本文へ移動
cccskills
無料GitHub で公開

context-window-management

Manage LLM context budgets—prioritization, summarization, compaction, and what to load vs reference. Use for long sessions, large repos, or multi-doc tasks.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md2.3 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Context window management

Lifecycle

PhaseAction
BootstrapLoad spec, constraints, key paths only—not whole repo
During taskAppend deltas; replace full file reads with summaries after use
Before compactionWrite Session state block (objective, done, open, paths)
Session endDrop tool noise; keep decisions and verification evidence

Strategy order

  1. Do not load — use search/read targeted files only.
  2. Reference — pointers (paths, line ranges) instead of full paste.
  3. Summarize — compress completed work; keep decisions and open items.
  4. Drop — remove obsolete tool output and duplicated content.

What to keep in active context

  • Current objective and acceptance criteria
  • Constraints (env, versions, "do not touch")
  • Recent errors and fixes
  • Open questions

What to offload

  • Full file contents already summarized
  • Long command outputs (keep exit code + last N lines)
  • Exploratory branches that did not ship

Compaction pattern

## Session state (compacted)
Objective: ...
Done: ...
Open: ...
Key paths: ...
Do not repeat: [list already-established facts]

Multi-file work

  • Load one module at a time when possible.
  • Prefer ripgrep/semantic search over dumping trees.
  • For RAG: retrieve only top-k relevant chunks.

Anti-patterns

  • Pasting entire repos or logs into chat.
  • Re-explaining architecture every turn without delta.
  • Keeping failed attempts at full length after resolution.

Session setup (context engineering)

Before long tasks, establish a minimal working set:

  1. Objective block — one paragraph: goal, non-goals, done-when
  2. Constraint block — versions, env, files off-limits
  3. Reference map — paths to spec, ADR, or ticket; load on demand
  4. Tool policy — which tools/skills apply; avoid loading unused skill bodies

Refresh the objective block after major pivots; do not re-paste full history.

Pairing

Use with rag-systems for external knowledge; clarify-underspecified when scope grows mid-session; interview-me before loading large specs.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

"Implement and select ad bidding strategies from manual CPC to automated target-CPA and target-ROAS. Use this skill when the user needs to choose a bidding strategy, set up automated bidding, or optimize bid parameters — even if they say 'what bidding strategy should I use', 'target CPA setup', or 'smart bidding configuration'.".

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。

charlieviettq/awesome-agent-skill262026年7月20日 更新

"Optimize advertising budget allocation across campaigns using marginal returns analysis. Use this skill when the user needs to distribute budget across multiple campaigns, optimize spend pacing, or maximize overall ROAS under budget constraints — even if they say 'how to split my ad budget', 'campaign budget optimization', or 'diminishing returns on ad spend'.".

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。

charlieviettq/awesome-agent-skill262026年7月20日 更新

"Build CTR prediction models for estimating ad click-through rates from features. Use this skill when the user needs to predict click probability, build an ad ranking model, or evaluate ad creative performance — even if they say 'predict click rate', 'ad relevance scoring', or 'which ad will get more clicks'.".

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。

charlieviettq/awesome-agent-skill262026年7月20日 更新

"Implement Generalized Second Price auction for ad slot allocation and pricing. Use this skill when the user needs to understand search ad auctions, compute ad positions and costs-per-click, or analyze bidding dynamics — even if they say 'how does Google Ads auction work', 'ad rank calculation', or 'second price auction for ads'.".

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。

charlieviettq/awesome-agent-skill262026年7月20日 更新

"Implement VCG mechanism for incentive-compatible ad slot allocation with truthful bidding. Use this skill when the user needs to design a truthful auction mechanism, compute externality-based payments, or understand why platforms may prefer GSP over VCG — even if they say 'truthful auction design', 'VCG payments', or 'incentive-compatible mechanism'.".

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。

charlieviettq/awesome-agent-skill262026年7月20日 更新

"Explain blockchain fundamentals including distributed ledger architecture, consensus mechanisms, and block structure. Use this skill when the user needs to understand blockchain concepts, evaluate whether blockchain fits a use case, or design a blockchain-based solution — even if they say 'how does blockchain work', 'do I need blockchain', or 'distributed ledger'.".

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。

charlieviettq/awesome-agent-skill262026年7月20日 更新

charlieviettq のスキルをすべて見る

このスキルの問題を報告する