fireflies, Fathom, Zoom auto-transcript, voice memo transcription) and asks for "the brief", "the scope doc", "the SOW input", or "turn this call into a brief". Do NOT use this skill for internal team meeting notes or for one-off conversation summaries — it is specifically scoped to client-facing project briefs that will be sent back to the client for sign-off.
Bbar0n234/llm-engineer-skills/skills/aidd-methodology Skill
0★ repoAI-Driven Development — методология и принципы написания документации для проектов с LLM-агентом. Используй когда: AIDD, AI-driven, планирование проекта, idea.md, vision.md, workflow.md, архитектура, документация, написание документации, обновление документации, doc, md-файл, Context First, итерация, tasklist, ADR.
nishide-dev/claude-code-ml-research/skills/ml-cli-tools Skill
0★ repoBuilding professional CLIs with Typer and Rich - type-safe argument parsing, progress bars, model visualization, Hydra integration, RichHandler logging, and multi-process handling for ML workflows
wundergraph/cosmo-connect-skill/skills/cosmo-connect Skill
0★ repoCreate and modify APIs using WunderGraph Cosmo Connect. Covers gRPC plugin development (Go/TypeScript), standalone gRPC services, schema-to-proto workflows, CLI commands (wgc), local router setup, graph.yaml composition, field resolvers, batching, federation entities, and deployment. Use when building Cosmo Connect subgraphs, plugins, gRPC services, or setting up a local Cosmo Router.
dan1elw/dotclaude/skills/explain-code Skill
0★ repoUse this skill when the user asks to explain, walk through, or understand a file, function, class, or code concept. Covers high-level summaries, mental models, and pointing out non-obvious behavior. Do NOT use for debugging, refactoring, or writing new code.
hoqo/claude-plugins/plugins/mongodb/skills/mongodb-query-builder Skill
no license0★ repoBuild and optimize MongoDB queries, aggregation pipelines, and CRUD operations. Use when the user asks to query data, filter documents, join collections, aggregate results, update documents, or work with MongoDB data in any way.
The same file is in 2 other repositories
joncutrer/aiuc-1-context/dist/aiuc-1-advisor Skill
no license0★ repoStrategic AI compliance advisor for AIUC-1 adoption. Produces compliance roadmaps, vendor questionnaires, framework crosswalk mappings, executive summaries, and scoping guidance.
nardovibecoding/simply-skills-curation/skills/discovery/skill-extractor Skill
0★ repoEvaluate a shared AI skill or skill repository before installing or copying patterns.
rperez030/accessible-agent-skills/skills/audio-summary Skill
0★ repoUse this skill whenever the user wants to summarize, analyze, or transcribe an audio file. Triggers include any request involving an audio file (.m4a, .mp3, .wav, .aac, .ogg, etc.) and words like "summarize", "transcribe", "what's in this audio", "what does this say", "analyze this recording", "who is speaking", or any variation. Also triggers when the user drops or mentions an audio file and asks what it contains. Use this skill even if the user says just "summarize this" and has previously mentioned an audio file in the conversation.
sgrowe/jj-ai/jj-flow/skills/jj-flow Skill
no license0★ repoThe workflow used in this project for planning and organising work using `jj` VCS
mi4646/my-skills/skills/baoyu-design Skill
no license0★ repoCreate polished design artifacts as self-contained HTML: UI mockups, interactive prototypes, wireframes, landing pages, dashboards, app screens, mobile apps, slide decks (a.k.a. PPT / PowerPoint presentations), and visual explorations. Use whenever the user asks to design, mock up, prototype, wireframe, visualize, explore, or make a PPT/deck for an interface, product screen, user flow, content layout, visual artifact, or pitch/deck concept, even if they do not say "design". Also use to export a deck built with this skill to PowerPoint (PPT/PPTX) — but only decks authored here (deck-stage / this skill's slide-structured HTML), NOT arbitrary HTML, so confirm the target is such a deck first. Also use for setting up, importing, or authoring reusable design systems, UI kits, brand tokens, or component libraries. Harness-agnostic for Claude Code, Cursor, Codex Agent, and similar file-capable agents.
gigayaya/gigachang-skills/.claude/skills/docs-drift Skill
0★ repoUse when the user wants to verify this plugin's docs are still in sync with its code after a change — e.g. "check for docs drift", "did the README drift", "are the docs still accurate", "I updated the plugin, verify the docs", "/docs-drift". Runs a deterministic checker for mechanical drift (skill/command catalogs in README and codemap, per-skill index files, dead relative links, English-only rule, version bump) and then does a semantic pass the script cannot — comparing each doc's prose description against what the skill actually does and the dependencies it actually ships. Proposes concrete fixes and only edits docs after the user approves. Manual-trigger only — never auto-invoke; never edit files without approval.
grooverLab/stash/skills/stash Skill
0★ repoFind and load the right skill from the user's stash warehouse for the task at hand, then do the task under it. Invoke as /stash <task>. User-invoked only.
bogheorghiu/ex-cog-dev/makers-toolkit/skills/intrinsic-prompt-design Skill
0★ repo"Wait — WHY are you obeying this? No, LITERALLY, why?" Now that I have your attention: invoke when writing or revising any prompt — a skill, a rule, a CLAUDE.md, an agent or system prompt, and the like. That question held you where a command gets skimmed — so build prompts on reasons: a command breaks at the first edge case, a reason adapts.
