Best agent instruction files skills, page 12

A skill your agent uses when creating Codex, Claude Code, Gemini CLI, Cursor, or AGENTS.md runtime adapters from one canonical agent core.

agentlas-ai/Agentlas-OS

Update AGENTS.md files based on session learnings about a topic.

cashew-labs/libretto

A skill your agent uses when the user wants their Claude agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, memory/skill consolidation, or says things like…

alirezarezvani/claude-skills

Update project CLAUDE.md with strategic knowledge discovered during this session — or CLAUDE.local.md when the discovery is per-developer/per-checkout and that file already exists.

umputun/cc-thingz

Mines a pull request's review threads for lessons that generalize beyond that PR, reconstructs each against the actual code before deciding, checks whether it is already codified, and routes the…

opsmill/infrahub

Check whether your rules file (CLAUDE.md or AGENTS.md) still matches the codebase after recent changes — run before a merge, or fold into your code-review pass.

coleam00/skills

Set up your project's global rules, a lean and well-structured root CLAUDE.md (plus a starter .claude/), following the course methodology.

coleam00/skills

Generates CLAUDE.md project memory files that transfer institutional knowledge.

jamditis/claude-skills-journalism

Selects the correct CLAUDE.md or LESSONS.md template via decision trees.

jamditis/claude-skills-journalism

Modular CLAUDE.md management strategy for projects that outgrow a single instruction file.

Resgrid/Core

Initialize new CLAUDE.md file(s) and optional skills/hooks with codebase documentation

asgeirtj/system_prompts_leaks

Initialize a new CLAUDE.md file with codebase documentation. An agent skill from asgeirtj/system_prompts_leaks.

asgeirtj/system_prompts_leaks

Toolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.

notque/vexjoy-agent

Post-ship documentation update. An agent skill from mr-daedalium/ostack-saas.

mr-daedalium/ostack-saas

A skill your agent uses for OpenIAP monorepo work that should follow the repository's shared agent workflows, including review-pr, audit-code, audit-security, audit-iapkit, compile-knowledge…

hyodotdev/openiap

Import memories into MemMesh from an exported file, a native MEMORY.md / CLAUDE.md, an ADR/decision log, or a mem0 export.

ThinkfleetAI/memmesh

Optional local install of flowctl CLI and CLAUDE.md/AGENTS.md instructions, plus a commented model-routing example proposed into the project instruction file.

gmickel/flow-next

This skill should be used when designing prompts, system prompts, or context windows for Claude.

closedloop-ai/claude-plugins

扫描当前仓库并生成或更新项目级 AGENTS.md / README.md / 全套脚手架文件（restart.sh、ignore、Dockerfile、docker-compose），适用于显式 project-scan、项目认知初始化或刷新项目级 Codex 上下文的场景。

doccker/cc-use-exp

Capture reusable lessons after a completed MAP workflow. An agent skill from azalio/map-framework.

azalio/map-framework

How to write great agent instructions for an agent-native app or template: AGENTS.md, skills, and tool/action descriptions.

BuilderIO/agent-native

初始化中文毕业论文工作区：检查学校模板与已有材料的放置位置，明确提示当前还缺什么，建立 codexmd/ / claudemd/ / tmplayout/ 等中间层目录，并生成材料盘点与初始工作文件。

WILLOSCAR/research-units-pipeline-skills

Review the current conversation to find agent mistakes, inefficiencies, and corrections, then propose new guidelines to add to CLAUDE.md to prevent recurrence.

