SKILLEMALL.ai
GitHub ↗ RU Sign in

BC icc-jeanne-sulzer

Research, drafting, and analysis involving the International Criminal Court (Rome Statute system). Enforces a verification-first methodology — every case-law, decision, filing, warrant, and statement citation is verified against an authoritative primary source (icc-cpi.int, legal-tools.org) in the current conversation before it appears in an output. Foundational texts (Rome Statute, Elements of Crimes, RPE, Regulations of the Court) may be cited from project knowledge when present. Use whenever the user is working with ICC case law, OTP statements, ASP documents, or ICC procedure.

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 9 files body ≈ 1 457 tokens Open the sourcegithub.com↗ analyzed 85 min ago

Research, drafting, and analysis involving the International Criminal Court (Rome Statute system).

As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

AnalyzerResearchtype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
B
92/100
safety, quality, tests
Safety 60%
98
Quality 40%
84
Run on models
none yet
Process rating
C
55/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Risky intent intent-offensive-security examples/example-verification.md:35
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file; quoted — discussed, not commanded)
      > Under Article 28(a) of the Rome Statute, a military commander incurs criminal responsibility for crimes committed by forces under his "effective command and control". The Trial Chamber in *Bemba* he
      fixturequoted
    • low Risky intent intent-offensive-security references/verification-workflow.md:84
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      > Under Article 28(a) of the Rome Statute, a military commander incurs criminal responsibility for crimes committed by forces under his effective command and control. The Trial Chamber in *Bemba* arti

    Files scanned: 9. 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 55/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 40Consistency. Frontmatter name (icc-jeanne-sulzer) differs from the folder (international-criminal-court-jeanne-sulzer)
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 85Steps. 24 steps, 1 vague phrases
    • 100Failures and branches. 1 branches, has a failure section
    • 100Execution cost. Instruction body is 1457 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
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 587: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 24 items
    • +4Reference files are cited in the instructions (4 of 4)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.