SKILLEMALL.ai
GitHub ↗ RU Sign in

BD context-compressor

Context Compressor — Real-time conversation context compression engine. Activates when user says "compress context", "压缩上下文", "上下文爆了", "context full", "上下文瘦身", "reduce context", or when context exceeds 70% threshold. This skill compresses the CURRENT conversation history into a clean, short prompt. NOT a memory manager — pure context compression tool. Core capabilities: - Compress current chat history (180k → 30k instantly) - Auto-trigger at 70% context threshold - Structured JSON output with compression metrics - Preserve system prompt, keep recent N messages intact - Summarize older messages with configurable intensity - No database, no dependencies, pure Python

ClawHub Agent Skills author: Gao.QiLin v1.1.0 MIT-0 8 files · 1 script body ≈ 756 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI and agentsInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
85
Quality 40%
96
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 3

    ✓ No critical or high findings

    Medium and low: 3
    • medium Dangerous commands cmd-shell-rc scripts/install.sh:11
      Writes to a shell startup file
      echo "[install] Adding ~/bin to PATH in ~/.bashrc..."
    • medium Dangerous commands cmd-shell-rc scripts/install.sh:12
      Writes to a shell startup file
      echo 'export PATH="$HOME/bin:$PATH"' >> "$HOME/.bashrc"
    • medium Dangerous commands cmd-shell-rc scripts/install.sh:20
      Writes to a shell startup file
      echo "[install] Run: source ~/.bashrc && hawk-compress --help"

    Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 49/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 40Consistency. Frontmatter name (context-compressor) differs from the folder (hawk-context)
    • 100Tools and files. No external tools needed
    • 100Steps. 10 steps
    • 100Execution cost. Instruction body is 756 tokens
    • 100Running it twice. No mutating operations
    • low 10 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 3 example trigger phrases
    • +3Description length 673: enough signal without eating the budget
    • +4Structure: 17 headings
    • +3Step-by-step instructions: 10 items
    • +4Has examples (8 code blocks)
    • +4Reference files are cited in the instructions (4 of 4)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.

    External checks

    ClawHub: suspicious
    This skill is a plausible context-compression helper, but it also stores conversation-derived history and changes shell startup files without clearly bounded controls.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026