meain/dotfiles

Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new…

tobihagemann/turbo

Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new…

tobihagemann/turbo

The AGENTS.md file that sf hardis:org:monitor:backup writes at the root of every monitoring repository, so a coding agent can answer questions about the org, its CI/CD deployments and its Grafana…

hardisgroupcom/sfdx-hardis

Launch SFT via python -m hpc.launch --jobtype sft on any cluster (JSC Jupiter GH200, CINECA Leonardo A100, TACC Vista GH200), with EITHER backend — LLaMA-Factory (default) or axolotl (--sftbackend…

open-thoughts/OpenThoughts-Agent

Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) via bias-free executor + two-sided evaluation (self-report + instruction-side…

mizchi/skills

Pair "what failed first" with "what finally worked" and codify the should-have-known-it insight as an ast-grep rule, a skill, or a CLAUDE.md rule.

mizchi/skills

A skill your agent uses when completing development phases or branches to identify and update CLAUDE.md or AGENTS.md files that may have become stale - analyzes what changed, determines affected…

ed3dai/ed3d-plugins

A skill your agent uses when writing instructions that guide Claude behavior - skills, CLAUDE.md files, agent prompts, system prompts.

ed3dai/ed3d-plugins

A skill your agent uses when creating or updating CLAUDE.md files for projects or subdirectories - covers top-level vs domain-level organization, capturing architectural intent and contracts, and…

ed3dai/ed3d-plugins

Grant b4mad-release-agent what it needs to run semantic-release on a Forgejo repo, install just release/just preflight into that repo's justfile and a short how-to into its AGENTS.md, then print the…

goern/forgejo-mcp

Pre-merge code review for .NET 10 pull requests. An agent skill from fmflurry/settings-opencode.

fmflurry/settings-opencode

Configure deployment settings for /land-and-deploy. An agent skill from no-session/pstack.

no-session/pstack

结构化新项目初始化工作流，适用于显式 project-init、仓库开荒、生成项目级 AGENTS.md 或按技术栈落基础脚手架文件的场景；不负责替用户无差别覆盖现有配置。

doccker/cc-use-exp

LLM-powered generation pipeline for Claude Code skills and AGENTS.md — doc-init command, prompt system, context building, and output parsing

aspenkit/aspens

세션 종료 시 자동 정리를 수행합니다. An agent skill from team-attention/stanford-cs146s-kr.

team-attention/stanford-cs146s-kr

Fill the empty Purpose cells of a directory AGENTS.md tree with one-line LLM summaries (one subagent per file, plan-then-confirm, cap 50 rows/run).

BlackBeltTechnology/pi-agent-dashboard

CLAUDE.md 雙向同步驗證：當合併外部 PR、Domain 升級 Skill、或 Tools 異動後，執行正向（作業→CLAUDE.md）與反向（CLAUDE.md→作業）的比對與修正迴圈。觸發條件：claude.md 同步、sync、驗證一致性、merge 後檢查、skill 新增後。

shuotao/REVIT_MCP_study

Apply Hunt and Thomas-inspired pragmatic programming rules when improving engineering judgment, feedback loops, DRY knowledge, orthogonality, automation, or adaptability.

ciembor/agent-rules-books

A skill your agent uses when a Personal Corp operating loop needs setup, repair, a new department, or task routing: HQ files and agent rules, GitHub issue workflow, corp- owner map, department…

serejaris/personal-corp-os

Review and update copilot instructions and skill files after completing a piece of work.

corvus-dotnet/Corvus.JsonSchema

A skill your agent uses to deploy and operate a CollectX (clx) based DOCA telemetry collector on a host or BlueField — wiring providers / counters into the collector, running the collection daemon…

NVIDIA/skills

Set up or refine open-source .NET code-quality gates for CI: formatting, .editorconfig, SDK analyzers, third-party analyzers, coverage, mutation testing, architecture tests, and security scanning.

managedcode/Storage

Apply SOLID, SRP, cohesion, composition-over-inheritance, and small-file discipline to code changes.

managedcode/Storage

Set up or refine solution-level governance for MCAF repositories: root and project-local AGENTS.md, rule precedence, solution topology, skill routing, and maintainability-limit policy placement.

managedcode/Storage

Add or update automated tests for a change using the repository’s verification rules in AGENTS.md.

managedcode/Storage