Vai al contenuto
TakoAPI
Torna alle skill

context-engineering

di leoyessi10-tech

Smart Home & IoT
2.4kDownload riportati da clawskills.sh
1Stelle
0Visualizzazioni
0 likeAccedi per mettere like a questa skill
—Non ancora valutato
La tua valutazione

Sintesi

This skill should be used when the user asks.

Descrizione

Cosa fa questa skill

Covers strategies for compressing agent conversation history when sessions exceed context window limits. Three production-ready approaches are compared: anchored iterative summarization, opaque compression, and regenerative full summaries. The core metric is tokens-per-task rather than tokens-per-request.

Optimizing for tokens-per-task rather than tokens-per-request avoids the hidden cost of re-fetching lost context, which naive compression strategies miss entirely.

Quando usarla

  • Preventing coding agents from forgetting modified files mid-session
  • Handling codebases larger than the model context window
  • Designing summarization pipelines for long-running agent workflows
  • Evaluating compression quality with probe-based testing
  • Tuning compression trigger thresholds for multi-phase tasks

Esempio di workflow

INPUT

User asks: compress the current 90,000-token debugging session before continuing

AGENT
  1. 1

    Identify the structured summary sections: Session Intent, Files Modified, Decisions Made, Current State, Next Steps

  2. 2

    Summarize only the newly-truncated span of conversation history into those sections

  3. 3

    Merge the new section content into the existing persistent summary rather than regenerating from scratch

  4. 4

    Verify artifact trail completeness by checking that all read and modified files are listed

  5. 5

    Run probe-based checks asking factual questions to confirm critical details were retained

OUTPUT

Compressed structured summary under 2,000 tokens, with full file tracking and decision history preserved, ready to continue the session

Installazione

clawhub install leoyessi10-tech/context-engineering

Esegui il comando CLI oppure incolla il prompt in Claude Code, Cursor, Codex o nell'agente di coding che usi.

Link