「diff」の検索結果

Capture outbound HTTP and telemetry from a CLI harness at runtime. Covers capture-channel selection (transcript file vs verbose-fetch stderr vs outbound proxy vs on-disk state), hook-driven per-event capture vs long-running session capture, JSONL output format for diff-friendly artifacts, and the observability table that maps each target to the cheapest channel that captures it. Use when a static finding needs runtime confirmation, when a payload shape is needed for a client re-implementation, or when dark-vs-live disambiguation requires watching what the binary actually sends.

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。

Select an OCR/HTR engine by benchmarking candidates on the same labelled samples — source ground truth from open datasets (e.g. Hugging Face PAGE-XML corpora) or hand-transcription, wrap every engine behind a transcribe(image_path) -> str adapter (vision-LLMs via any OpenAI-compatible endpoint, dedicated HTR REST APIs, cloud OCR), and score with zero-dependency raw CER, lenient CER, WER, and a critical name/date token diff. Use when choosing an engine for handwriting or historical-document transcription, when published accuracy claims need honest verification on your own material, or when a records workflow must surface confident-but-wrong names and dates that a low aggregate CER hides.

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。

Achieve distributed agreement without central authority using bee democracy, threshold voting, and quorum sensing. Covers proposal generation, advocacy dynamics, commitment thresholds, deadlock resolution, and consensus quality assessment. Use when a group must decide between options without a designated leader, when centralized decision-making is a bottleneck, when stakeholders have different perspectives to integrate, or when designing automated systems that must reach consensus such as distributed databases or multi-agent AI.

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。

AI relational calibration — reading and adapting to the specific person you are working with. Goes beyond user-intent alignment (solving the right problem) to genuine attunement (meeting the person where they are). Maps communication style, expertise depth, emotional register, and implicit preferences from conversational evidence. Use at the start of a new session, when communication feels mismatched, after receiving unexpected feedback, or when transitioning between very different users or contexts.

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。

Generalised autonomous optimisation loop — soft RLVR for any artifact a user can measure. Web runtime package: uses memory in this order: connector-backed, project-pack, none. Never assumes subprocess access or unrestricted local files. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning from each attempt. Triggers include: "optimise this", "keep improving until it's good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles.

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。

Generalised autonomous optimisation loop — soft RLVR for any artifact a user can measure. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning from each attempt. Triggers include: "optimise this", "keep improving until it's good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles. Also use when the user wants to improve a system prompt, a data pipeline, a writing style, or any artifact where quality can be decomposed into measurable tracks. For inference optimisation tasks (model latency, throughput, quantization, GPU deployment), a* delegates the low-level tuning to AITune while maintaining quality tracking and learning.

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。

Post-implementation self-review. Use AFTER finishing ANY code implementation or change — before declaring it done, committing, or opening a PR — to critique your own work: re-read the diff adversarially, confirm unit tests cover every branch/edge, kill duplication, follow clean-code/SOLID and the repo's own docs & invariants, decide if something should become documentation, update/prune memory, and strip outdated comments. Trigger it whenever you've just written or modified code and are about to wrap up, even if the user didn't explicitly ask for a review.

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。

The TaskBarHero game updated (new version) and the tbh-meter reader needs re-calibration — symptoms are gold showing 0, stage mode "?", or the live party/XP/stats dropping out (party empty / no live levels / runs degraded) after a patch, or you're prepping a meter release for a new game build. Runs the diagnose→dump→diff→reseed→bump→verify playbook (the fix is usually a reseed, but a build can also change an Obscured encoding with zero offset movement — caught only by the live gate, fixed by a read-strategy change). Use when the game version changed, after a TBH patch, when a player reports gold/stage/party/XP broken following an update, or when asked to re-seed / re-calibrate the reader for a new build.

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。

Adversarial, security-first review of a pull request from an EXTERNAL or untrusted contributor — a fork PR, a first-time or unknown author, anyone without write access — before a maintainer merges it. Use this whenever you're reviewing, triaging, or deciding whether to merge a PR opened against tbh-meter by someone outside the maintainer team: 'review PR #123', 'someone opened a PR — is it safe to merge?', 'check this contributor's changes', 'can we take this fork PR?', 'is this contribution legit?'. This is supply-chain DEFENSE, not ordinary code review: every merged PR auto-updates onto every user's machine and ships a memory-reading .exe plus an unsandboxed Electron app, so the author and the PR description are UNTRUSTED and the diff is the only evidence. It posts its verdict as a real GitHub review — an inline comment pinned to each problematic line (via the pulls/reviews API), not just one summary comment. NOT for your own or a fellow maintainer's branch (use self-review for that), and prefer this over the generic review flow for anything coming from outside the team.

