SKILLEMALL.ai
GitHub ↗ RU Sign in

BC context-compactor-cli

Condense a long agent session transcript into a compact handoff memo: decisions, tasks, risks, facts & links. Credential values are auto-redacted before output (best-effort - review memos before sharing; --strict drops whole suspect lines). EN/RU heuristics, zero dependencies. The CLI prints what it reads and where it writes. Use ONLY with the user's explicit consent: tell the user which transcript file will be read.

ClawHub Agent Skills v1.1.6 5 files body ≈ 664 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

IntegrationAI 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
87/100
safety, quality, tests
Safety 60%
87
Quality 40%
88
Run on models
none yet
Process rating
C
56/100
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

The same skill appears in 1 more place: ClawHub

What is at stake

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

Secrets in code 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 files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Secrets in code secret-private-key compactor.py:299
      Private key material (key header without key body; quoted — discussed, not commanded)
      "-----BEGIN PRIVATE KEY----- …
      header onlyquoted
    • medium Secrets in code secret-private-key compactor.py:327
      Private key material (key header without key body; quoted — discussed, not commanded)
      big_pem = "-----BEGIN PRIVATE KEY----- …\n"
      header onlyquoted
    • low Secrets in code secret-high-entropy-token compactor.py:300
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "MIIE…ial\n"
      quoted
    • low Secrets in code secret-high-entropy-token compactor.py:302
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "Ассистент: решили: BEGIN RSA PRIVATE KEY-…END RSA PRIVATE KEY----- для доступа по ssh.\n"
      quoted
    • low Secrets in code secret-high-entropy-token compactor.py:319
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      ok_jwt = "eyJh…CJ9" not in memo
      quoted

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "tools"

    Process rating: all ten parameters 56/100

    • 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
    • 30Running it twice. 4 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 10 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 664 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • high The skill tells the model to perform an irreversible action with no human approval

    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
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 420: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 10 items
    • +4Has examples (1 code blocks)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

    External checks

    ClawHub: suspicious
    This is a local transcript-compaction tool, but it needs review because one install path runs unreviewed npm code and some GitHub tokens can pass through its redaction.
    LLM: suspicious (high)