テスト・セキュリティのスキル

Audit CLI, API, MCP or SDK discovery, first use and error recovery. Use when: designing an agent-facing tool or investigating misuse, including one command.

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。

Review code for security problems; scan for vulnerabilities, secrets, dependency and prompt risks. Use when: asked whether code is safe to ship, even one small handler.

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。

Find or curate supported lessons and agent rules. Use when: asked to remember, trace a corrected claim, audit instructions or write an agent rule.

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。

Brainstorm evidence-backed options for what to build, or stress-test an idea. Use when: deciding what to build next, comparing options or testing an idea.

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。

Write or assess tests that prove behavior and would fail without the fix. Use when: writing tests, TDD, or asked whether a green test is enough.

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。

Create, repair, audit or consolidate agent skills (SKILL.md packages). Use when: writing or fixing a skill, its description or structure. Not for one-off lessons; use Memory.

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。

Audit claims that work is done or shipped against the diff or repo. Use when: asked whether something really got done, even if it looks obvious.

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。

Change or repair code, config or services without weakening tests; report what ran and what did not. Use when: implementing a change or fixing a defect.

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, sanity-checks and reads out product experiments (A/B tests, holdouts, pre/post, geo and incrementality tests) and produces an experiment brief plus a readout with a ship / hold / replicate call. Use when you ask 'should we A/B test this', 'how long should the test run', 'is this result real', 'sample size', 'stat sig', 'SRM', 'holdout', 'our win rate is low', or need to grade an existing test plan or readout. Draws on 191 insights from 71 Lenny's Podcast guests, led by Ronny Kohavi, Ramesh Johari and Archie Abrams.

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 an idea into a working, user-testable prototype with AI builders (Lovable, v0, Bolt, Replit, Cursor, Claude Code) and gets you unstuck when the tool breaks. Produces a Prototype Brief with a build-prompt pack, a debugging log and a user-test plan. Use for 'vibe coding', 'build a prototype', 'prototype this feature', 'Lovable prompt', 'my AI builder is stuck', 'prototype instead of a PRD', or 'demo for users'. Draws on 44 Lenny's Podcast guests incl. Lazar Jovanovic, Zevi Arnovitz and Guillermo Rauch.

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 product or startup idea into a ranked list of riskiest assumptions, the cheapest test for each, pass/kill thresholds, and a go/pivot/kill readout, before anyone builds. Use when someone says "validate my idea", "is this worth building", "what's the riskiest assumption", "design an MVP", "fake door", "smoke test", "will people pay", "pre-sell", "customer discovery plan" or "should we build this". Draws on 82 Lenny's Podcast guests incl. Mike Maples Jr., Eric Ries and Jake Knapp.

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 an eval plan for an AI feature - error analysis on real traces, failure-mode ranking, code checks and binary LLM judges validated against human labels, CI tests, production monitoring, and a launch bar. Use when you ask how do we eval this, how do I test an AI feature, our LLM outputs are inconsistent, are the evals good enough, LLM-as-judge, hallucinations, or what accuracy is good enough to launch. Draws on 41 Lenny's Podcast guests incl. Hamel Husain, Shreya Shankar and Sander Schulhoff.

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 wiring a verify-then-fix loop around a code-editing LLM agent. The agent edits → runs lint/test → reads the output → fixes → re-runs, bounded by an iteration cap and an escalation rule. Activates whenever a coder agent has a verifiable success criterion (exit code, type-checker output, failing assertion) and the user wants the agent to converge to "green" on its own. Framework-agnostic — wraps Aider's `--auto-lint`/`--auto-test`, an OpenHands SWE-Bench loop, a manual LangGraph cycle, or Claude Code's bash tool just the same.

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。

Symbol-level code context for LLM coder-agents: tree-sitter extracts symbols, PageRank ranks them over the cross-file reference graph, and the top class/function signatures are fed to the LLM as a token-budgeted read-only map (not RAG, no vector index, human-auditable). Use when an agent must locate the right files in a large/multi-file repo, when builds/refreshes/scopes a repo-map, or when "model edits the wrong file" needs fixing.

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。

Build a held-out eval set, run it on every prompt/model change, and block regressions in CI. An LM change is a code change — gate it with a test suite (eval set + metric + threshold). Cross-framework SOP not surfaced by any single base skill.

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 terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format + human-in-loop REPL). Use when editing code in an existing git repo via an LLM, when you need to converge a change to 2-5 files, pick an edit format that fits the model, run architect+editor mode, or wire an auto-test loop.

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。

Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix cycles. Encodes the one rule every framework documents quietly and every team relearns expensively: the LM in the loop is NEVER a reliable terminator. Termination must be provided by an explicit counter + exit predicate + stagnation signal + escalation path that live OUTSIDE the LM's control. This is a tool- level, framework-agnostic skill. It maps onto LangGraph (recursion_limit + state counter + interrupt), CrewAI (max_iter + max_rpm + human_input), Claude / OpenAI SDKs (max_iterations + tool_use_budget), DSPy (declared evaluation budget), Aider (REPL + explicit retry cap), and AutoGen (max_consecutive_auto_reply). Search keywords: infinite loop, recursion limit, recursion_limit, GraphRecursionError, max iterations, max_iter, agent stuck, agent won't stop, runaway agent, ReAct loop not terminating, agent repeating itself.

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。

Audit how a brand appears in AI-powered search (ChatGPT, Perplexity, Claude, Gemini). Use when user mentions "AI search," "how do I show up in ChatGPT," "AI discoverability," "AEO," "LLM visibility," or wants to understand their brand's AI presence.

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。

Full conversion audit for any homepage or landing page. Use when someone asks to "review my homepage," "audit my landing page," "why isn't my page converting," "check my website," or wants feedback on their marketing page. Requires URL or screenshot before proceeding.

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。

Audit your Obsidian vault in Claude Code — finds stale drafts, empty folders, duplicate filenames, and incomplete files. Saves a dated report.

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。

Audit and rewrite your LinkedIn profile to attract the right people. Scores each section, rewrites headline and about copy, and includes an AI visibility checklist so you show up in ChatGPT, Perplexity, and Claude search. Use when someone says "optimize my LinkedIn," "LinkedIn profile help," "rewrite my about section," or "how do I show up in AI search."

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。

Security architecture and implementation patterns. Use when designing security controls, implementing authentication/authorization, conducting threat modeling, or ensuring compliance with security frameworks.

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。

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

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。

Query and manage Google NotebookLM notebooks with persistent profile auth, source sync, batch/multi queries, and structured exports. Use when user asks to query NotebookLM, 'ask my notebook', shares NotebookLM notebook URLs, wants to list/create notebooks, manage sources, do bulk folder sync, dedupe, or audit exports.

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。