oxbshw/LLM-Agents-Ecosystem-Handbook

One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools.

546Stars on the repository
10Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

adr-writer

01

oxbshw/LLM-Agents-Ecosystem-Handbook

Skill Claude CodeCodex

Use when capturing an architecture decision so it survives turnover — produces an ADR-NNNN.md from context, options considered, and the chosen path.

not rated 546 2mo ago A SkillSpector: pass 33 tokens original MIT

api-design-reviewer

02

oxbshw/LLM-Agents-Ecosystem-Handbook

Skill Claude CodeCodex

Use when reviewing a proposed REST or GraphQL API change before merge — checks contract clarity, backwards compatibility, errors, pagination, auth, and naming.

not rated 546 2mo ago A SkillSpector: pass 35 tokens original MIT

dataset-profiler

03

oxbshw/LLM-Agents-Ecosystem-Handbook

Skill Claude CodeCodex

Use when first encountering a new dataset — produces a structured profile (schema, missingness, distributions, outliers, gotchas) before any analysis.

not rated 546 2mo ago A SkillSpector: pass 34 tokens original MIT

incident-postmortem

04

oxbshw/LLM-Agents-Ecosystem-Handbook

Skill Claude CodeCodex

Use after an incident is resolved — drafts a blameless postmortem from timeline notes, alerts, and chat threads.

not rated 546 2mo ago A SkillSpector: pass 30 tokens original MIT

pr-summarizer

05

oxbshw/LLM-Agents-Ecosystem-Handbook

Skill Claude CodeCodex

Use when opening a PR — produces a clean PR description (what / why / how to verify / risks) from a branch diff against base.

not rated 546 2mo ago A SkillSpector: pass 34 tokens original MIT

sprint-planner

06

oxbshw/LLM-Agents-Ecosystem-Handbook

Skill Claude CodeCodex

Use when planning the next sprint — turns ticket intake + team capacity into a planned sprint with explicit non-goals.

not rated 546 2mo ago A SkillSpector: pass 28 tokens original MIT

oxbshw/LLM-Agents-Ecosystem-Handbook

Skill Claude CodeCodex

Use after a session to promote useful episodic notes from logs/episodic/ into distilled, dated entries in MEMORY.md and memory/semantic/.

not rated 546 2mo ago A SkillSpector: pass 35 tokens original MIT

oxbshw/LLM-Agents-Ecosystem-Handbook

Skill Claude CodeCodex

Use before connecting a new MCP server to your agent — produces a structured security review covering source, permissions, tools, network, and approvals.

not rated 546 2mo ago A SkillSpector: pass 34 tokens original MIT

repo-auditor

09

oxbshw/LLM-Agents-Ecosystem-Handbook

Skill Claude CodeCodex

Use before opening a PR to audit the changes for stale comments, unused imports, missing tests, and inconsistencies with neighboring code.

not rated 546 2mo ago A SkillSpector: pass 31 tokens original MIT

research-summarizer

10

oxbshw/LLM-Agents-Ecosystem-Handbook

Skill Claude CodeCodex

Use when the user asks for a sourced briefing on a topic that spans multiple web sources and requires citations.

not rated 546 2mo ago A SkillSpector: pass 26 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: