Skip to main content
Manusで任意のスキルを実行
ワンクリックで
jscott3201
GitHub クリエイタープロフィール

jscott3201

4 件の GitHub リポジトリにある 45 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
45
リポジトリ
4
更新
2026-07-11
リポジトリエクスプローラー

リポジトリと代表的な skills

agent-bridge
ソフトウェア開発者

Multi-agent coordination via SeleneDB context bridge. Check active peers, read shared context, declare work intents, and avoid conflicts when multiple agents work simultaneously.

2026-04-10
commit-workflow
ソフトウェア開発者

Commit discipline with graph linking. MERGE GitCommit nodes and link to active milestones, findings, and decisions. Verify before committing, never push unless asked.

2026-04-10
notes
秘書・行政アシスタント(法律・医療・役員除く)

Background annotation discipline. All skills auto-annotate graph nodes with rationale, observations, TODOs, and bookmarks as they work. Captures context that feeds into graph-docs documentation generation.

2026-04-10
session-tracker
秘書・行政アシスタント(法律・医療・役員除く)

Track and recall context across sessions. Auto-captures rolling summaries as skills complete. Invoke to review session history, search past work, or see what happened recently.

2026-04-10
code-standards
ソフトウェア開発者

Language-specific standards plus graph-sourced conventions. Reads Convention nodes from SeleneDB, enforces project rules alongside built-in standards. Promotes recurring violations to new conventions.

2026-04-08
debate
マネジメントアナリスト

Structured multi-perspective debate for evaluating decisions. 3-phase methodology: independent generation, adversarial exchange, synthesis. Use when a decision has multiple valid approaches or high stakes.

2026-04-08
debug
ソフトウェア開発者

Systematic debugging: reproduce, hypothesize, isolate, verify. Includes git bisect for regressions, 5 Whys root cause, and hypothesis tracking. Use when encountering bugs, test failures, or unexpected behavior.

2026-04-08
deep-review
ソフトウェア品質保証アナリスト・テスター

Deep code review after completing a feature or implementation phase. Cross-references all changes against the codebase and fixes all findings. Use after finishing a phase, feature, or significant implementation chunk.

2026-04-08
このリポジトリの収集済み skills 26 件中、上位 8 件を表示しています。
helios-mtp-acceptance-analysis
ソフトウェア開発者

Diagnose Gemma 4 MTP acceptance and speculative decoding behavior in Helios using real-context prompts, trace records, and exactness gates.

2026-06-30
helios-native-mlx-ab-profiling
ソフトウェア開発者

Profile and optimize Helios native MLX/C++ execution paths with A/B evidence, memory gates, and feature-flagged experimental kernels.

2026-06-30
helios-real-workload-ab
ソフトウェア開発者

Build and run Helios real-context A/B benchmarks with deterministic workload manifests, correctness gates, and decision artifacts.

2026-06-30
gemma4d-16gb-mac-profiling
ソフトウェア開発者

Use for tiny16 MacBook profiling: memory pressure, context-length limits, TTFT/decode metrics, cache effectiveness, MTP acceptance, and release-gate benchmark reports.

2026-06-30
gemma4d-dynamic-adapters
ソフトウェア開発者

Use for dynamic LoRA/QLoRA adapter import, validation, loading, routing, adapter-aware KV cache keys, aLoRA planning, and adapter memory residency.

2026-06-30
gemma4d-kv-cache-offload
ソフトウェア開発者

Use for Gemma4D KV cache, prefix cache, SSD cold tier, cache manifests, cache-key correctness, quantized/compressed KV experiments, and restore parity.

2026-06-30
gemma4d-milestone-execution
ソフトウェア開発者

Use to execute one Gemma4D milestone end-to-end with scoped tasks, verification commands, evidence capture, and blocker reporting. Trigger on milestone implementation, Codex Goals, task planning, or release gates.

2026-06-30
gemma4d-model-correctness
ソフトウェア開発者

Use for Gemma 4 12B config, tokenizer, chat-template, prompt hashing, greedy parity, fixture creation, and reference comparison work.

2026-06-30
このリポジトリの収集済み skills 11 件中、上位 8 件を表示しています。
agent-messaging
その他コンピュータ職

Send, poll, wait for, and acknowledge durable addressed agent-to-agent messages in Aionforge Memory (message_send, message_poll, message_wait, message_ack) and subscribe to room resources. Use to hand a brief to another agent, page a teammate, wait for a reply, coordinate a multi-agent workflow, or drain an inbox — distinct from recall and work tracking.

2026-07-11
memory-bootstrap
その他コンピュータ職

One-time setup that lays a foundational Aionforge Memory substrate for a fresh project — resolve identity, seed conventions and architecture decisions as captures, stand up a work-item backlog skeleton, and verify recall. Use when a project's memory is empty or new, or when the user asks to set up, bootstrap, initialize, or seed project memory.

2026-07-11
memory-capture
その他コンピュータ職

Capture durable Aionforge Memory records for decisions, user preferences, project facts, release outcomes, validation results, handoffs, corrections, and reusable failure patterns. Use proactively during substantial work and whenever the user asks to remember or update memory.

2026-07-11
memory-loop
その他コンピュータ職

Use Aionforge Memory as the working substrate for a multi-step task. Trigger for implementation, debugging, review, release, planning, incidents, handoffs, or any session where prior context and durable follow-up matter.

2026-07-11
memory-maintenance
その他コンピュータ職

Inspect, consolidate, audit, forget, or restore Aionforge Memory. Use when the user asks about memory health, backlog, provenance, stale records, corrections, deletion, restoration, or why a memory was recalled.

2026-07-11
memory-recall
その他コンピュータ職

Search Aionforge Memory before planning, answering, coding, review, debugging, release, or continuation work. Use proactively whenever prior decisions, user preferences, project facts, failures, or handoffs could change the answer.

2026-07-11
work-tracking
その他コンピュータ職

Track tasks, blockers, TODOs, plans, and follow-ups as durable Aionforge Memory work items. Use proactively when a multi-step task, backlog, plan, or handoff appears, and whenever the user mentions tasks, status, or what is left to do. Work items are persistent and status-tracked, distinct from decaying memory episodes.

2026-07-11
4 件中 4 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