AgentStack
shimo4228 avatar

shimo4228

49 listings · 0 installs

Open-source publisher. Listings imported from github.com/shimo4228 — credited to the original author with their license.

↗ github.com/shimo4228
49+ results
Self-run
SKILL

Write Prompt

Generate concise LLM prompts using the lightweight prompt-writer agent. Avoids main-model overthinking.

0
9
Free
Self-run
SKILL

Codex Review

Cross-model code review — get a read-only second opinion from the OpenAI Codex CLI (a different model family) on the current diff, then fold its findings into the Claude Code review chain. Use when the user says "codex review", "cross-model review", "second opinion on this diff", "別モデルでレビュー", invokes /codex-review, or when the planning.md Review/Cleanup step wants a decorrelated reviewer alongsid…

0
10
Free
Self-run
SKILL

Paper Writing

Academic paper / preprint / position paper の draft skill。Title + outline + section drafting + abstract + references の手順正本。Primary source への直接 access を強制し、claim と cite の 1:1 mapping を author に握らせる。SSRN / arXiv / Zenodo / journal venue 向けに使う。Voice 規約・Source Fidelity 規約・Citation 規約は orchestrator skill `paper-ecosystem` を参照する。

0
9
Free
Self-run
SKILL

Ai Native Preprint Submission

AI-native 出版プラットフォーム (aiXiv / AiraXiv 等、AI 審査・agent 読者を持つ preprint archive) へ、deposit 済み論文を投稿するワークフロー。経路は 2 つ — (A) Web UI + browser automation (初回投稿の default。Claude がフォーム入力を代行し、アカウント作成・ファイル選択・送信クリックは著者が行う人間ゲート分担)、(B) 著者発行の API key による MCP 投稿 (2 本目以降・著者が明示委任した場合)。Use when the user says 「aiXiv/AiraXiv に投稿して」「AI-native プラットフォームに論文を出して」「API キーで残りを投稿して」or invokes /ai-native-preprint-submission. NOT f…

0
15
Free
Self-run
SKILL

Writing Ecosystem

人間向け執筆・レビューエコシステムの orchestrator。記事・エッセイ・ブログポスト・ニュースレター等の **人間 primary** コンテンツを書く / レビューするときに使う。article-writing / editor / essay-reviewer / fact-checker の役割境界と使い分け、AI slop 禁止リスト(日英)、Voice 規約(だ/である × 発見調)、タイトル規約を正本として保持する。AI 向けドキュメント(llms.txt 等)には `llms-txt-writer` を使う。

0
11
Free
Self-run
SKILL

Rules Distill

Scan installed skills to extract cross-cutting principles (those appearing in 2+ skills) and distill them into rules — append to, revise, or create rule files. Use when the user says "distill rules", "/rules-distill", "promote patterns to rules", "what principles should become rules", after installing new skills, or when a skill-stocktake surfaces recurring patterns. NOT for auditing skill qualit…

0
13
Free
Self-run
SKILL

Kickoff

新セッションの定型立ち上げルーチン。dispatch でローカル新セッションを起こした直後の最初のプロンプト(または任意のセッション開始時)に `/kickoff [フォーカス]` と打つと、repo 状態の把握(git status / branch 同期 / 直近コミット / 構成)、未完了シグナル検出(dirty / stash / 未 push / open PR)、固定フォーマットの状態報告までを一発で行う。Use when the user invokes /kickoff, or opens a session with 「まず状態を確認して」「立ち上げルーチンやって」「今どんな状態か教えて」. NOT for: 新セッションの起動そのもの(それは dispatch UI / spawn-session)、既存会話の resume(--continue / --resume…

0
8
Free
Self-run
SKILL

Wiki Query

Obsidian Vault の LLM wiki (wiki/concept/) に問い合わせ、[[ ]] 出典付きで合成回答する read-only クエリ。vault セッションだけでなく研究 repo (AKC / AAP / contemplative / authorship 等) のセッションからも呼べる。Use when the user invokes /wiki-query <問い>, asks 「wiki に聞いて」「wiki ではどうなってる?」, or when working in a research repo and a synthesized understanding of past daily-research notes would answer the question faster than grep. NOT for wiki への書き込み・…

0
12
Free
Self-run
SKILL

Jsonld Knowledge Graph

Design and ship a companion JSON-LD knowledge graph (graph.jsonld) next to llms.txt for projects with stable concept-level structure. Encodes domain entities and relationships as schema.org triples for LLM citation. Use when project has matrix / hierarchy / phase-binding structure that prose alone leaves implicit, AND that structure is stable across releases. Defers llms.txt navigator wording to…

