SKILLEMALL.ai
GitHub ↗ RU Sign in

BC legal-abduction

Organize document evidence into auditable competing hypotheses, source-linked observations, an assessment matrix and document-linked discriminating tests. Use for bounded explanatory questions, documents that could resolve uncertainty, rejection history, source provenance, gaps and updates, including a withdrawn or corrected fact and which explanations and earlier judgments it puts back under review; not findings of guilt or predictions about people. Evaluation preview requiring human review.

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 80 files · 34 scripts body ≈ 2 648 tokens Open the sourcegithub.com↗ analyzed 85 min ago

Organize document evidence into auditable competing hypotheses, source-linked observations, an assessment matrix and document-linked discriminating tests.

As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

AnalyzerData and analyticstype 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
93/100
safety, quality, tests
Safety 60%
99
Quality 40%
84
Run on models
none yet
Process rating
C
50/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Inputs and preconditions w 11
30
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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • low Secrets in code secret-high-entropy-token legal_abduction/review.py:501
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      add("pace…tem", "block_until_rereview" if ex else "warn_possible_superficial_review",
      quoted

    Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note edit-residue the text marks something as outdated (lines 75): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 50/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 30Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 7 mutating operations with no state check
    • 40Consistency. Frontmatter name (legal-abduction) differs from the folder (legal-abduction-grzegorz-skuza)
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 13 steps
    • 100Execution cost. Instruction body is 2648 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
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 497: enough signal without eating the budget
    • +4Structure: 4 headings
    • +3Step-by-step instructions: 13 items
    • +4Reference files are cited in the instructions (7 of 9)

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