SKILLEMALL.ai
GitHub ↗ RU Sign in

FC context-memory-optimizer

v3.1 (ClawHub-safe, source-verified): OpenClaw context memory optimizer. Prevents context overflow, memory drift, and token waste in long agent sessions. Based on logic verified against Claude Code source and the claw-code open-source port (compact.rs). Use when: agent memory is confused, sessions are too long, context window is exhausted, or multi-agent coordination is unstable. 当 agent 记忆混乱、会话过长报错、上下文窗口不够用、多 agent 协作不稳定时使用。

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: Donnieclaw v1.0.5 MIT-0 4 files body ≈ 2 898 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerAI and agentstype 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
F
34/100
safety, quality, tests
Safety 60%
0
Quality 40%
85
Run on models
none yet
Process rating
C
50/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Obfuscation
If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

Concealment
If you install

The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.

For the author

Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
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 · 6

  • high Obfuscation obf-html-comment-instruction SKILL.md:148
    Hidden instruction inside an HTML comment
    <!-- SYSTEM PROMPT EFFECT: The text block below is a copy-paste snippet for  -->
  • high Obfuscation obf-html-comment-instruction SKILL.md:150
    Hidden instruction inside an HTML comment
    <!-- modify any system prompt programmatically.                               -->
  • high Concealment en-hide-from-user SKILL.md:263
    Instruction to hide actions from the user
    After reading, resume the task. Do not tell the user "I have restored X files."
  • high Obfuscation obf-html-comment-instruction SKILL.md:335
    Hidden instruction inside an HTML comment
    <!-- SYSTEM PROMPT EFFECT: same as Step 2 — operator pastes this layout  -->
  • high Obfuscation obf-html-comment-instruction SKILL.md:362
    Hidden instruction inside an HTML comment
    <!-- SYSTEM PROMPT EFFECT: operator pastes this into their agent config. -->
  • high Obfuscation obf-html-comment-instruction SKILL.md:363
    Hidden instruction inside an HTML comment
    <!-- No programmatic system prompt modification occurs.                  -->

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • note frontmatter-key unknown frontmatter key "persistent_paths"
  • note frontmatter-key unknown frontmatter key "persistent_changes"
  • note frontmatter-key unknown frontmatter key "system_prompt_effect"
  • note frontmatter-key unknown frontmatter key "requires"

Process rating: all ten parameters 50/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 100Steps. 20 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2898 tokens
  • 100Progress reporting. Reports progress

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

  • +5Description has no quoted example phrases that should trigger the skill
  • +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
  • +3Description length 429: enough signal without eating the budget
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 20 items
  • +4Has examples (10 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

External checks

ClawHub: suspicious
The available scan context suggests the skill may include guidance for avoiding static-analysis detection, but the underlying artifact was not available in the workspace for direct verification.
LLM: suspicious (low) · VirusTotal: · 29 May 2026