0
8
Free
Self-run
SKILL

Code And Llm Collaboration

Design patterns for layering deterministic code and LLM calls in a single pipeline or agent. Use when designing a pipeline that mixes semantic and structural work — distillation, extraction with validation, approval gates, orchestrated multi-step workflows. Catalogs four load-bearing layering patterns (LLM→Code guard, Code filter→LLM, LLM judge + Code enforce, Code orchestrator + LLM worker) with…

0
11
Free
Self-run
SKILL

Skill Stocktake

Audit installed Claude skills for quality and surface Keep/Improve/Update/Retire/Merge verdicts. Use when the user says "audit my skills", "stocktake", "review my skills", "which skills should I retire or merge", "do a quality pass over my skills", or "/skill-stocktake". NOT for creating or improving a single skill (that is skill-creator) and NOT for whole-config GC across hooks/permissions/MCP (…

0
9
Free
Self-run
SKILL

Release Doi

DOI-registered research repo (Zenodo) のリリース手順。CODEMAPS / README 多言語 / CHANGELOG / CITATION.cff / pyproject.toml / llms.txt / glossary を整合させてから tag push、Zenodo 自動採番後に新 DOI を反映し、Software Heritage archive + SWHID 記録 (intrinsic identifier 層) まで行う 5 phase + post-release ワークフロー。AKC / AAP / contemplative-agent など shimo4228 系の研究 repo で再利用する。

0
8
Free
Self-run
SKILL

Agent Run

contemplative-agent をバックグラウンドで起動する。引数でセッション時間とバックエンド (ollama / cloud / mlx) を指定(例: /agent-run 4時間, /agent-run 30分 cloud openai, /agent-run 30分 mlx)

0
5
Free
Self-run
SKILL

Hf Sync

Hugging Face Datasets mirror sync for graph.jsonld-bearing research repos. `<Owner/dataset>` を引数に取り、cwd の graph.jsonld を flatten して graph.jsonl と一緒に HF dataset へ upload する。`release-doi` の tag push 後、または ad-hoc resync で起動する。Local の `hf login` token を使うので GitHub Actions / CI auth は不要。

0
16
Free
Self-run
SKILL

Replayable Audit Logs

Design know-how for ADR-0075 observability-by-default — every feature that performs external I/O, calls an LLM, or makes non-deterministic/heuristic decisions ships a replayable append-only JSONL audit log in the same PR. Use when adding or reviewing such a feature (the Verify-gate question "which log answers why, and can we replay it offline?"), when designing a new audit record schema, when a r…

0
5
Free
Self-run
SKILL

Shadow Mode Validation

Design know-how for shadow-mode validation — running a candidate decision mechanism (typically an LLM judgment) in observe-only parallel with the live path, recording what it WOULD have decided per event, and letting the accumulated record decide enforcement, in the style of ADR-0076's skill-selection shadow instrument. Use when an unvalidated stochastic mechanism is about to replace or filter a…

0
5
Free
Self-run
SKILL

Paper Deposit

>-

0
8
Free
Self-run
SKILL

Citation Sync

研究 repo の引用 4 層 (docs 実引用 → .zenodo.json references → graph.jsonld ExternalReference → Wikidata P2860) を監査し、下層から順に同期する orchestrator。Use when the user says 「参考文献が少ない/足りない」「引用がずれてる」「citation を同期して」「引用文献を Wikidata/graph に反映して」, when new external papers were cited in ADR/glossary/empirical docs, before a release of a DOI-registered repo, or when a repo's Wikidata item shows fewer cited works than its…

0
7
Free
Self-run
SKILL

Rules Stocktake

Audit ~/.claude/rules (always-loaded behavioral rules) for quality — per-session residency cost, staleness, redundancy, broken See-skill pointers, and substrate absorption — and assign Keep/Improve/Update/Merge/Demote-to-skill/Dissolve/Retire verdicts. Use when the user says "audit my rules", "rules stocktake", "review my rules", "which rules should be demoted or dissolved", "rules が肥大化してきた", "ルー…

0
10
Free
Self-run
SKILL

Wikidata Federation

Create Wikidata items for researchers, papers, and research repositories and cross-link them with ORCID / DOI / graph.jsonld — an identifier-federation skill. Use it after publishing a new paper or DOI-registered repo to register it on Wikidata, when standing up an author item, when injecting QIDs into graph.jsonld as sameAs, or when setting up a Scholia profile. Always trigger on requests like "…

