Skip to main content
Run any Skill in Manus
with one click
emiliosheinz
GitHub creator profile

emiliosheinz

Repository-level view of 4 collected skills across 1 GitHub repositories.

skills collected
4
repositories
1
updated
2026-07-08
repository map

Where the skills live

Top repositories by collected skill count, with their share of this creator catalog and occupation spread.

repository explorer

Repositories and representative skills

forge
software-developers

Spec-driven development workflow that takes a change from problem to shipped, verified code in four phases: specify, design, plan, execute — plus a `fix` command to correct course mid-stream. Auto-sizes from one-line fixes to multi-repo refactors. Invoke with `/forge specify|design|plan|execute|fix`. TRIGGER when: the user asks to ship/build/implement a feature, write a PRD or spec or requirements, design architecture, write a technical design, break work into tasks or an implementation plan, run TDD or write acceptance criteria, or correct/adjust an in-flight change — a misstated requirement, a design or implementation detail that's wrong, or a bug found while testing. SKIP for: trivial one-off edits the user already has fully specified, pure code review, or questions about how forge itself works.

2026-07-08
create-adr
project-management-specialists

Creates Architecture Decision Records (ADRs) to document architectural choices and their rationale. Use when asked to create or write an ADR, document a decision, record why something was chosen, or capture an architectural decision.

2026-07-03
create-rfc
project-management-specialists

Creates structured Request for Comments (RFC) documents for proposing and deciding on significant changes. Use when asked to create or write an RFC, draft a proposal, align stakeholders, or propose a change before a decision.

2026-07-03
diagnose
software-quality-assurance-analysts-and-testers

Root-causes complex bugs through a structured loop and saves a verified fix proposal — it diagnoses, it never fixes. Builds a fast deterministic feedback loop, reproduces, then probes ranked falsifiable hypotheses with parallel subagents and confirms the cause adversarially before writing the report. Use when a bug, error, crash, exception, failing or flaky test, regression, or unexplained behavior needs root-causing — especially when it is intermittent, subtle, cross-system, or resisted a first fix.

2026-07-03
Showing 1 of 1 repositories
All repositories loaded