SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

Agent-Skills-for-Context-Engineeringmuratcankoylan/Agent-Skills-for-Context-Engineering

Provides a reusable set of context engineering and evaluation skills for developers building and tuning AI agents,…

No ratings yet Rate this skill
Stars18.2k
Forks1.5k
Watchers18.2k
Open Issues57

InstallOne-line install

Installable · 32 skills

This repository follows the Agent Skills spec, so one command installs it into your AI client — works across Claude Code, Codex, Cursor, Copilot, Windsurf, and 18+ other clients.

npx skills@latest add muratcankoylan/Agent-Skills-for-Context-Engineering

32 more are not listed — run npx skills@latest add muratcankoylan/Agent-Skills-for-Context-Engineering --list to see them all.

Add -g install globally (available in every project) · add --agent claude-code to target a client · add --yes to skip the prompts. Restart your AI client afterward and it will pick it up.

OverviewOverview

Key Features

Provides a reusable set of context engineering and evaluation skills for developers building and tuning AI agents, solving context bloat, cross-module contamination, and hard-to-quantify output quality. Key capabilities include: 1. Progressive Disclosure: loads context in layers on demand instead of filling the window at once, keeping key information within limited tokens for long tasks; 2. Module Isolation: isolates agent modules with different responsibilities to prevent instruction and state interference and improve multi-module collaboration stability; 3. Append-Only Memory: maintains dialogue and task memory in an append-only way, preserving full history without overwrite loss; 4. Automation Scripts: turns repetitive context organization and evaluation flows into executable scripts to reduce manual work; 5. Direct Scoring and Pairwise Comparison: scores model outputs individually or compares them in pairs to quantify answer quality; 6. Rubric Generation: automatically generates evaluation rubrics so scoring has a consistent basis; 7. Intelligent Segmentation and Prompt Diversity: intelligently splits long texts and generates diverse prompt variants to cover different input cases.

Use Cases

context compression for long-document QA and multi-turn dialogues, module isolation and memory management for multi-agent systems, model output quality evaluation and A/B comparison, batch generation of evaluation rubrics and prompts.

Target Roles

AI / Algorithm Engineer, Backend Developer, Product Manager (PM), Test / QA Engineer.

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID82
Data sourceGitHub
Repositorymuratcankoylan/Agent-Skills-for-Context-Engineering
CategoryAI & Agent Development / Context Engineering & Prompt Design
Primary languagePython
LicenseMIT License
Default branchmain
GitHub repository ID1120349776
Node IDR_kgDOQscuUA
Rank#78 (position within the source ranking)
Site-wide popularity rank#94 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

05k10k15k20k2026-10-102026-10-222026-10-10 · 18,0972026-10-14 · 18,0972026-10-16 · 18,0972026-10-22 · 18,188
  • Now18,188
  • Previous point · 10-16 18,097
  • vs previous point +91
  • 4 data points 12 days
05001k1.5k2k2026-10-102026-10-222026-10-10 · 1,4942026-10-14 · 1,4942026-10-16 · 1,4942026-10-22 · 1,503
  • Now1,503
  • Previous point · 10-16 1,494
  • vs previous point +9
  • 4 data points 12 days

TimelineTimeline

Repository created2025-12-21 02:43:4211 months ago
Data last updated2026-10-26 11:49:3222 days ago
Last commit2026-10-12 02:06:401 months ago

CommitLatest commit

committed by muratcankoylan. Category: Maintenance & Optimization. Commit message: Merge pull request #141 from muratcankoylan/long-horizon-handoff-cont….

9ff0c99 muratcankoylan 2026-10-12