インフラ・DevOpsのスキル

Runs a product quality review on a journey, feature, landing page, onboarding flow, or AI/agent surface and returns a friction log, a scored critical-journey review, and a taste bar your team can calibrate against. Use when someone asks is this good enough to ship, how polished should it be, why do users bounce, what is our quality bar, how do we build taste, or to review a design, prototype, onboarding, or checkout. Draws on 264 insights from 100 Lenny's Podcast guests incl. Katie Dill, Dylan Field and Stewart Butterfield.

日本語の概要は準備中です。原文の説明を表示しています。

Builds a role scorecard, interview loop, sourcing plan, reference-check guide and close plan for a hire, and grades an existing job description or loop. Use when you say 'I need to hire a PM', 'write a job description', 'interview questions', 'how do I run references', 'first sales hire', 'first marketer', 'head of product search', 'scorecard' or 'how do I close a candidate'. Draws on 210 Lenny's Podcast guests including Adam Ward, Keith Rabois and Lauren Ipsen.

日本語の概要は準備中です。原文の説明を表示しています。

Decide which AI features to build, delay, shelve or kill, and whether each one gets better as models improve. Produces an AI Bet Memo (feature-by-feature verdicts, retest triggers, scaffolding ledger, moat and safety check) from a roadmap or idea list. Use for 'AI strategy', 'AI roadmap', 'what should we build with AI', 'will the next model make this obsolete', 'build vs wait for the model', 'will OpenAI/Anthropic build this', 'agent or chatbot', 'is this feature worth shipping'. Draws on 118 Lenny's Podcast guests incl. Nick Turley, Kevin Weil and Dianne Penn.

日本語の概要は準備中です。原文の説明を表示しています。

Writes (or rewrites) a spec, PRD, PR-FAQ or shaped pitch and grades it against what the best product teams actually do. Use when you ask 'write a PRD', 'how do I spec this', 'PR/FAQ', 'working backwards doc', 'shape this project', 'do we even need a PRD', or 'engineering says the spec isn't detailed enough'. Draws on 56 insights from 38 Lenny's Podcast guests incl. Ryan Singer, Bill Carr and Lane Shackleton.

日本語の概要は準備中です。原文の説明を表示しています。

Turns a hard product or career decision into a one-page decision memo with the eigenquestion, options, pre-mortem with kill criteria, reversibility rating, a named decider and a review date. Use when you ask 'how should we decide', 'should we build or kill this', 'one-way door or two-way door', 'run a pre-mortem', 'we keep going in circles', 'quit or pivot', or want to grade a decision doc. Draws on 396 insights from 177 Lenny's Podcast guests, led by Annie Duke, Shreyas Doshi and Shishir Mehrotra.

日本語の概要は準備中です。原文の説明を表示しています。

Rewrite an exec update, memo, strategy doc, deck outline, Slack post or talk so it lands with senior people, and get a graded score plus the top 3 fixes. Use when you say 'rewrite this for my VP', 'exec update', 'how do I present to the CEO', 'my memo is too long', 'prep me for this review', 'all-hands talk' or 'I get nervous presenting'. Draws on 296 insights from 90 Lenny's Podcast guests incl. Wes Kao, Nancy Duarte and Matt Abrahams.

日本語の概要は準備中です。原文の説明を表示しています。

Diagnoses product-market fit from survey, usage and pipeline data and returns a scored verdict with the next moves. Use when you ask 'do we have product-market fit', 'is our PMF survey good enough', 'what does 35% very disappointed mean', 'should we scale yet', 'why is growth stalling', or need a Sean Ellis survey, retention check, or PMF level read. Draws on 137 insights from 66 Lenny's Podcast guests incl. Sean Ellis, Todd Jackson and Rahul Vohra.

日本語の概要は準備中です。原文の説明を表示しています。

Writes you a ready-to-use script for a feedback or hard conversation, then rehearses the pushback. Use when you need to give tough feedback, confront a peer, tell a report they are underperforming, deny a promotion, prepare to fire someone, say no to your boss, ask for feedback, or repair a conversation that went badly. Draws on 66 Lenny's Podcast guests including Kim Scott, Carole Robin and Alisa Cohn.

