SKILLEMALL.ai
GitHub ↗ RU Sign in

CC prompt-compressor

当用户说『提示词太长/token烧太快』『上下文塞不下了』『把这段压缩一下还别丢重点』『长文档怎么塞进窗口』，或要压低 agent 每轮上下文成本时使用。基于「信息密度」裁剪：保留关键词密集/位置靠前的句子，删冗余/客套/复述，给出可运行脚本（提示压缩器，按密度+位置打分删句）。与 context-engineering 互补：context 管『放什么』，compressor 管『怎么压短』。理论根基：LGD 三律之收敛（删除冗余，单一有效信息）。触发词：提示压缩、prompt压缩、上下文压缩、压缩token、长文本精简、context压缩、省token、摘要进窗口、prompt shorten。

ClawHub Hermes author: zhaoxinghua09-cell v1.0.3 MIT-0 7 files · 1 script body ≈ 764 tokens Open the sourceclawhub.ai↗ analyzed 14 d ago

当用户说『提示词太长/token烧太快』『上下文塞不下了』『把这段压缩一下还别丢重点』『长文档怎么塞进窗口』，或要压低 agent 每轮上下文成本时使用。基于「信息密度」裁剪：保留关键词密集/位置靠前的句子，删冗余/客套/复述，给出可运行脚本（提示压缩器，按密度+位置打分删句）。与…

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
C
84/100
safety, quality, tests
Safety 60%
95
Quality 40%
67
Run on models
none yet
Process rating
C
53/100
Has gaps
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.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Read Glob Grep Bash Write WebFetch

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 303 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning description-no-when neither description nor a "## When to Use" section says when to use the skill
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "display_name"
  • note frontmatter-key unknown frontmatter key "displayName"
  • note frontmatter-key unknown frontmatter key "title"
  • note frontmatter-key unknown frontmatter key "license_scope"
  • note frontmatter-key unknown frontmatter key "display_name_en"
  • note frontmatter-key unknown frontmatter key "summary"
  • note frontmatter-key unknown frontmatter key "agent_created"
  • note frontmatter-key unknown frontmatter key "copyright"
  • note frontmatter-key unknown frontmatter key "read_when"
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 53/100

  • 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
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 12 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 764 tokens
  • 100Running it twice. No mutating operations

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
  • +2Single-language instructions
  • +3Description length 303: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 12 items
  • +4Has examples (2 code blocks)
  • +3All 1 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.

External checks

ClawHub: clean
This is a disclosed local prompt-compression skill with a small Python script and no evidence of hidden execution, credential access, persistence, or data exfiltration.
LLM: benign (high) · VirusTotal: · 28 Sept 2026