SKILLEMALL.ai
GitHub ↗ RU Sign in

CF normalisation-juridique-fr-christophe-quezel-ambrunaz

La compétence Normalisation juridique FR nettoie un document Word rédigé en français juridique. Elle distingue deux régimes : les corrections déterministes (apostrophes courbes, guillemets français, espaces insécables, insécables des références — art. 1240, n° 21-12.345, 50 % —, ordinaux 1ère → 1re, ligatures œ, la loi dispose et non stipule, anglicismes-calques), appliquées directement ; et les réécritures de jugement (virgule avant « et », ternaires creux, formules emphatiques, harmonisations), posées en révisions Word soumises à votre acceptation. Chaque changement est consigné et restitué en tableau récapitulatif : on revient en arrière mot à mot — « défais 3, 7-10 ». La normalisation des citations reste purement formelle. Fonctionne en Cowork ou sur fichier Word.

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 11 files · 2 scripts body ≈ 2 395 tokens Open the sourcegithub.com↗ analyzed 76 min ago

La compétence Normalisation juridique FR nettoie un document Word rédigé en français juridique.

As a process F 31/100 · No process to follow — References files that are not bundled: scripts/office/unpack.py, scripts/office/pack.py, scripts/comment.py

ProcedureTableauWordResearchtype 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
87/100
safety, quality, tests
Safety 60%
100
Quality 40%
67
Run on models
none yet
Process rating
F
31/100
No process to follow
References files that are not bundled: scripts/office/unpack.py, scripts/office/pack.py, scripts/comment.py
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
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.
  2. The text references files that are not there: add them or drop the references.
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: 11. 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")
  • warning missing-ref reference to a missing file: scripts/office/unpack.py
  • warning missing-ref reference to a missing file: scripts/office/pack.py
  • warning missing-ref reference to a missing file: scripts/comment.py
  • warning missing-ref reference to a missing file: scripts/accept_changes.py

Process rating: all ten parameters 31/100

Will not run. References files that are not bundled: scripts/office/unpack.py, scripts/office/pack.py, scripts/comment.py
  • 0Tools and files. 4 referenced file(s) missing: scripts/office/unpack.py, scripts/office/pack.py, scripts/comment.py
  • 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
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (normalisation-juridique-fr-christophe-quezel-ambrunaz) differs from the folder (normalisation-juridique-christophe-quezel-ambrunaz)
  • 100Steps. 23 steps
  • 100Execution cost. Instruction body is 2395 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
  • +1No license
  • +2Single-language instructions
  • +3Description length 778: enough signal without eating the budget
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 23 items
  • +4Has examples (5 code blocks)
  • +4Reference files are cited in the instructions (7 of 7)
  • +3All 2 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.