日本語の概要は準備中です。原文の説明を表示しています。

Builds a stakeholder map and an influence plan for getting buy-in from executives, founders, peers, engineering, sales or legal, then scripts the pitch, the pushback and the follow-up. Use it for stakeholder management, managing up, getting buy-in, handling a founder's pet idea, disagreeing with the CEO, saying no to a flood of requests, or building trust as a new PM. Draws on 140 Lenny's Podcast guests incl. Jessica Fain, Jeffrey Pfeffer and Hilary Gridley.

日本語の概要は準備中です。原文の説明を表示しています。

Diagnoses why your product team ships slowly and produces a velocity plan with a baseline, a bottleneck map, the top 3 interventions and a stop-doing list. Use it when you say 'we're too slow', 'how do we ship faster', 'projects keep slipping', 'too many meetings', 'approvals take forever', 'our releases are scary', 'velocity', 'cycle time', 'we hired more people and nothing got faster' or 'AI made coding fast but we still ship slowly'. Draws on 226 Lenny's Podcast guests including Farhan Thawar, Nicole Forsgren and Melissa Perri.

日本語の概要は準備中です。原文の説明を表示しています。

Diagnose where your growth is actually leaking (acquisition, activation, retention, or loops) and produce a growth plan with a named loop, an activation definition, a 90-day experiment portfolio and channel guardrails. Use it when someone says growth stalled, signups don't activate, retention is flat, how do we build a growth loop, should we go PLG, onboarding redesign, churn, referral program, or which channel should we bet on. Draws on 672 insights from 143 Lenny's Podcast guests, led by Elena Verna, Casey Winters and Lauryn Isford.

日本語の概要は準備中です。原文の説明を表示しています。

Turns a career question into a decision brief the PM can act on this week - a career plan, a promotion case, a stay-or-leave verdict, a job-search system, or an offer-negotiation script. Use when someone says 'how do I get promoted', 'should I leave my job', 'job search', 'I got laid off', 'negotiate my offer', 'career plan', 'IC or manager', 'next role', 'am I stuck', 'how do I stay relevant with AI' or 'how do I break into PM'. Draws on 188 Lenny's Podcast guests including Phyl Terry, Nikhyl Singhal and Deb Liu.

日本語の概要は準備中です。原文の説明を表示しています。

Builds a pricing model, packaging/tier structure and willingness-to-pay research plan, then grades your existing pricing page or plan. Use when you ask 'how much should we charge', 'what should our pricing model be', 'seat vs usage vs outcome pricing', 'good-better-best tiers', 'what goes in the free plan', 'should we raise prices', 'freemium vs free trial', or 'how do we price our AI product'. Draws on 199 insights from 79 Lenny's Podcast guests including Madhavan Ramanujam, Naomi Ionita and Patrick Campbell.

日本語の概要は準備中です。原文の説明を表示しています。

Turns a pile of ideas, requests and goals into a confidence-scored roadmap plus a goals/OKR set the team can actually follow. Use when someone says 'prioritize', 'what should we build next', 'roadmap', 'now next later', 'ICE or RICE', 'write our OKRs', 'quarterly planning', 'too many priorities' or 'sales keeps changing the plan'. Draws on 133 Lenny's Podcast guests including Itamar Gilad, Christina Wodtke and Janna Bastow.

日本語の概要は準備中です。原文の説明を表示しています。

Designs customer interviews and turns the transcripts into decisions. Produces an interview guide plus a synthesis (forces of progress, jobs, pathways, opportunities) you can paste into a doc. Use for 'customer interviews', 'discovery calls', 'JTBD', 'switch interview', 'who should I talk to', 'how many interviews', 'synthesize these transcripts', or 'why do customers churn/buy'. Draws on 140 Lenny's Podcast guests incl. Teresa Torres, Bob Moesta and Judd Antin.

日本語の概要は準備中です。原文の説明を表示しています。

Builds your north star metric, a metric tree with owned input metrics and guardrails, and a review cadence, as a one-page metrics spec you can paste into a doc. Use it when you ask 'what should our north star be', 'which metric should this team goal on', 'our dashboard is a mess', 'how do we measure AI productivity', 'activation metric', 'OKR metrics', 'vanity metrics', or 'metrics review cadence'. Draws on 254 insights from 118 Lenny's Podcast guests incl. Sarah Tavel, Crystal Widjaja and Jessica Lachs.

