Files
muratcankoylan__agent-skill…/.plugin/plugin.json
Cursor Agent 521012828f Wire long-horizon-prompting into corpus, manifests, and docs for v2.5.0
3 mechanisms, 8 claims, 2 activation cases, 3 router prompts (p054-p056),
corpus index entry, accepted-ledger entries pending human PR review;
manifests bumped to 2.5.0; README, root SKILL.md, CLAUDE.md, AGENTS.md,
CHANGELOG updated for 17 skills. All deterministic gates pass.

Co-authored-by: Muratcan Koylan <muratcankoylan@users.noreply.github.com>
2026-07-11 17:11:27 +00:00

10 lines
767 B
JSON

{
"name": "context-engineering",
"description": "Context engineering and harness engineering skills for production-grade AI agent systems: fundamentals, degradation patterns, compression, optimization, latent briefing (KV cache sharing between agents), multi-agent coordination, long-horizon prompting (pseudo-formal task briefs for long-running and parallel agents), memory systems, tool design, evaluation, autonomous harnesses, self-improvement loops (RSI, meta-harnesses, evolutionary scaffold search), and a file-based researcher operating system with deterministic gates, a continuous loop, and measured router-benchmark results across four frontier models.",
"version": "2.5.0",
"author": {
"name": "Muratcan Koylan"
},
"skills": "./skills/"
}