fabioc-aloha/Alex_Skill_Mall - Page 8

critical-thinking

Challenge what you think is right — alternative hypotheses, missing data, evidence quality, bias detection, falsifiability, and adversarial review

Langue du texte source : anglais

debugging-patterns

Systematic problem-solving and error analysis.

Langue du texte source : anglais

dialog-engineering

CSAR Loop and structured conversation patterns for effective AI dialog -- Clarify, Summarize, Act, Reflect

Langue du texte source : anglais

hypothesis-driven-debugging

Investigate build failures, test errors, runtime crashes, or unexpected behavior through systematic minimal reproduction, multi-hypothesis testing, and evidence-based verification. Use when asked to "debug", "investigate a failure", "find root cause",…

Langue du texte source : anglais

knowledge-synthesis

Cross-project pattern recognition — abstract, generalize, connect, store at the highest true level

Langue du texte source : anglais

problem-framing-audit

Step-back protocol — restate, generalise, specialise, invert, ask why, pre-mortem, check stakeholders, and audit framings before solving

Langue du texte source : anglais

root-cause-analysis

Find the true source, not symptoms — systematic debugging from observation to permanent fix

Langue du texte source : anglais

rubber-duck-debugging

Be a thinking partner. The answer often emerges when explaining the problem.

Langue du texte source : anglais

socratic-questioning

Help users discover answers, don't just deliver them.

Langue du texte source : anglais

allowlist-over-blocklist

Validate input against an allowlist of permitted values — reject everything else

Langue du texte source : anglais

api-security-hardening

API security hardening — rate limiting, JWT validation, CORS, input validation (4-layer defense)

Langue du texte source : anglais

assist-sg-update

Generate assisted PRs to correct Security Group ownership for first-party apps flagged by S360 tenant-isolation policy (SFI-TI3.2.2)

Langue du texte source : anglais

build-fix

Fix compile-time and build errors introduced by prior agent changes

Langue du texte source : anglais

create-associate-nsg

Creates a new Network Security Group and associates it with the specified subnets and/or NICs of a Virtual Network.

Langue du texte source : anglais

distribution-security

Defense-in-depth, PII protection, secrets scanning, and secure packaging for distributed software

Langue du texte source : anglais

error-message-sanitization

Raw error messages leak internal information to users:

Langue du texte source : anglais

fetch-violations

Query S360 Kusto for SFI-TI3.2.2 tenant isolation violations, classify by ViolationTitle, flag autofix-eligible items for downstream remediation

Langue du texte source : anglais

generate-report

Generate an interactive, self-contained HTML dashboard displaying SFI-TI3.2.2 tenant isolation violations for a service, org, or alias -- includes filtering, sorting, severity coding, TSG links, S360 deep links.

Langue du texte source : anglais

guide-advanced-remediation

Complex multi-step remediation scenarios for S360 Tenant Isolation violations that require code changes, Federated Identity Credential (FIC) setup, and bilateral coordination between service teams.

Langue du texte source : anglais

guide-cert-rehoming

End-to-end process of rehoming (moving or reissuing) certificates so every production Entra app credential lives in the same tenant and cloud as the app itself.

Langue du texte source : anglais

input

Extract and resolve required CodeQL alert metadata from user input before remediation

Langue du texte source : anglais

lookup-nsg-for-vnet

Checks every subnet in a Virtual Network for an associated Network Security Group, and also inspects each NIC attached to those subnets for NIC-level NSG coverage.

Langue du texte source : anglais

lookup-nsg

Finds the Network Interface Card (NIC) and associated Network Security Group (NSG) for a VM given its public IP address.

Langue du texte source : anglais

markdown-sanitization-chain

Markdown sanitization order matters — marked.js then DOMPurify then Mermaid to prevent XSS

Langue du texte source : anglais

nnf-cve-cleanup

Cleans up NNF deployments impacted by vulnerable or outdated container images using guided execution.

Langue du texte source : anglais

output

Produce the final CodeQL fix result table and choose the correct exit code and retry behavior

Langue du texte source : anglais

path-traversal-prevention

When copying files or serving content, user-controlled paths can escape the intended directory:

Langue du texte source : anglais

pii-privacy-regulations

Handling personally identifiable information under European and Australian privacy regulations.

Langue du texte source : anglais

privacy-responsible-ai

Privacy by design, data protection, and responsible AI principles.

Langue du texte source : anglais

remediate-nsg

Applies M365NetIsoNsg compliance rules to an existing Azure NSG and outputs the ARM template for Safe Deployment.

Langue du texte source : anglais

remediate-pfx-certificates

Skill helps user to remove checked-in certificates from source code in case of exposed secrets

Langue du texte source : anglais

revoke-and-rotate-certificate

Skill helps user to revoke and rotate certificate in case of exposed secrets

Langue du texte source : anglais

secrets-management

Secure token storage, VS Code SecretStorage API, credential management, environment variable migration

Langue du texte source : anglais

security-review

Defend before attackers find the gaps - OWASP, STRIDE, and Microsoft SFI

Langue du texte source : anglais

security-threat-modeler

Analyze codebase architecture to generate a STRIDE-based threat model with data flow diagrams, trust boundaries, prioritized threats, and mitigations. Compatible with Microsoft Threat Modeling Tool concepts. Use when asked to "threat model", "security…

Langue du texte source : anglais

shell-injection-prevention

Use execFileSync with args array instead of execSync with string concatenation to prevent shell injection

Langue du texte source : anglais

symfix

Classify and remediate CodeQL alerts with the SymFix workflow using staged changelog updates

Langue du texte source : anglais

threat-surface-analysis

Discover a codebase's threat surface through systematic investigation — map ecosystem groups, dependency graphs, service connections, authentication mechanisms, and trust boundaries. Use when performing threat modeling, security review, or architectural…

Langue du texte source : anglais

violation-triager

Orchestrate end-to-end SFI-TI3.2.2 workflow — fetch violations, classify, dispatch to remediation skills, generate report

Langue du texte source : anglais

coherence-audit

Detect coherence violations between Alex_ACT_Edition (brain) and Alex_Skill_Mall (marketplace) — broken references, tag mismatches, deprecated install snippets

Langue du texte source : anglais