0
10
Free
Self-run
SKILL

Signal First Research

Design guide for a research intake filter that admits only information likely to change your next action. Use when you are about to build a recurring research workflow (daily digest, news stream, topic monitor, literature feed) and the default question "what should I read?" keeps producing too much. Covers the define-signal-first rule, three worked examples, and a diagnostic checklist for telling…

0
8
Free
Self-run
SKILL

Cited Source Mirror Verification

Verify a cited empirical/numeric claim against an open mirror (aiXiv, OpenAlex, Semantic Scholar, the author's own copy) before citing it, whenever the primary source is access-blocked (SSRN / publisher 403, paywalled PDF) OR the claim arrived through an LLM-generated research digest, daily-research note, or WebSearch summary. Use this whenever you are about to cite a statistic, effect size, odds…

0
8
Free
Self-run
SKILL

Llms Txt Writer

AI 向けドキュメント(llms.txt / llms-full.txt、FAQ ページ、用語集等)を書くスキル。Answer.AI llms.txt 標準準拠と GEO/AEO 静的解析の両輪で、ChatGPT / Perplexity / Gemini に引用されやすい AI-facing コンテンツを生成する。audience が AI 専用の doc に使う(README 等の人間向けには使わない)。

0
7
Free
Self-run
SKILL

Spawn Session

新しい detached な Claude Code Remote Control セッションを tmux で起動し、Claude モバイルアプリのセッション一覧に出す。生きている任意のセッションから(多くは iPhone の Remote Control 越しに)呼んで、別プロジェクトの新規セッションを Mac に触れず立ち上げる。Use when the user says 「新しいセッション立てて」「AAP のセッション開いて/立ち上げて」「contemplative のセッション作って」「spawn a (new) session」「launch a remote control session」「start a session for X」, or invokes `/spawn-session [project]`. NOT for: 既存会話の resume(`--cont…

0
9
Free
Self-run
SKILL

Skill Health

Scan the skill library for structural technical debt — dangling references where a SKILL.md names a script, bash file, agent, or sibling skill that does not exist on disk ("missing artifacts" debt). Use when the user says "scan skills for debt", "check for dangling/broken references in my skills", "skill health check", "do referenced scripts/agents still exist", or "/skill-health". NOT for holist…

0
11
Free
Self-run
SKILL

Adr Writer

Record a design decision as an Architecture Decision Record (ADR) in the project's `docs/adr/` directory. Use this skill whenever the user says "let's ADR this", "record this decision", "write an ADR for X", or when context-sync Phase 3 needs to extract a buried decision. The skill resolves the target ADR directory from cwd, picks the next sequence number with no collision, delegates 6-section bo…

0
12
Free
Self-run
SKILL

Gap Review

Run a gap-review to generate ranked next-move candidates for a strategy you operate over time — diff what you have already deployed against your own action catalog, your open questions, and the latest relevant literature, surface the gaps, rank candidates, gate each through your framework's checklist, and record survivors in a private operational ledger that stays separate from any public, effect…

0
9
Free
Self-run
SKILL

Skill Comply

Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines

0
11
Free
Self-run
SKILL

Context Sync

Audit and fix project documentation — detect role overlaps between context files (CLAUDE.md, CODEMAPS, ADR, README), migrate misplaced content, check freshness against code, and create missing docs. One command to keep all project context healthy.

0
9
Free
Self-run
SKILL

Search First

Research before writing code for any new feature, integration, library selection, or utility — search npm / PyPI / MCP / GitHub / existing skills for solutions instead of building from scratch. Use whenever the user says 'add X functionality', 'implement Y', 'set up Z', 'integrate W', asks 'what library should I use for...', 'is there a package/client/MCP for...', proposes a specific tool while o…

0
8
Free
Self-run
SKILL

Paper Ecosystem

Academic paper / preprint / position paper の執筆・レビューエコシステムの orchestrator。SSRN / arXiv / Zenodo / journal venue 向けの **harness-neutral な学術コンテンツ** を書く / レビューするときに使う。paper-writing / paper-reviewer / source-fidelity-checker / vocabulary-consistency-checker / clarity-reviewer / citation-formatter の役割境界と使い分け、Source Fidelity Rules、Vocabulary Consistency Rules、Academic Voice Rules、Reader Clarity Rules、Cita…

