Vérifier qu'un changement marche vraiment avant de le livrer : contrôles rapides (lint, types, tests), tests E2E persistants (un par critère d'acceptation du PLAN), checklist déclenchée par le diff, passe exploratoire sur l'app qui tourne, puis rapport de preuves. Au premier lancement, installe la vérification du projet dans `docs/VERIFICATION.md`. Utilise sur /verifie, "vérifie", "teste tout", "est-ce que ça marche ?", "c'est prêt ?", avant de déclarer une phase terminée, ou quand /livre le déclenche. Pair naturel de /planifie (amont, critères) et /livre (aval).
- Stars
- 68
- Version
- v1
- Copies
- 0
Overview
Waxell's checks found 3 findings to review, highest severity high.
- Highest severity
- high
- Findings
- 3
- What ran
- Static analysis + deep scan
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked 2 days ago
Result
Review findings Waxell's checks found 3 findings to review, highest severity high.
Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work
Findings (3)
high · 2
- high
Tool Misuse: Chaining Abuse
SKILL.md:167 · skillspector:TM2
- high
Tells Claude to install unpinned packages (@playwright/test)
SKILL.md:49 · skill_risk:S2
medium · 1
- medium
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and pub
SKILL.md:49 · skillspector:RP1
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
One version so far: v1, seen 2026-11-19.
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More engineering skills and plugins
runcomfy-cliprime-skillsRun any model on RunComfy from the command line. The `runcomfy` CLI is one binary, one auth, hundreds of model endpoints, image… Review findingsEngineeringAI & agents62
huawei-cloud-cloudrobo-data-pipelinehuaweicloudGuide users to create or revise custom CloudRobo pipelines for sim/teleop VLA model training data, generate validated pipeline.yaml drafts… High riskEngineeringData & analytics59
huawei-cloud-cloudrobo-trainhuaweicloudManage CloudRobo model training tasks and simulation reinforcement learning (SimRL) tasks, create pretrain (TRAIN_FROM_SCRATCH) and… High riskEngineeringProductivity59
huawei-cloud-maas-model-guidancehuaweicloudHuawei Cloud MaaS (Model as a Service) model invocation guidance skill. Provides comprehensive guidance for customers to invoke AI models… High riskEngineeringImages, video & audio59