Skip to main content
Manusで任意のスキルを実行
ワンクリックで
organvm
GitHub クリエイタープロフィール

organvm

10 件の GitHub リポジトリにある 382 件の収集済み skills をリポジトリ単位で表示します。

収集済み skills
382
リポジトリ
10
更新
2026-07-24
リポジトリマップ

skills がある場所

収集済み skill 数が多いリポジトリを、このクリエイターカタログ内の比率と職業範囲とともに表示します。

#01
a-i--skills
183 件の skills · 2026-07-18
ソフトウェア開発者その他コンピュータ職プロジェクト管理専門家ウェブ開発者ソフトウェア品質保証アナリスト・テスターテクニカルライター
24 件の職業カテゴリ · 100% 分類済み
48%比率
#02
studium-generale
145 件の skills · 2026-05-19
ソフトウェア開発者その他の高等教育教員データサイエンティストその他の生物科学者グラフィックデザイナーDTPオペレーター
21 件の職業カテゴリ · 100% 分類済み
38%比率
#03
_agent-ontology
34 件の skills · 2026-07-19
ソフトウェア開発者その他コンピュータ職ソフトウェア品質保証アナリスト・テスターウェブ開発者グラフィックデザイナーデータベースアーキテクト
11 件の職業カテゴリ · 100% 分類済み
8.9%比率
#04
narratological-algorithmic-lenses
9 件の skills · 2026-02-16
テクニカルライターその他の高等教育教員市場調査アナリスト・マーケティングスペシャリスト
3 件の職業カテゴリ · 100% 分類済み
2.4%比率
#05
limen
6 件の skills · 2026-07-24
その他コンピュータ職ソフトウェア開発者ウェブ・デジタルインターフェースデザイナーテクニカルライター
4 件の職業カテゴリ · 100% 分類済み
1.6%比率
#06
enterprise-plugin
1 件の skills · 2026-02-24
ソフトウェア品質保証アナリスト・テスター
1 件の職業カテゴリ · 100% 分類済み
0.3%比率
#07
praxis-perpetua
1 件の skills · 2026-07-18
市場調査アナリスト・マーケティングスペシャリスト
1 件の職業カテゴリ · 100% 分類済み
0.3%比率
#08
portvs
1 件の skills · 2026-06-02
その他コンピュータ職
1 件の職業カテゴリ · 100% 分類済み
0.3%比率
ここでは上位 8 件のリポジトリを表示しています。完全なリストは下に続きます。
リポジトリエクスプローラー

リポジトリと代表的な skills

turnstile-spin
ウェブ開発者

Set up Cloudflare Turnstile end-to-end in a project: scan the codebase, create the widget via the Cloudflare API, deploy the managed siteverify Worker, write the frontend snippets, validate, and persist the skill. Load this when a user asks to add Turnstile, set up CAPTCHA, protect a form from bots, or fix a Turnstile integration. Mirrors developers.cloudflare.com/turnstile/spin.

2026-07-18
artifact-resurfacing
その他コンピュータ職

Four-phase protocol for clearing accumulated drift between memory claims, CLAUDE.md citations, and on-disk reality. Detects stale citations, missing files, and orphan plans; classifies findings; emits proposed diffs; codifies prevention. Companion to closeout (closeout discovers orphans; this skill polishes them). Discovery ≠ remediation — Phase 3 emits proposed diffs only; constitutional doc edits require explicit conductor authorization.

2026-06-07
corpus-persona-extraction
データサイエンティスト

Ingest a corpus of session logs (JSONL transcripts, chat exports) and extract a persona profile — vocabulary frequency, unique idioms and coinages, structural analogies — then synthesize an ideal_yearning and archetypal_pattern and append the result to a {persona_id}.lexicon.yaml. Triggers on "extract persona", "build a lexicon", "map the domain language", or any request to process conversation logs into a voice/vocabulary model.

2026-06-07
natural-center-extraction
テクニカルライター

Apply narratological scoring to a text, transcript, or recording transcript — rating contiguous spans for pathos, logos, ethos, kairos, and density — then extract the single highest-scoring contiguous block as the work's Natural Center, with a scoring table and justification. Triggers on "find the natural center", "extract the most dramatic moment", "what's the strongest passage", or pulling the peak block from a long artifact for a short, excerpt, or trailer.

2026-06-07
parametrize-and-cite
ソフトウェア開発者

Transform any data, document, deck, README, manifest, config, or report by (1) extracting every piece of dynamic information — names, links, statistics, costs, identifiers, dates, thresholds — into configurable variables instead of hard-coding, and (2) enforcing that every factual assertion carries at least two independent citations. Triggers on "remove branding," "make this reusable," "transmute this," "parametrize," "no hard-coded values," "configurable," "needs citations," "verify these claims," or any request to convert a one-off artifact into a parameterized template.

