SKILLEMALL.ai
GitHub ↗ RU Sign in

CD gouvernance-emetteurs-cotes

Index analytiques sourcés du corpus réglementaire et doctrinal sur la gouvernance des émetteurs cotés français (rapports AMF et HCGE 2020-2025, guide d'application HCGE, rapport sénatorial Rietmann/Gay, Code AFEP-MEDEF, sources légales et européennes). À utiliser pour : (1) retrouver une position, une statistique ou une citation exacte avec sa source et sa page ; (2) analyser l'évolution longitudinale des positions AMF/HCGE/ESMA sur un thème ; (3) appliquer la grille d'analyse en 13 blocs (A-M) à un émetteur. Déclencher pour toute question sur la gouvernance d'une société cotée française : conseil d'administration, indépendance des administrateurs, comités, rémunération des dirigeants, say on pay, say on climate, assemblée générale, droits des actionnaires, plans de succession, mixité, RSE/CSRD, comply-or-explain, name and shame AMF, soft law AFEP-MEDEF, recommandations AMF, positions HCGE.

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 44 files · 11 scripts body ≈ 20 396 tokens Open the sourcegithub.com↗ analyzed 71 min ago

Index analytiques sourcés du corpus réglementaire et doctrinal sur la gouvernance des émetteurs cotés français (rapports AMF et HCGE 2020-2025, guide…

As a process D 36/100 · Unfinished process — weak spots: when it triggers, inputs and preconditions, failures and branches

AnalyzerResearchSoftware developmenttype 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
83/100
safety, quality, tests
Safety 60%
98
Quality 40%
60
Run on models
none yet
Process rating
D
36/100
Unfinished process
Inputs and preconditions w 11
0
Failures and branches w 10
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.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 Secrets in code secret-high-entropy-token INDEX_MAITRE.md:108
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **Say on climate / durabilité / CSRD** → AMF (F) + HCGE (J) + `inde…024`, `inde…025`, `inde…025`.
    quoted
  • low Secrets in code secret-high-entropy-token INDEX_MAITRE.md:109
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **Assemblée générale / droits des actionnaires** → AMF (F) + `references/droits-actionnaires-cotees.md` + `inde…024`.
    quoted

Files scanned: 44. 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 body-long SKILL.md body ≈ 20396 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 36/100

  • 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
  • 10Execution cost. Instruction body is 20396 tokens: crowds the task out of the window
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 40Consistency. Frontmatter name (gouvernance-emetteurs-cotes) differs from the folder (gouvernance-societes-cotees-gillan-saleh)
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 60Steps. 184 steps, 7 vague phrases
  • 60Result and completion. Output format stated, no completion criterion
  • low 11 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)
  • +3Description length 903: 120–800 characters recommended
  • +4No input/output examples
  • -34 of 11 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +4Structure: 68 headings
  • +3Step-by-step instructions: 184 items
  • +3Output format is stated explicitly
  • +4Reference files are cited in the instructions (1 of 2)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.