All authors
Claude Skills by nikhilw
github.com/nikhilw17 skills0 installs24 views
- 3p ReviewIndependent third-person code review. Use after ALL build phases are complete for a holistic review of the entire feature, or anytime the user wants a quality gate. Reviews as an independent Senior Architect who did NOT write the code and now owns it, so it must meet world-class standards.Votes: 0GitHub stars: 6
- Agentic WorkflowThe Structured Agentic Development Workflow — orchestrates brainstorm, write-plan, build-phase, 3p-review, handoff-summary, triage, test-driven-development, systematic-debugging, and verify-completion skills. Use when starting new work, switching between development phases, or when the user asks about the workflow. A dedicated build model uses the build-model workflow instead of this one.Votes: 0GitHub stars: 6
- BrainstormExplore a problem space before planning. Proposes architectural approaches with trade-offs, challenges the obvious solution, estimates impact, and produces a decision document. Code is the LAST thing we touch — this skill never writes code or plans.Votes: 0GitHub stars: 6
- Build ModelEntry point for a dedicated build model — a smaller/faster model run in a session whose only job is to build a plan, review it, and hand off. Orchestrates /build-phase across all phases, then /3p-review (loop until clean), then /handoff-summary, then pauses. Does NOT run /verify-completion. The main model uses agentic-workflow instead.Votes: 0GitHub stars: 6
- Build PhaseExecute one phase from a plan file using the TDD → Test → Self-Review loop. Use when a plan has been approved and it's time to build. Accepts a plan file path and phase number. Builds phase by phase and produces a build completion report. Review (/3p-review) and handoff (/handoff-summary) are driven by the orchestrating workflow — agentic-workflow for the main model, build-model for a dedicated build model — not by this skill.Votes: 0GitHub stars: 6
- Decision SummarySummarise what has been decided so far, in plain words, from two angles, what the user will get and how it works. Use when the user asks for a summary, a recap, or "what did we decide", during or after a brainstorm or a plan discussion. It is a capability, not a phase; it changes nothing and the discussion can carry on after it.Votes: 0GitHub stars: 6
- Existing MechanismsThe eight questions that must be answered about what a codebase already does before anything new is proposed, planned, or built, and the self-duplication inventory that catches a change duplicating its own code. Shared reference loaded by brainstorm, write-plan, build-phase and 3p-review. It is a reference, not a step of its own.Votes: 0GitHub stars: 6
- Github BacklogMaintain and manage features and bugs on GitHub. Creates, updates, lists, and links GitHub issues and project cards.Votes: 0GitHub stars: 6
- Handoff SummaryEmit the Build Handoff Summary artifact in its fixed format. Use at the end of a build, immediately after /3p-review passes — invoked by the build-model workflow (dedicated build model) or by the main model after all build phases. Produces the fixed handoff template the reviewing model consumes.Votes: 0GitHub stars: 6
- Knowledge GraphHow this workflow uses a graphify index: refreshing it, querying it, and the three limits on what a graph answer is worth, including why in typed code the count comes from the type checker, not the graph. Shared reference loaded by brainstorm and write-plan, and only when graphify is actually installed. It is a reference, not a step of its own.Votes: 0GitHub stars: 6
- Review LensesThe perspectives every review in this workflow looks through, one question each (impact, removal, logic, behaviour, business sense, proof, coherence), the checklist each lens walks, the table of which gate runs which lens at what depth, and the brief for handing a review to an outside model. Shared reference loaded by brainstorm, write-plan and 3p-review. It is a reference, not a step of its own.Votes: 0GitHub stars: 6
- Test ScopeHow wide a test run must be at each gate of the workflow, what a run may execute, and when a run already made can be cited instead of re-run. Shared definition loaded by build-phase, 3p-review, build-model, verify-completion and agentic-workflow. It is a reference, not a step of its own.Votes: 0GitHub stars: 6
- TriageRecommend what to work on next by reading the backlog (bugs.md, features.md, plans/) and considering what is already loaded in the current conversation context. Minimizes context thrash — prefers tasks aligned with current context. Recommends bugs when context is low, features when resources are plentiful.Votes: 0GitHub stars: 6
- Verify CompletionThe final gate before any claim of "done", "fixed", or "passing", and before any commit or PR. Runs three checks that nothing earlier in the workflow guarantees, a fresh full-suite result, a line-by-line tick-off of the plan's requirements, and a plan-drift audit from the decision document through the plan to the code. Evidence before assertions, always.Votes: 0GitHub stars: 6
- Workflow ConfigConfigure the Structured Agentic Development Workflow — set testing methodology (TDD/BDD), output style (caveman brevity), and persist preferences to agent memory.Votes: 0GitHub stars: 6
- Write PlanWrite a formal phased implementation plan to docs/plans/new/. Use after brainstorming is complete and a direction has been chosen. Creates a plan file that decouples the planning agent from the building agent.Votes: 0GitHub stars: 6
- Compact BriefWrite a one-line compact command for the user to run, and a resume brief to paste right after it, carrying what the rest of the workflow needs past a context compaction: where the work stands, the owner's rulings, what only ever lived in the conversation, and how the owner wants this model to work. Suggested at the workflow's two compact slots (plan approved, before the build; before verify-completion), and usable any time the user asks for a compact prompt.Votes: 0GitHub stars: 6