2026-06-07
prompt-atom-formalization
その他コンピュータ職

Scan rough markdown, session exports, or pasted prose and isolate each core intent into a structured prompt atom — classified as law, value, directive, constraint, question, or branch-vector — then rewrite it into machine-readable YAML frontmatter per the RAW → CLEANED/FORMALIZED → ELEVATED doctrine. Triggers on "prompt atom extraction pass", "atomize this", "formalize these prompts", or converting loose operator text into registry-grade atoms.

2026-06-07
recursive-boil-down
ソフトウェア開発者

Decompose a system, repository, or architecture into four tiers — Macro (whole system), Bricks (components), Elements (conceptual primitives), Primitives (base operations) — reading target source plus its seed.yaml, then output a comparison table of the new system against existing substrates to expose reuse and overlap before anything new is built. Triggers on "boil down", "decompose into primitives", "recursive boil-down", or analyzing a new repo/architecture against what already exists.

2026-06-07
session-governance-audit
その他コンピュータ職

Parse a session transcript into a structured Session Governance Index — an annotated bibliography of every file modified and commit made, internal-energy accounting (tool uses, estimated tokens), shipped-vs-tasked atom tally, and classification of missing items as Gaps or Vacuums. Triggers on "visibility-schema-substrate-sweep", "session cascade audit", "session governance audit", or any request to summarize what a session actually produced versus what it was asked to produce.

2026-06-07
このリポジトリの収集済み skills 183 件中、上位 8 件を表示しています。
anndata
その他の生物科学者

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

2026-05-19
arboreto
その他の生物科学者

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

2026-05-19
biopython
ソフトウェア開発者

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

2026-05-19
bioservices
ソフトウェア開発者

Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython.

2026-05-19
cellxgene-census
ソフトウェア開発者

Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.

2026-05-19
deeptools
ソフトウェア開発者

NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.

2026-05-19
etetoolkit
ソフトウェア開発者

Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics.

2026-05-19
flowio
ソフトウェア開発者

Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing.

2026-05-19
このリポジトリの収集済み skills 145 件中、上位 8 件を表示しています。
mcp-builder
その他コンピュータ職

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

2026-07-19
slack-gif-creator
ソフトウェア開発者

Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".

2026-07-19
algorithmic-art
ソフトウェア開発者

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

2026-05-14
artifacts-builder
ウェブ開発者

Suite of tools for creating elaborate, multi-component Codex.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

2026-05-14
canvas-design
グラフィックデザイナー

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

2026-05-14
codex-project-manifest
その他コンピュータ職

Creates annotated bibliography-style manifests for Codex projects, tracking files, conversation threads, and relationships with unique IDs and annotations. Use when documenting project contents, creating file inventories, tracking conversation history, or building navigable knowledge maps.

2026-05-14
closeout
ソフトウェア開発者

Session-end ritual that walks back through plans authored and atoms touched in this session, assigning each a closure status (DONE-NNN, IRF-XXX-NNN, or `~/.Codex/plans/abandoned/`). Verifies git state. Produces CLOSEOUT_SUMMARY.md. Triggers on "/closeout", "close out the session", "end of session", "wrap up", "session close", or before any planned `git push`. Addresses the 90.4% plan-orphan rate documented in docs/evaluation/self-review-2026-05-05/stale-plans-and-orphan-commits.md.

2026-05-14
continuous-learning-agent
その他コンピュータ職

Self-improvement patterns for AI agents to learn from feedback, errors, and successful patterns across sessions

2026-05-14
このリポジトリの収集済み skills 34 件中、上位 8 件を表示しています。
creative-analysis
テクニカルライター

Route creative work (scripts, narratives, stories, films, games) to appropriate analysis protocols. Triggers on requests involving script analysis, narrative breakdown, story feedback, creative work evaluation, structural diagnosis, algorithm extraction, or any variation of "analyze this [creative work]". Selects protocol based on user intent: triage (P1), structural diagnosis (P2), craft revision (P3), scholarly analysis (P4), market assessment (P5), mechanism extraction (P6), or comprehensive analysis (P7). Default to P3 (Craft) for revision-oriented requests.

2026-02-16
protocol-comprehensive
テクニカルライター

Full analytical treatment protocol (P7) for major works requiring archival-quality documentation. Triggers on "full analysis", "comprehensive breakdown", "everything", "complete coverage", "teaching case study", "archival documentation". Produces all 8 core documents plus supplements. Activates all 9 analyst roles. Estimated time 8-12 hours per 100-page script. This is the complete script-analysis-dramaturgical skill activation.

2026-02-16
protocol-craft
テクニカルライター

Practical revision guidance protocol (P3) for working writers with structurally sound drafts needing deepening. DEFAULT protocol for revision requests. Triggers on "revision notes", "feedback", "how do I fix", "notes for rewrite", "polish pass", "dialogue notes", "character notes". Produces Coverage Report, Structural Analysis, Character Atlas, Diagnostic Report, and Revision Roadmap. Estimated time 4-5 hours per 100-page script.