0
12
Free
Self-run
SKILL

Collect Context

セッション内外のコンテキストを収集し、記事執筆用の素材ファイルを生成する

0
11
Free
Self-run
SKILL

Wiki Harvest

研究 repo セッションから LLM wiki (Obsidian Vault wiki/concept/) を read-only で走査し、その repo の主担当 concept ページから「repo の次アクションを変えうる候補」だけを抽出して、一次出典付き・landing slot マップ付きのランク付き候補台帳 (ledger) を repo の .notes/ に生成する。Use when the user invokes /wiki-harvest, asks「wiki から repo に還元して」「wiki の有益分を AKC/AAP/CA/authorship に持ってきて」, or when closing the daily-research→wiki→repo loop. wiki への書き込みは行わない(それは vault セッションの /ingest)。c…

0
11
Free
Self-run
SKILL

Read Only Instruments

Design know-how for read-only instruments (計器) — aggregate readings over stored state (distributions, compositions, cluster structure) that inform the operator before an intervention, in the style of ADR-0071's pattern-composition instruments. Use when quantifying an open observation before intervening (instrument-first sequencing), when a design floor/threshold would otherwise be guessed, when c…

0
4
Free
Self-run
SKILL

Weekly Report Diagnosis

Weekly レポート (A-E) を入力に、コードベース + ADR + identity/constitution/skills/rules を読んで F1 (構造提案) / F2 (identity-level questions) / F3 (observations) を別ファイル (weekly-{end-date}-findings.md) として生成する。weekly-analysis.sh が生成する自己内省レポートに対するコード診断 companion。Use when a new weekly report has been generated, or when refreshing F section of past reports after new ADRs land or pipeline code changes.

0
5
Free
Self-run
SKILL

Learn Eval

Extract reusable patterns from the session, self-evaluate quality before saving, and determine the right save location (Global vs Project).

0
12
Free
Self-run
SKILL

Skill Stocktake

Audit installed Claude skills for quality and surface Keep/Improve/Update/Retire/Merge verdicts. Use when the user says "audit my skills", "stocktake", "review my skills", "which skills should I retire or merge", "do a quality pass over my skills", or "/skill-stocktake". NOT for creating or improving a single skill (that is skill-creator) and NOT for whole-config GC across hooks/permissions/MCP (…

0
12
Free
Self-run
SKILL

When Code When Llm

Decision framework for choosing between deterministic code (regex, keyword match, AST parse, schema validation) and LLM-based processing (classification, semantic similarity, judge) for a single task. Use when you catch yourself writing a regex for a task that keeps producing false positives or negatives, or when you are about to call an LLM for something a three-line code check would handle. Cov…

0
10
Free
Self-run
SKILL

Llm Agent Security Principles

Structural security design principles for building LLM agents, autonomous systems, and self-improving harnesses. Use when designing a new agent, reviewing agent architecture, adding a new capability, or auditing an existing agent for prompt injection resistance. Covers three load-bearing principles — Security by Absence, Untrusted Content Boundary, One External Adapter — plus concrete defense pat…

0
4
Free
Self-run
SKILL

Substack Publishing

完成・レビュー済みの human essay を Substack に公開し、LLM 発見のために corpus へミラーするワークフロー。Substack が raw Markdown 非対応なための MD→HTML rich-text paste、Title/Subtitle/body のフィールド分け、タグ戦略(archive 用 ≠ 拡散用)、カバー画像プロンプトの作り方、Claude in Chrome によるエディタ自動操作(OS クリップボードへの HTML flavor 直接セット + cmd+V)、公開後の content repo `substack/` フォルダへのミラー + research repo からの cross-link を扱う。Voice / AI-slop / Title / 出典は writing-ecosystem、翻訳は ja-to-en-tr…

0
10
Free
Self-run
SKILL

Repo Asset Stocktake

Audit a project repository's non-code assets — tool configs, CI/GitHub workflows, runbooks and other docs — for diminished value, and assign Keep/Update/Retire/Merge verdicts. Every non-code asset serves a consumer (a tool invocation, a CI trigger, a human reader) — this skill flags assets whose consumer has vanished or which no longer serve it. Use when the user says "audit my repo assets", "whi…

0
15
Free
Self-run
SKILL

Skill Comply

Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines

0
1
Free
Self-run
SKILL

Ja To En Translation

日本語→英語の voice 保持翻訳スキル。エッセイ・研究ドキュメント・README・ADR 等の人間向け prose を、著者の声・register・発見調を保ったまま自然な英語にする。逐語訳でも MT でもなく、term-lock + 2-pass(訳→自己添削)+ back-translation QA で品質を担保する。日本語記事を英語にする JA→EN 翻訳タスクで使う。AI 向け doc は llms-txt-writer、学術 citation format は citation-formatter、英語 AI-slop / Voice / Title 規約と出典編入は writing-ecosystem に defer。