日本語の概要は準備中です。原文の説明を表示しています。

Shape a request into one end-to-end slice with observable behavior; review write scope and reversible decisions. Use when: planning, breaking down or scoping a change.

日本語の概要は準備中です。原文の説明を表示しています。

Enhancement-overlay skill — the DECISION + WIRING layer for LM observability that the single-backend skills [[langsmith]], [[phoenix]], [[mlflow]] do NOT cover. Each of those installs one backend; none of them help you DECIDE which backend fits your stack/scale/budget, nor give you a one-line autolog that turns it on fast. Use when starting any LM project, before the first deploy, or the moment someone asks "why did it do that?" and there are no traces to answer with. The skill picks a backend by stack (LangSmith for LangChain/LangGraph; Phoenix for OSS/local OpenTelemetry; MLflow for ML-shops already on MLflow; Langfuse for self-host), wires one-line autolog, verifies traces land, and adds eval hooks — instrumenting BEFORE you need it. Cross-links the first-debug-move skill [[agentsop-prompt-history-inspect]]. Do NOT activate to re-teach a backend you already chose (defer to its own skill), or for non-LM ML experiment tracking with no LLM calls (that is plain MLflow).

日本語の概要は準備中です。原文の説明を表示しています。

SOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin marketplace + observability, self-hostable. Use when shipping LLM apps fast with a "no-code to pro-code" gradient, especially when non-engineers need to co-author the flow.

日本語の概要は準備中です。原文の説明を表示しています。

Screens biomedical / life-science papers for signs of data fabrication, image manipulation, and statistical anomalies, using the detection techniques distilled from the field's canonical exposure platforms (PubPeer, Data Colada, Science Integrity Digest, For Better Science) and tools (ImageTwin/Proofig, statcheck, GRIM/GRIMMER, Problematic Paper Screener, Seek & Blastn). Use when asked to check a paper/figure for image duplication, blot splicing, impossible statistics, paper-mill or tortured-phrase signals, research integrity, or "is this data faked"; or when a user shares a figure, Western blot, supplementary dataset, or DOI and asks whether it looks manipulated. Reports observable anomalies as questions for clarification — it never accuses anyone of fraud.

日本語の概要は準備中です。原文の説明を表示しています。

Decision protocol for building, debugging, and operating LangGraph-based agent systems. Activates when a coder agent is asked to design a stateful LLM workflow, add human-in-the-loop, choose a multi-agent pattern (supervisor / swarm / hierarchical), pick a checkpoint backend, or migrate a fragile chain into a durable graph. LangGraph is positioned by its maintainers as a "low-level orchestration framework for building, managing, and deploying long-running, stateful agents" — this skill encodes the *when* and *why*, not the API.

日本語の概要は準備中です。原文の説明を表示しています。

Project-kickoff rubric for the self-host vs managed-cloud decision — when is running your own inference engine / LLM platform worth the ops cost vs paying per-token for a managed API? Decide on two axes — VOLUME (a cost-crossover slider) and COMPLIANCE (a hard gate). Use at kickoff when choosing where to run inference, or when cost / data-residency pressure forces a re-evaluation.

日本語の概要は準備中です。原文の説明を表示しています。

Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check security alerts, manage variable groups, approve deployments, or configure branch policies. Covers 13 domains with 99 tools via REST API.

日本語の概要は準備中です。原文の説明を表示しています。

Convert documents and text to audio using Google Cloud Text-to-Speech. Use this skill when the user wants to: narrate a document, read aloud text, generate audio from a file, convert text to speech, create a recording of documentation or analysis, create a podcast from a document, or use Google TTS/text-to-speech. Trigger phrases: "read this aloud", "narrate this", "create a recording", "text to speech", "TTS", "convert to audio", "audio from document", "listen to this", "generate audio", "google tts", "create a podcast".

日本語の概要は準備中です。原文の説明を表示しています。