SKILLEMALL.ai
GitHub ↗ RU Sign in

CD stl-lebanon-jeanne-sulzer

Verification-first methodology for the Special Tribunal for Lebanon. Citations are verified against the STL legacy archive and legal-tools.org. Covers the Ayyash et al. case, the two contempt cases (STL-14-05 New TV/Al-Khayat and STL-14-06 Akhbar Beirut/Al-Amin), and the 2011 terrorism decision. Research aid, not legal advice. Part of the open-source "Skills for International Justice" library — methodology: github.com/jeannesulzer/international-criminal-tribunals-skills

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 10 files body ≈ 4 003 tokens Open the sourcegithub.com↗ analyzed 85 min ago

Verification-first methodology for the Special Tribunal for Lebanon.

As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerGitHubResearchtype 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
C
89/100
safety, quality, tests
Safety 60%
100
Quality 40%
72
Run on models
none yet
Process rating
D
45/100
Unfinished process
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

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 0

✓ No critical or high findings

Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note edit-residue the text marks something as outdated (lines 8, 12, 65): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 45/100

  • 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
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (stl-lebanon-jeanne-sulzer) differs from the folder (special-tribunal-for-lebanon-jeanne-sulzer)
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 70Execution cost. Instruction body is 4003 tokens
  • 100Steps. 71 steps
  • 100Running it twice. No mutating operations
  • low 13 top-level sections: this looks like several domains in one skill

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 474: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 71 items
  • +4Reference files are cited in the instructions (5 of 5)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.