LIVE
US Military Avoids Close Call After AI-Generated Intelligence Hallucination18/09/26|Study finds gender bias in GPT models is not reduced but reshaped across generations17/09/26 · OpenAI|Architectural tweaks may break conventional scaling law exponents16/09/26|OpenAI publishes a framework for reporting model misalignment16/09/26 · OpenAI|NVIDIA's Vera Rubin NVL72 Debuts in MLPerf Inference v6.116/09/26 · NVIDIA|OpenAI expands ChatGPT advertising with Sponsored Agents16/09/26 · OpenAI|OpenAI moves into advertising with 'Sponsored Agents'16/09/26 · OpenAI|Google DeepMind Introduces Gemini 3.8 Live and Its Extended Thinking Variant15/09/26 · Google DeepMind|What's at stake in AI's trillion-dollar infrastructure bet15/09/26|A Flaw in Chain-of-Thought Safety Monitoring14/09/26|Stellar Colosseum: A Multi-Agent System for Long-Horizon Mathematical Research14/09/26|Apple Code Hints Siri Could Be Swapped for ChatGPT or Claude14/09/26 · Apple|US Military Avoids Close Call After AI-Generated Intelligence Hallucination18/09/26|Study finds gender bias in GPT models is not reduced but reshaped across generations17/09/26 · OpenAI|Architectural tweaks may break conventional scaling law exponents16/09/26|OpenAI publishes a framework for reporting model misalignment16/09/26 · OpenAI|NVIDIA's Vera Rubin NVL72 Debuts in MLPerf Inference v6.116/09/26 · NVIDIA|OpenAI expands ChatGPT advertising with Sponsored Agents16/09/26 · OpenAI|OpenAI moves into advertising with 'Sponsored Agents'16/09/26 · OpenAI|Google DeepMind Introduces Gemini 3.8 Live and Its Extended Thinking Variant15/09/26 · Google DeepMind|What's at stake in AI's trillion-dollar infrastructure bet15/09/26|A Flaw in Chain-of-Thought Safety Monitoring14/09/26|Stellar Colosseum: A Multi-Agent System for Long-Horizon Mathematical Research14/09/26|Apple Code Hints Siri Could Be Swapped for ChatGPT or Claude14/09/26 · Apple|
SkillNewofficial publisher

Compte-rendu de comité sécurité (skill nAIvigate)

Skill : A reusable method: instructions, procedures, sometimes scripts or templates · requires claude-code

Turns raw committee notes into decisions, dated actions with owners, open risks and deferred items.

Someone who missed the meeting reads it in three minutes and knows who does what by when.

Overall score
8.1 /10
Security: nothing to flag
Utility
7.0
Reliability
7.0
Security
No caveat on record
Ease
1 click · Beginner

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Security committee notes often end up as a verbatim nobody re-reads. This skill classifies each sentence of the notes as a decision, an action, an open risk or information, then produces a short minute: numbered decisions, action table with owner, due date and status, open risks with their treatment (covered by an action, accepted, deferred), deferred items, one-line information.

If the previous minute is provided, it carries its actions forward and gives their status as seen in the notes, including 'not discussed', a useful status in itself. It never writes what the committee should have decided: a visible gap goes into the writer's notes, not the decisions.

Built for security committees, ISMS steering committees, ISO 27001 management reviews and cold post-crisis debriefs. The minute is to be reviewed by the chair before circulation.

What it offers

  • ·Classifies each note as a decision, action, open risk or information.
  • ·Action table: owner, due date, status; what is missing stays marked 'to set' or 'unassigned'.
  • ·Carries forward the previous committee's actions with status, including 'not discussed'.
  • ·Consistency check: every open risk is covered, accepted or deferred, otherwise flagged.
  • ·Follows an in-house template if provided.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
claude, claude-code
Host
claude-code
Licence
MIT
FR interface
Yes

Security and data

Rating
Security: nothing to flag
Your data
Data stays local
Maintenance
Active

Links and repository checked on 19 September 2026 · added on 19 September 2026

How to install Compte-rendu de comité sécurité (skill nAIvigate)

1. Download https://naivigate.com/downloads/skills/compte-rendu-comite-securite.skill (direct link, no sign-up). 2. Claude.ai: open the file in a conversation, or Settings › Capabilities › Skills › Import. The skill triggers on its own when the request matches. 3. Claude Code: unzip the file and copy the folder into ~/.claude/skills/ (personal) or .claude/skills/ in the project (shared). 4. Other editors: SKILL.md is plain Markdown, paste it into the project instructions. 5. Before first use, read the skill's 'Data never to provide' section.

Official documentation

In the same category

Whole category Frame (methods, guardrails)