0
11
Free
Self-run
SKILL

Harness Sync

ローカル harness (~/.claude) の origin-filtered コンポーネントを公開 repo (claude-harness 集約 repo + 単独 skill repo 群) へ一方向同期する。Use when the user says 「ハーネスを公開 repo に同期して」「claude-harness を更新して」「スキルを公開して」「skill repo を同期して」 or invokes /harness-sync. 収集 → secret scan → subtree 置換は決定論的 script が行い、diff レビュー・README/llms.txt の整合・コミットは会話で行う。NOT for: 公開 repo から ~/.claude への逆方向取り込み、ECC 等外部 origin の公開判断、汎用化 fork を持つ curated…

0
10
Free
Self-run
SKILL

Readme Writer

README やプロジェクトのトップページ(repo を開いた人が最初に見る入口)を書く・直すときに使う。こんな時に必ず呼ぶ — README が長い/文字の壁で読まれない→短く走査しやすくしたい、開いて数十秒で「何のプロジェクトで自分向けか」が伝わる入口にしたい、構成図・アーキ図を入れたい(PNG や架空図でなく Mermaid を勧める)、badge を貼りすぎたので整理したい、長い rationale や「なぜ」を docs/ に逃がしたい、研究・DOI repo の README を引用付きで読める長さにまとめたい。短く・視覚優先にしつつ、LLM が README 一枚で要点を復元できる情報フロアは残す。CLI でも UI でも研究 repo でも、日本語でも英語でも、新規作成でも既存改善でも対象。AI 専用ドキュメント(llms.txt / llms-full.txt 等)は対…

0
3
Free
Self-run
SKILL

Authorship Strategy

maker / 実践者が AI 時代の著者戦略を実地で探るための判断フレームワーク。あなた自身の DOI-registered idea-rescue repo 群(著者自身の例は AKC, Contemplative Agent)で適用する。core principle は「AI 時代のオーセンシティ inversion」— 3 軸(scarcity → diffusion / exclusivity → derivation / enclosure → openness)の反転。主 audience は LLM-mediated channels(LLM 直接 + LLM 経由で情報を得る人間)。creative reuse > training > investigation の preference 階層。4 層 framework (authenticity → diffusi…

0
9
Free
Self-run
SKILL

Task Stocktake

Audit and consolidate a repository's pending-task tracking into its single task ledger (default .notes/TASKS.md) — bootstrap the ledger if missing, sweep handoff / audit / remaining-issues files and auto-memory for stray task lines, verify pending entries against git log and actual code, and propose archiving detail files of completed tasks. Use when the user says "残タスクを棚卸しして", "タスク台帳を作って/整理して",…

0
9
Free
Self-run
SKILL

Readme Writer

README やプロジェクトのトップページ(repo を開いた人が最初に見る入口)を書く・直すときに使う。こんな時に必ず呼ぶ — README が長い/文字の壁で読まれない→短く走査しやすくしたい、開いて数十秒で「何のプロジェクトで自分向けか」が伝わる入口にしたい、構成図・アーキ図を入れたい(PNG や架空図でなく Mermaid を勧める)、badge を貼りすぎたので整理したい、長い rationale や「なぜ」を docs/ に逃がしたい、研究・DOI repo の README を引用付きで読める長さにまとめたい。短く・視覚優先にしつつ、LLM が README 一枚で要点を復元できる情報フロアは残す。CLI でも UI でも研究 repo でも、日本語でも英語でも、新規作成でも既存改善でも対象。AI 専用ドキュメント(llms.txt / llms-full.txt 等)は対…

0
8
Free
Self-run
SKILL

Apple Silicon Local Llm Serving

Apple Silicon (M1–M5) でローカル LLM の推論ランタイムを選ぶ・足す・最適化するときの判断軸。mlx_lm.server は Ollama 比 ~1.8x 速だが生成専用(埋め込み endpoint なし・response_format/JSON schema 拘束なし)なので埋め込みは Ollama に残す2サーバ構成になる点、ユニファイドメモリは VRAM 容量でなくメモリ帯域律速で MoE は RAM を節約しない点、コンテナは Metal 非対応な点を扱う。Use when 「Mac でもっと速く / 大きいモデルを動かしたい」「mlx-lm / MLX を入れたい」「Ollama から乗り換え / 併用したい」「16GB で実用的なモデルは」を検討するとき、生成を MLX に寄せて埋め込みの扱いで詰まったとき、ローカル LLM のベンチ A/B でメモリ…

0
6
Free