Agent Skills by rajnishkhatri
Showing 19 vetted skills indexed across 1 GitHub repositories.
agentsframework-eval-probe
Monitor and evaluate LLM-calls in software repositories with tiered L1, L2, L3 probes.
sdd-spec
Generate EARS specs, plans, and task lists from a direction.
sdd-converge
Classify gaps between built and specified requirements and spawn fix tasks.
governance-trace-audit
Audit AgentsFramework Langfuse traces against governance triangle compliance rules.
sdd-lifecycle
Orchestrate a 10-stage spec-driven development process with automated routing and stage ownership.
llm-eval-grounded-theory
Automate LLM evaluation pipelines from trace collection to continuous monitoring.
agentsframework-okf-curator
Automate OKF documentation curation and drift checking with Python scripts.
code-review
Automate Python code review and generate compliance reports.
playwright-agentic-e2e
Automate end-to-end testing of streaming chat applications with Playwright.
sdd-brainstorm
Expand problem statements into candidate directions validated against repository evidence.
gcp-live-smoke
Run live GCP/Cloud Run smoke tests on the eval-UI stack with Playwright.
deploy-gcp
Automate GCP Tier A deployments with OpenTofu policy enforcement and smoke tests.
memory-compaction
Compact Claude Code's MEMORY.md index to stay under the 12 KB limit.
agentsframework-playwright
Automate end-to-end frontend testing in AgentsFramework using Playwright and Cloud Run.
sdd-replan
Automate SDD Stage 5 replanning and sprint board adjustments.
agentsframework-open-coding
Manually code qualitative data from agent traces into a Langfuse dataset.
agentsframework-axial-coding
Automate axial coding of open-coded data into named failure categories.
sdd-implement
Execute SDD Stage 6 tasks using red/green TDD and EARS verification.
idea-to-design
Convert conversational ideas into design prompts for Claude's Design tool.