opencode plugin skills

150 tagged opencode plugin, measured the same way as everything else here.

Browse within: opencode 83Orchestration 42agent-browser 35hiai 35multi-agent-systems 35Multi-Agent 25harness-engineering 25knowledge-management 25sdd 25spec-driven 25subagents 25agent-teams 24agentic-skills 8claude-plugin 8

spotme

01

wtfzambo/spotme

Skill Claude CodeCodex

Gym mode for agentic coding. When active, hands off implementation exercises to the human instead of completing them. Tracks difficulty and reviews submitted work.

190 3mo ago A 32 tokens

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Use this skill when autoresearchteam needs to manage an end-to-end research lifecycle from Boss brief to literature, idea, implementation, experiments, synthesis, and LaTeX delivery. Trigger for open-ended research tasks, autonomous research loops, idea-to-paper workflows, or long-running experiment iteration.

110 2mo ago A 65 tokens original MIT

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Use this skill when discovering papers, mapping related work, reading papers deeply, checking citations, or building evidence cards for an auto research task.

110 2mo ago A 35 tokens original MIT

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Use this skill when autoresearchteam needs deeper literature coverage, more citations in paper writing, stronger related-work synthesis, or a gate that prevents shallow research from reaching ideation or LaTeX.

110 2mo ago A 44 tokens original MIT

ndom91/open-plan-annotator

Skill Claude CodeCodex

Required reading whenever drafting any multi-step proposal, implementation plan, refactor approach, or response containing file paths and decision points. Use BEFORE writing any response that lists 3+ file paths, 2+ option-tradeoffs, a "Plan:"/"Steps:"/"Concrete changes:" section, or ends with "OK to proceed?" /…

90 14d ago A 199 tokens original MIT

btspoony/mstar-harness

Skill Claude CodeCodex

Morning Star 业务仓 Git 功能分支、worktree 隔离(L1 跨 plan:control worktree + 每 plan feature worktree + executionlease,默认 gitignore 下经 control 绝对路径读写进程产物;L2 同 plan:references/parallel-writable-pre-dispatch.md,N 次 invoke ≠ 隔离)、Spec 集成分支、QC/QA 检出对齐(Review cwd / Working branch / planid / Review range / Diff basis 三审 + QA 逐字相同)。Read…

57 yesterday A 166 tokens original MIT

mstar-conventions

07

btspoony/mstar-harness

Skill Claude CodeCodex

Morning Star (启明星) harness 计划目录约定 —— {HARNESSDIR} / {PLANDIR} / {SDDDIR} / {ITERATIONDIR} / {KNOWLEDGEDIR} / {SPECSDIR} / {WORKFLOWDIR} / {PROJECTDIR} 发现与初始化(默认 .mstar/,兼容 .agents/)、docs 与 harness 子树边界、review bundle、未启用 plan 时的工作方式、Spec 集成分支与多 Plan 实现分支(显式 base / merge 靶 / PR target)、Morning Star plan-writing path…

57 yesterday A 237 tokens original MIT

mstar-iteration

08

btspoony/mstar-harness

Skill Claude CodeCodex

Use when starting, driving, resuming, or closing a Morning Star iteration, or running an autonomous Phase 1–5 loop — including without a slash command (e.g. 'start an iteration', 'drive the iteration', 'run an autonomous loop'). Manages Phase 1 (default interactive direction lock; opt-in autonomous), Autonomous…

57 yesterday A 112 tokens original MIT

NovasPlace/CSM

Skill Claude CodeCodex

Coordinate Git and Cross-Session Memory as version control for agent work. Use when Codex needs AgentBook status, checkpoints, history, resume or handoff, provenance, isolated agent approaches, semantic comparison, or an evidence-backed game-development tuning and playtest iteration with an explicit keep or revert…

41 8d ago A 65 tokens original MIT

csm-continuity

13

NovasPlace/CSM

Skill Claude CodeCodex

Use the complete native Cross-Session Memory (CSM) runtime for continuity, memory governance, living state, beliefs, self-model, AgentBook, checkpoints, context cache, goals, work ledger, compaction, re-entry, or handoff across Codex tasks.

41 8d ago A 60 tokens original MIT

csm-governance

14

NovasPlace/CSM

Skill Claude CodeCodex

Safely deduplicate, review, merge, and archive Cross-Session Memory. Use when memory needs cleanup, dedup, merge, archive-candidate review, or recall-quality assessment.

41 8d ago A 43 tokens original MIT

java-patterns

15

DVNghiem/FlowDeck

Skill Claude CodeCodex

Modern Java 17+ patterns — records, sealed classes, Stream API, CompletableFuture, Spring Boot, JPA. Activate when writing or reviewing Java.

24 12d ago A 35 tokens original MIT

python-patterns

16

DVNghiem/FlowDeck

Skill Claude CodeCodex

Python idioms — type hints, dataclasses, async/await, generators, pytest, common pitfalls. Activate when writing or reviewing Python code.

24 12d ago A 33 tokens original MIT

research-first

17

DVNghiem/FlowDeck

Skill Claude CodeCodex

Strict research hierarchy before writing code — search codebase, docs, web, and registries in order.

24 12d ago A 24 tokens original MIT

HiAi-gg/hiai-opencode

Skill Claude CodeCodex

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

16 5d ago A 51 tokens

kibi-bootstrap

21

Looted/kibi

Skill Claude CodeCodex

Bootstrap Kibi from the current Git checkout with exact Git attachment, preview approval, source-first writes, and repair-safe completion.

8 yesterday A 29 tokens AGPL-3.0

kibi-freshness

22

Looted/kibi

Skill Claude CodeCodex

Check exact Git attachment, branch migration/quarantine, compiled-store freshness, source linkage, and repair state before decisions or writes.

8 yesterday A 31 tokens AGPL-3.0

Kibi Usage

23

Looted/kibi

Skill Claude CodeCodex

Use Kibi's source-first, exact-Git, migration-aware, proof-aware operations safely across MCP or the trusted local CLI, including partial completion repair.

8 yesterday A 35 tokens AGPL-3.0

annotate-md

24

konradmichalik/md-annotator

Skill Claude CodeCodex

Open Markdown file(s) in the browser-based md-annotator for interactive review, then apply the user's annotation feedback.

5 13d ago A 28 tokens original MIT