s-kostyaev
- 11 skills
- 0 followers
- 6 hours ago last updated
- ▌
- ▌
- ▌ Mq · s-kostyaevQuery markdown files efficiently with mq CLI. Use when exploring documentation structure, extracting specific sections, or reducing token usage when reading .md files.
- ▌
- ▌ Code Review · s-kostyaev bundleReview code changes with a focused multi-agent workflow. Use when auditing a diff, branch, pull request, patch, commit range, or local worktree for bugs, regressions, missing tests, security issues, API breakage, maintainability risks, or review readiness.
- ▌ Skill Creator · s-kostyaev bundleCreate or update Ellama Agent Skills. Use when designing new skills, porting skills from other agent systems, improving SKILL.md instructions, adding bundled resources, validating metadata, or adapting skills for small/local models.
- ▌ Ddgr Web Search · s-kostyaevRun DuckDuckGo web searches from the terminal using `ddgr` with JSON output. Use when the task calls for lightweight web search, quick result triage, or filtering by region/time/site.
- ▌ Web Browse Context · s-kostyaev bundleEfficiently capture web pages as clean markdown and query them with `mq` to avoid loading full content into context. Use when browsing web pages, extracting specific sections, or summarizing sources with minimal context usage.
- ▌ Agent Harness Engineering · s-kostyaev bundleBuild, audit, or improve agentic coding/research systems and their harnesses. Use when designing agent workflows, small-model scaffolds, tool schemas, progressive-disclosure context, repository knowledge maps, guardrails, validation loops, subagents, evals, recovery mechanisms, or autonomous-agent safety policies.
- ▌ Oq · s-kostyaevQuery Org-mode files and directories with oq using deterministic, structure-first, low-token workflows. Use when an agent needs to inspect .org content, locate sections/tasks/metadata, extract only scoped text.
- ▌ Deep Research · s-kostyaev bundleConduct durable, source-grounded research with Sandwalk, including planning, parallel claims, immutable web or local-document snapshots, exact excerpts, reviewed findings, citation-safe drafting, recovery, and finalization. Use for research tasks that need auditable provenance, interruption recovery, independent evidence review, or a reviewed report rather than an informal summary.