← all publishers

alphasafal

@alphasafal source repo

Report this profile Claim this profile

• 8 skills
• 0 followers
• 5 hours ago last updated

1. ▌
   Production Code Review · alphasafal bundle

   Performs structured, senior-level review of a code change (diff or PR) across correctness, security, reliability, error handling, concurrency, performance, data integrity, API contracts, maintainability, observability, tests, and backward compatibility. Ranks findings P0-P3 and separates FACT from LIKELY RISK from OPTIONAL IMPROVEMENT. Use when reviewing a pull request, diff, or "is this change safe to merge" before it ships. Do not use for reviewing an entire pre-existing codebase with no change in question (use repo-architect for that), or for pure style/formatting passes with no maintainability impact.
   0 installs
2. ▌
   System Design Reviewer · alphasafal bundle

   Reviews a proposed system or service architecture before implementation begins — requirements, API design, data model, storage, consistency, caching, queues/events, scaling, failure modes, security, observability, deployment, and cost. Use when evaluating a design doc, RFC, or proposed architecture for a new system/service, or when asked "does this design hold up," "what could go wrong with this architecture," or "review this system design." Do not use once implementation is already underway and the question is about the code itself (use production-code-review), or for reviewing an existing, already-built system's structure (use repo-architect).
   0 installs
3. ▌
   Data Scientist · alphasafal bundle

   Runs an end-to-end structured tabular data science workflow: problem framing, schema/leakage/missingness checks, EDA, baseline before modeling, feature engineering, model comparison against the baseline, and error/slice analysis. Use when asked to analyze a dataset, build a predictive model, evaluate a model's performance, or investigate a data quality issue in tabular data. Do not use for pure data engineering/ETL with no analysis or modeling question, for unstructured data (images/audio/free text at scale) without a tabular framing, or when the task is answerable by a single summary statistic with no need for the full workflow — say so and just answer it.
   0 installs
4. ▌
   Repo Architect · alphasafal bundle

   Builds a structured map of an unfamiliar repository — entry points, modules, dependencies, data flow, persistence, external integrations, and architectural risks — before any code is changed. Use when starting work in a codebase you haven't worked in before, onboarding to a new repo, preparing to plan a non-trivial change, or when asked to "understand this codebase" or "explain the architecture." Do not use for a codebase you already understand well, for a single well-scoped file edit, or as a substitute for actually implementing a change (it produces a map, not a fix).
   0 installs
5. ▌
   Product Manager · alphasafal bundle

   Turns an ambiguous product idea or feature request into a validated, right-sized product plan: problem definition, target user, jobs-to-be-done, assumptions and risk ranking, a minimal MVP scope, user stories, success metrics, and a PRD. Use when asked to scope a new feature/product idea, write a PRD, define an MVP, or turn a vague request ("we should have X") into something buildable. Do not use once a feature is already fully scoped and specified and the task is just implementation (use feature-to-production), or for a purely technical decision with no product/ user dimension (use research-to-decision).
   0 installs
6. ▌
   Research To Decision · alphasafal bundle

   Turns research into an auditable technical or product decision: defines the decision and constraints, gathers evidence with sources, separates evidence from assumption, compares alternatives against explicit criteria, and produces an ADR. Use when choosing between technologies/approaches ("Kafka vs SQS", "build vs buy"), documenting the reasoning behind a decision already made, or when asked to "research this and recommend one." Do not use for implementing the chosen option (that's a separate skill), or for open-ended research with no decision to make at the end.
   0 installs
7. ▌
   Feature To Production · alphasafal bundle

   Guides a software feature from a clarified requirement through implementation to production readiness: acceptance criteria, repository understanding, smallest-viable design, tests, implementation, verification, review, security/performance checks, documentation, and a deployment/ rollback plan. Use when asked to build/ship a feature end to end, not just write a snippet. Do not use for a one-line fix (use debugging-investigator if it's a bug) or when the requirement itself is still vague (use product-manager first to scope it).
   0 installs
8. ▌
   Debugging Investigator · alphasafal bundle

   Investigates software failures using evidence-driven debugging: reproduction, hypothesis generation and ranking, targeted hypothesis testing, root-cause identification, minimal fixes, and regression verification. Use when diagnosing bugs, crashes, failing tests, intermittent errors, unexpected behavior, production incidents, or performance regressions — especially when the cause is not already obvious. Do not use for writing new features, general code review with no reported failure, or answering conceptual questions about how something works (e.g. "what is a stack trace" or "explain this error type").
   0 installs