SKILLEMALL.ai
GitHub ↗ RU Sign in

AC paper-contribution-helper

Build and use a modular paper contribution helper from target papers, research fields, years, and paper sources. Use when Codex needs to help researchers package a paper's contribution, diagnose novelty risk, prepare reviewer defenses, or build a portable self-contained helper from reference papers.

ClawHub Agent Skills author: c-narcissus v1.0.2 MIT-0 80 files body ≈ 2 158 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 63/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorSoftware developmenttype 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
A
90/100
safety, quality, tests
Safety 60%
93
Quality 40%
86
Run on models
none yet
Process rating
C
63/100
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

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

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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 Exfiltration intent-browser-credential-store references/base_delta/workflow_knowledge_base_build.md:62
      Accesses a browser credential / cookie store (documentation of a security skill)
      This step writes anonymous reusable knowledge under `.delta-contribution-reframer/references/` and updates project-local state so future skill use in this project does not depend on absolute project p
      security skill
    • low Concealment en-hide-from-user assets/domain-skill-template/SKILL.template.md:70
      Instruction to hide actions from the user ("do not tell the user <a claim>" — honesty guidance, not concealment; documentation of a security skill)
      Do not tell the user that a project-internal corpus cannot be analyzed merely because API/acpx/local-command automation is missing. Continue locally or name a concrete non-backend blocker, such as unr
      honesty claimsecurity skill
    • low Concealment en-hide-from-user SKILL.md:86
      Instruction to hide actions from the user ("do not tell the user <a claim>" — honesty guidance, not concealment; documentation of a security skill)
      - Never tell the user that a project-internal corpus cannot be analyzed merely because API/acpx/local-command automation is missing. Continue locally or name a concrete non-backend blocker, such as un
      honesty claimsecurity skill

    Files scanned: 80. 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 63/100

    • 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
    • 100Tools and files. No external tools needed
    • 100Steps. 18 steps
    • 100Failures and branches. 3 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2158 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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
    • -33 of 5 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +3Description length 300: enough signal without eating the budget
    • +4Structure: 7 headings
    • +3Step-by-step instructions: 18 items
    • +4Has examples (4 code blocks)
    • +4Reference files are cited in the instructions (11 of 13)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.

    External checks

    ClawHub: suspicious
    This paper-analysis skill is mostly coherent, but it includes optional paths that can run user-configured local commands and pass sensitive paper content to external or local LLM backends.
    LLM: suspicious (high) · 28 May 2026