Loading...
Loading...
Found 10 Skills
Use when compressing agent context, implementing conversation summarization, reducing token usage in long sessions, or asking about "context compression", "conversation history", "token optimization", "context limits", "summarization strategies"
Use when conversation context is too long, hitting token limits, or responses are degrading. Compresses history while preserving critical information using anchored summarization and probe-based validation.
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
Design and evaluate compression strategies for long-running sessions
Search-aware context compression workflow for agent-studio. Use pnpm hybrid search + token-saver compression, then persist distilled learnings via MemoryRecord.
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress <filepath> or "compress memory file"
Use this when the user explicitly requests to "write/polish NSFC grant abstract", "generate Chinese and English abstracts", or "translate Chinese abstract to English abstract". Output both Chinese and English versions: The English version must be a faithful translation of the Chinese version (no additional information, no omission of key constraints). The default limit for Chinese abstract is ≤400 characters (including punctuation), and ≤4000 characters for English abstract (including punctuation); the final limit shall prevail as specified in `skills/nsfc-abstract/config.yaml:limits`. Also output **title suggestions**: By default, provide 1 recommended title + 5 candidate titles with justifications (the quantity shall follow `config.yaml:title.title_candidates_default`). Output method: Write the results to `NSFC-ABSTRACTS.md` in the **working directory** (the file name shall follow `config.yaml:output.filename`), which includes in order `# Title Suggestions`, Chinese abstract, English abstract, and length self-check. ⚠️ Not applicable in the following cases: - The user only wants to translate a general text unrelated to grant proposals (direct translation is required instead) - The user only wants to write the main body of project justification/research content/research foundation (use the corresponding NSFC series skill instead)
Context compression and summarization methodology. Techniques for reducing token usage while preserving decision-critical information.
[Tooling & Meta] Compress conversation context to optimize tokens
Compress long conversation histories, large code files, research results, and documents by 70% without losing critical information. Triggers when context window fills up, when summarizing previous steps in multi-step tasks, before loading large files into context, or on "summarize", "compress", "reduce context", "save tokens".