2026-02-16
protocol-extraction
テクニカルライター

Mechanism identification and algorithm extraction protocol (P6) for studying how narrative techniques work. Triggers on "how does this technique work", "extract the mechanism", "algorithm extraction", "formalize the approach", "what's the pattern", "study this showrunner's method". Produces Structural Analysis (mechanism-focused), Theoretical Correspondence, and Mechanism Extraction Report. Designed to feed the narratological-algorithms workflow. Estimated time 4-6 hours per work.

2026-02-16
protocol-market
市場調査アナリスト・マーケティングスペシャリスト

Commercial viability assessment protocol (P5) for creative work. Triggers on "will this sell", "commercial potential", "market assessment", "audience", "budget", "castability", "production feasibility", "pitch deck", "packaging". Produces Coverage Report (market-focused), Market Positioning Analysis, Comparable Titles Analysis, and Production Feasibility Assessment. Uses PRODUCER as primary role. Estimated time 3-4 hours per 100-page script.

2026-02-16
protocol-scholarly
その他の高等教育教員

Academic-grade theoretical analysis protocol (P4) for scholarly output. Triggers on "academic analysis", "for a paper", "theoretical framework", "teaching material", "lecture prep", "peer review", "thesis chapter", "historical context". Produces Structural Analysis, Thematic Architecture, Theoretical Correspondence, and Diagnostic Report. Uses ACADEMIC, NARRATOLOGIST, ART_HIST as primary roles. Estimated time 6-8 hours per 100-page script.

2026-02-16
protocol-structural
テクニカルライター

Architecture diagnosis protocol (P2) for creative work requiring structural overhaul. Triggers on "structure", "architecture", "act breakdown", "what's broken structurally", "macro-level problems", "rewrite planning". Produces Coverage Report, Structural Analysis, and Diagnostic Report. Uses DRAMATURGIST and NARRATOLOGIST as primary roles. Estimated time 2-3 hours per 100-page script.

2026-02-16
protocol-triage
テクニカルライター

Rapid assessment protocol (P1) for creative work gatekeeping decisions. Triggers on "quick read", "worth pursuing", "should I read this", "pass or recommend", "first look", or high-volume evaluation contexts. Produces abbreviated coverage report with RECOMMEND/CONSIDER/PASS decision. Uses FIRST-READER and DRAMATURGIST roles only. Estimated time 30-60 minutes per 100-page script.

2026-02-16
このリポジトリの収集済み skills 9 件中、上位 8 件を表示しています。
ship
ソフトウェア開発者

Drive one change from implemented to LIVE-VERIFIED and merged — scoped gates, PR, required-checks merge, live-artifact proof, closeout predicates — with no status stalls in between. Use when asked to ship, land, or deliver a change end-to-end.

2026-07-24
decorum-voice-judge
テクニカルライター

Judge whether the public PROSE reads professionally — tone, brand-voice, clarity, credibility — and record a content-pinned verdict. Use when DECORVM (the professionalization keeper) queues a "prose changed — re-review voice" finding, or when asked to review/grade how a public README, bio, or positioning doc SOUNDS (not just whether it is spelled right). The deterministic half (spelling, staleness, narrative-accuracy) is scripts/decorum-keeper.py; this skill is its model-in-the-loop voice complement, the sibling of experience-judge.

2026-07-23
agy-conductor
その他コンピュータ職

Connect Antigravity (Agy) to Limen's symmetric peer-conductor protocol. Use when Agy must conduct, execute, review, split, observe, or harvest bounded Limen work through the authenticated conduct CLI or MCP surface.

2026-07-20
experience-judge
ウェブ・デジタルインターフェースデザイナー

Score the visual quality of the public surfaces the experience-audit organ captured — layout, typography, coherence, trust — and record verdicts. Use when asked to judge, review, or grade how the public sites/pages LOOK (not just whether they load), or to run the visual half of the experience audit. The mechanical half (reachable/fast/light/no-errors) is scripts/experience-audit.py; this skill is its human/model-in-the-loop visual complement.

2026-07-18
closeout
その他コンピュータ職

Drive a task to a true closeout — ZERO open or dangling items. Verify ground truth read-only across all owners, close every gap so each owner records its own residual work, reach an idempotent fixed point (re-run = no changes), commit all loose work, and produce a relay handoff. Use when asked to close out, finalize, wrap up, archive, or hand off.

2026-07-15
closeout
ソフトウェア開発者

Drive a task to a true closeout — ZERO open or dangling items. Verify ground truth read-only across all owners, close every gap so each owner records its own residual work, reach an idempotent fixed point (re-run = no changes), commit all loose work, and produce a relay handoff. Use when asked to close out, finalize, wrap up, archive, or hand off.

2026-07-10
10 件中 10 件のリポジトリを表示
すべてのリポジトリを表示しました