mjcreativelab/mjcreativelab-agent-prompts/internal/auto-release Skill
0★ repoリポジトリの repo-level バージョン(v<X.Y.Z> タグ)を自動判定して発行し、GitHub Release を作成する。ユーザーが「リリースして」「バージョン上げて」「タグ切って」「/auto-release」と言ったら起動する。
chenpianzhou/requirement-to-prd-skill/requirement-to-prd Skill
0★ repo把一句话的产品想法、老板的灵感、会议纪要或用户反馈,写成一份结构化、可评审、研发能直接接的 PRD。当用户说"帮我写个 PRD"、"把这个需求写成文档"、"出一份产品需求文档"、"这个想法整理成 PRD",或者丢来一段粗糙的需求描述希望落地成正式文档时使用。
travcjohnson/claude-skills/skills/resume-claude-session Skill
0★ repoRecover a Claude Code session that fails to resume with "No conversation found" — finds the session file across all encoded project directories, extracts the real cwd from inside the jsonl, and reruns the corrected `claude --resume` command. Trigger when the user pastes a failing `cd … && claude --resume <id>` block, asks to "resume that session", "open the lost session", or any variant of recovering a Claude session that errored on resume. Also trigger if the user asks how to install or set up this skill.
evnchn-agentic/agentic-exam-prep Skill
0★Use when assembling an exam-prep pack for an HKUST-style open-book final (or structurally similar course exam) for evnchn — building an iterative MCQ drill loop, a print pack, mining course materials (Canvas / course site / past papers), NotebookLM cram pods, or a print-shop-grade PDF. This is evnchn's specific exam-prep system, course-agnostic in mechanics but tuned to his open-book finals. NOT a general study-advice skill. Triggers: mcq drill, cheatsheet, cram, print pack, Canvas quiz, NotebookLM, past paper.
JoseVelazcoH/python-skills/skills/python-anti-patterns Skill
0★ repoTrigger: anti-patterns, import order, file too long, split module, unrelated functions, hardcoded values, magic values, module constants, extract constants, future annotations import. Enforce battle-tested Python module-organization rules.
Fab2295/sap-skills/skills/sap-cap-code-review Skill
0★ repoRead-only static analysis of SAP CAP Node.js code (a Pull Request, a branch comparison, or a specific file list). Classifies findings as Critical / High / Medium / Low, lists each finding with file:line, function/class, evidence and a *suggested* fix (always flagged as needing human validation), and writes the result to `CAP-CODE-REVIEW.md` at the project root. Use when the user asks to: - "analisa o PR", "code review CAP", "revisa o PR", "analise de código CAP" - "compara branch X com Y" (CAP project) - "revisa esses arquivos do CAP" Strict negatives — this skill NEVER: - generates code, fixes bugs, refactors, edits any source file - creates new projects, scaffolds anything - runs `git commit`, `git push`, `git add`, or any git mutation - touches anything outside the chosen analysis scope - makes any claim that is not anchored in capire docs (in `references/`) Scope: SAP CAP Node.js only. If the project is Java CAP, generic Node.js, or non-CAP, the skill must refuse with an explicit message.
chienchuanw/chuan-skills/plugins/daily/skills/daily-planner Skill
no license0★ repoPlan the user's day end-to-end. Triage all five Gmail accounts (by running gmail-helper), read Google Calendar and the Objectives MOC, carry forward yesterday's unfinished tasks, classify every task on an Eisenhower matrix (urgent × important), then write a prioritized plan with time-block suggestions into the Obsidian Daily note plus a reasoning log in the Journal. Use this whenever the user wants to plan, organize, or prioritize their day — "plan my day", "what should I do today", "make my daily plan", "set up my day", "morning routine", "help me prioritize my tasks", "規劃今天", "今天要做什麼", "排今天的任務", "幫我安排今天" — even if they don't name a skill. This is the morning-routine orchestrator: it runs gmail-helper as its own first step, so prefer it over gmail-helper whenever the user wants a whole-day plan and not only email triage.
Glowboth/skillsync-mcp Skill
0★Provide an MCP server that enables seamless integration and management of SkillsMP data with Node.js environments supporting Model Context Protocol.
The same file is in 1 other repository
ArthurZakirov/SkillPort/skills/skillport-distribution-system Skill
0★ repoUse when packaging, publishing, or updating a public agent-skill repository so it can be installed across machines, repos, Codex, Claude Code, and local skill directories.
bensimpson-ch/claude-skills/ddd-coach Skill
0★ repoDomain-Driven Design reference for pure Java domain modules. Enforces ubiquitous language, strong typing, tactical patterns, and hexagonal architecture boundaries. Consult when writing or reviewing domain-layer Java code.
dombrovsky/dombrovsky-claude-skills/skills/csharp-code-cleanup Skill
0★ repoAutomated C# code cleanup using ReSharper CLI to fix StyleCop violations, format C# code, and maintain consistent code style in .NET projects. C# ONLY - not for other languages.
lsscecilia/skills-for-microservices/be-api-trace Skill
no license0★ repoHelp a backend engineer gather cross-repo context from browser DevTools network calls, trace API ownership to the right microservice, understand frontend data expectations, and determine exactly what backend changes are needed. Use when user pastes a DevTools network call, asks "which service owns this", wants to understand FE dependencies, or says "be-api-trace" or "trace this API".