AGENT SKILLS · ÉQUIPEMENT DE MISSION / technobureau

technobureau · Agent Skills

5 skills with substantive source documentation and an official publisher or observed installation demand. Read each skill’s original documentation through its card.

technobureau
Communauté

ai-init

Bootstrap or refresh an evidence-grounded, stakeholder-readable documentation set for a new or existing repository. Use when asked to initialize AI context, create or refresh README.md or AGENTS.md, map repository structure, record architecture decisions, or establish baseline project documentation. Routes PRD, security, tests, design, and code-quality work to dedicated skills.

installations
1
GitHub Stars
0
Mis à jour
20 oct.
technobureau
Communauté

code-quality

Improve maintainability and secure engineering quality by removing verified dead code and applying modular, documented, testable practices, API compatibility rules, dependency hygiene, and observability standards. Use for explicit cleanup, refactoring, code review, or code-standard tasks; not as a side effect of documentation.

installations
1
GitHub Stars
0
Mis à jour
20 oct.
technobureau
Communauté

prd

Create or refine a concise, implementation-grounded Product Requirements Document with permanent G-, D-, FR-, and NFR-IDs, acceptance criteria, and enterprise traceability. Use when a repository PRD is requested, when requirements must be clarified or audited, or when ai-init is documenting a product repository.

installations
1
GitHub Stars
0
Mis à jour
20 oct.
technobureau
Communauté

security

Create or refine an evidence-based, modular enterprise security profile, including applicable threat modeling, supply-chain, cryptographic agility/PQC, FIPS, OpenSCAP/SCAP, CIS, NIST, ISO/IEC 27001, OWASP, and AI/LLM controls. Use for repository security analysis, secure-design review, audit preparation, or posture documentation; implement hardening only when explicitly requested.

installations
1
GitHub Stars
0
Mis à jour
20 oct.
technobureau
Communauté

tests

Add, improve, review, or document repository tests using the project's existing frameworks and verified commands, with enterprise coverage of functional, security, accessibility, performance, and resilience risks. Use only when test work, test strategy, test evidence, or docs/tests.md is requested; testing documentation is not part of ai-init's default output.

installations
1
GitHub Stars
0
Mis à jour
20 oct.