kpab

@kpab source repo

16 skills
0 followers
6 hours ago last updated

▌
Socratic Comprehension · kpab
A Socratic sparring partner that helps the user understand a difficult text, paper, or concept well enough to explain it in their own words. It does not summarize or ghost-write; it makes the user reconstruct the logic and pushes back on their wording. Use it whenever the user wants to understand, grok, or internalize something for themselves — e.g. "what does this mean", "I want to understand this myself", "help me make this click", "I want to organize this for my own use", "break this down for me", "I want to check that I really got it", or in Japanese 「これどういうこと」「自分のために理解したい」「腹落ちさせたい」「自分用にまとめたい」「噛み砕きたい」「ちゃんと分かったか確かめたい」. Also applies when working through papers, articles, hard concepts, or jargon. Do NOT use it when the user clearly wants a deliverable written for them ("summarize this", "write an article", "draft an explanation" / 「要約して」「記事にして」「説明文を書いて」) — in that case skip the method and confirm the goal (understanding vs. a deliverable) exactly once.

0
installs
▌
Collect · kpab
ネタ系スキルの新規候補を発掘する。「新しいネタスキル探して」「候補集めて」「巡回して」と言われたら使う。GitHub を定型クエリで巡回し、未掲載のリポジトリ候補をリストアップする。

0
installs
▌
Add Skill · kpab
ネタ系スキルをリストに1件追加する。「このスキル追加して」「これ載せて」とURLを渡されたら使う。skills.yaml への追記と README 再生成までを一貫して行う。掲載対象は GitHub リポジトリのみ。

0
installs
▌
SEO Mastery · kpab bundle
Evidence-based SEO and generative search visibility: technical/content SEO, schema.org / JSON-LD, Core Web Vitals, E-E-A-T, Astro, Cloudflare Workers/Pages, and audits. Use for SEO, robots.txt, sitemaps, canonical, hreflang, meta tags, LCP/INP/CLS, GEO (Generative Engine Optimization), LLMO (Large Language Model Optimization), AEO (Answer Engine Optimization), AI visibility, AI citation / AI citations, AI mentions, generative search, ChatGPT Search, Perplexity, Claude search, AI search optimization, AI Overviews / AI Mode, llms.txt, AI crawler control, citation readiness, entity clarity, and information gain audits. For English requests use this skill; for Japanese use seo-mastery-jp. Load only one.

0
installs
▌
SEO Mastery Jp · kpab bundle
公式情報・研究に基づくSEOと生成AI検索の可視性改善。技術SEO、コンテンツ、schema.org / JSON-LD、Core Web Vitals、E-E-A-T、Astro、Cloudflare Workers/Pages、サイト監査に対応。SEO、robots.txt、sitemap、canonical、hreflang、meta tags、LCP/INP/CLS、GEO (Generative Engine Optimization)、LLMO (Large Language Model Optimization)、AEO (Answer Engine Optimization)、AI visibility、AI citation / AI citations、AI mentions、generative search、ChatGPT Search、Perplexity、Claude search、AI search optimization、AI Overviews / AI Mode、llms.txt、AIクローラー制御、引用可能性・エンティティ・独自情報の監査で使用する。日本語の依頼には本Skill、英語にはseo-masteryを使い、両方を同時に読み込まない。

0
installs
▌
Claude Fable 5 Skills · kpab bundle
10 Agent Skills built specifically for Claude Fable 5 and 5.1 — intent, boundaries, and verification hooks instead of the step-by-step micromanagement older-model skills relied on. See skills/ for the individual skill files.

0
installs
▌
Scope Guard · kpab
Prevent Claude Fable 5 / 5.1 from taking unrequested actions — applying fixes when only asked to diagnose, sending or drafting messages nobody asked for, creating backup branches, or running state-changing commands on thin evidence. Use in ops/debugging sessions, shared environments, production-adjacent work, and any conversation where the user thinks out loud.

0
installs
▌
Act When Ready · kpab
Stop Claude Fable 5 / 5.1 from over-planning, re-deriving settled facts, or surveying options it will never pursue. Use in any interactive or agentic session where responses feel slow, turns run long on simple asks, or the model keeps restating context before acting. Especially valuable at high effort settings and in ambiguous, multi-threaded requests.

0
installs
▌
Markdown Memory · kpab
A file-based lesson memory that Claude Fable 5 / 5.1 reads and maintains across sessions. Use for any recurring agent (daily jobs, long projects, team assistants) where the same corrections keep being re-made, and when bootstrapping a new agent from past session history. Fable 5 benefits from recorded lessons noticeably more than prior models did.

0
installs
▌
No Gold Plating · kpab
Keep Claude Fable 5 / 5.1 changes minimal — no unrequested refactors, abstractions, defensive code, feature creep, or test files out of proportion to the change. Use in code review, bug fixes, and any coding session where diffs come back bigger than the ask, with extra helpers, error handling, "while I was here" cleanup, or more committed tests than the change warrants. Particularly important at high and xhigh effort.

0
installs
▌
Skill Refactorer · kpab
Audit and rewrite existing agent skills, system prompts, and CLAUDE.md files for Claude Fable 5 / 5.1. Use whenever the user mentions migrating, upgrading, porting, or "fixing" a skill or prompt for Fable 5 or 5.1, complains that a previously good skill now produces worse output, or asks why the model ignores or over-follows old instructions. Also trigger when reviewing any skill written before June 2026, or any skill written for Fable 5 that now runs on Fable 5.1.

0
installs
▌
Effort Calibrator · kpab
Choose and tune the effort setting for Claude Fable 5 / 5.1 workloads. Use whenever the user asks which effort level to use ("what effort should this batch job run at?", "is xhigh worth it here?"), complains that Fable 5 or 5.1 is slow or expensive, wants to cut latency or token cost, designs a pipeline/harness that mixes routine and hard tasks, migrates a tuned effort setting from Fable 5 to 5.1, or reviews API code that sets output_config.effort.

0
installs
▌
Grounded Progress · kpab
Make Claude Fable 5 / 5.1 progress reports verifiable against actual tool results during long autonomous runs. Use for any multi-hour or overnight agent session, scheduled pipelines, CI agents, or whenever the user has been burned by status updates claiming work that wasn't done. Apply before launch, not after a fabricated report appears.

0
installs
▌
Regrounding Summary · kpab
Make Claude Fable 5 / 5.1's final report readable to someone who saw none of the work. Use for long agentic sessions, overnight runs, and multi-tool tasks — whenever summaries come back as arrow-chain shorthand, invented abbreviations, references to reasoning the reader never saw, dense unbroken paragraphs, or source passages reproduced without quotation marks. Pair with grounded-progress for status content; this skill governs the prose.

0
installs
▌
Subagent Orchestration · kpab
Patterns for delegating work to parallel subagents with Claude Fable 5 / 5.1 — when to split tasks, async coordination, long-lived workers, fresh-context verifiers, and keeping tool calls batched in agent loops. Use when designing multi-agent harnesses, when a large task has independent parts, when runs bottleneck on sequential steps or on one-call-per-turn loops, or when self-review keeps missing its own mistakes.

0
installs
▌
Autonomous Continuation · kpab
Keep Claude Fable 5 / 5.1 running to completion in unattended pipelines — no stopping on a statement of intent, no mid-run permission questions, no quiet narrowing of the task, no self-imposed session splits over context worries. Use for overnight runs, scheduled jobs, CI agents, and any harness where nobody is watching to type "continue".

0
installs

16 published skills