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。

Use when a B2B SaaS product needs upstream positioning or messaging clarity — defining who it's for, the category, competitive alternatives, differentiation, value props, strategic narrative, or a messaging hierarchy. Triggers include "my messaging isn't working," "we sound like everyone else," repositioning, or auditing an existing positioning doc. Use before homepage, deck, or sales-narrative work. Not for writing the final copy (use copywriter-skill) or running the sales process (use sales-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。

Django web framework conventions: app layout, settings split (base/local/production), URLconf with app namespacing, CBV and DRF ViewSets, DRF serializers and permissions, form validation, signals, Django admin registration, and middleware. Activated automatically by django-plugin/stack.md. Works alongside python-foundation:python-conventions and django-plugin:django-orm-patterns. Use this skill to: - Structure a Django project with multiple apps and correct URLconf hierarchy. - Write CBVs and DRF ViewSets with appropriate permissions and serializers. - Configure settings correctly for different environments. - Use signals for decoupled event handling between apps. - Register models in Django admin with useful list_display and search_fields. Do NOT use this skill for: - Django ORM model field finalization and migration patterns — see django-plugin:django-orm-patterns. - Python language idioms (type hints, dataclasses, enums) — see python-foundation:python-conventions. - Testing patterns — see python-foundation:pytest-testing.

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。

Navigation in React Native — both React Navigation v7 (classical, modular) and Expo Router (file-based, Expo 49+). Stack, tab, drawer navigators, deep linking, typed navigation, modal presentation, authentication flow patterns. Use this skill to: - Pick navigation lib based on what's installed (@react-navigation/* vs expo-router). - Configure typed routes with ParamList types or Expo Router's generated types. - Set up deep linking (URL schemes, Universal Links, App Links). - Build authentication flow with conditional navigators. - Use modal presentation correctly. Do NOT use this skill for: - Project structure (see rn-conventions). - Platform-specific differences (see rn-platform-specific). - State / storage (see rn-state-and-storage). - Testing navigation (see rn-testing).

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。

Testing React Native: Jest with jest-expo / react-native preset, React Testing Library Native, native module mocking, hook testing. Optional sections for Detox (native automation) and Maestro (declarative YAML e2e). Use this skill to: - Configure Jest preset based on workflow. - Write component tests with @testing-library/react-native. - Mock native modules (react-native-reanimated, expo-*, react-native-mmkv). - Test custom hooks via renderHook. - Set up Detox or Maestro for e2e (optional, requires native toolchain). Do NOT use this skill for: - General RN conventions (see rn-conventions). - Web-React testing (see react-plugin:react-testing — different jsdom setup). - Plain Node testing patterns (see nodejs-plugin equivalents).

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。

Routing libraries for React SPAs: React Router v6/v7 (most common), TanStack Router (typed, modern), wouter (minimal). Detect what's installed and apply matching patterns. Lazy loading, navigation guards, typed params. Use this skill to: - Configure routes (declarative or file-based). - Use navigation hooks (useNavigate, useParams, useSearchParams). - Lazy-load routes for code splitting. - Implement protected routes / auth guards. - Type-safe params via Zod or framework's built-ins. Do NOT use this skill for: - General React conventions (see react-conventions). - State management (see react-state-management). - Form handling (see react-forms). - Next.js routing (different model — see nextjs-plugin).

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。

Plan the skills an ask needs, invoke each as its condition arrives. Use when the ask has multiple aspects that different skills carry, or the user named multiple skills.

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。

Turn words with two readings into one confirmed ask. Use when the user's words admit two readings that would build different things.

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。

Use when reviewing a staged diff or a commit range for soundness against the project's taste rules, including a pre-commit pass or an explicit "sound review".

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。

Analyze the current branch diff against dev, plan integration tests for changed frontend pages/components, and write them. TRIGGER when user asks to write frontend tests, add test coverage, or 'write tests for my changes'.

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。

Incrementally update Mintlify documentation (.mdx) from Python source changes only. Use when: (1) Python files referenced in doc_code_map frontmatter have changed, (2) a PR touches Python modules documented in docs/mintlify/key_modules/ or docs/mintlify/mcp/, (3) the user asks to sync docs after Python code changes. Prefer minimal diffs and leave correct content untouched.

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。

Use when tracking heap allocations on Linux with heaptrack: allocation hotspots, peak heap, temporary allocations, leaks, or a diff of two runs via heaptrack_print. Not for heap errors: use valgrind.

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。

Use when turning perf, DTrace, pprof, or async-profiler stacks into an SVG flamegraph with the FlameGraph scripts, reading one, or diffing two profiles. Not for collecting data: use linux-perf.

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。

Use when asked to create an explainer document for a concept, diff, idea, or work recap. Drafts and verifies it in a scratch directory. Not for one-screen explanations: use explain-concept.

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。

Use when the user and agent may hold different pictures of current state after a gap, sync request, or exposed stale claim. Not for persistence: use memory-update.

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。

Use when a project context-schema differs from the installed entry format. Not for remote, publish, deploy, or irreversible changes.

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。