Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
批量回放 CombatSolver 的“找到更优世界线”报告，筛出同根、可比较且扣除药水成本后仍成立的策略缺口，并按小批次完成定位、改进和数字记录；不用于普通语义错误分诊或全量性能审计。
Install Strategy Replay Iteration
$ npx skills add Torch1230/CombatSolver --skill strategy-replay-iteration -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Torch1230/CombatSolver strategy-replay-iteration --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Torch1230/CombatSolver.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/strategy-replay-iteration .claude/skills/strategy-replay-iteration && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "strategy-replay-iteration" agent skill from https://github.com/Torch1230/CombatSolver/tree/main/.agents/skills/strategy-replay-iteration into .claude/skills/strategy-replay-iteration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "strategy-replay-iteration", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Torch1230/CombatSolver/tree/main/.agents/skills/strategy-replay-iterationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Torch1230/CombatSolver --skill strategy-replay-iteration -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Torch1230/CombatSolver strategy-replay-iteration --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Torch1230/CombatSolver.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/strategy-replay-iteration .agents/skills/strategy-replay-iteration && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "strategy-replay-iteration" agent skill from https://github.com/Torch1230/CombatSolver/tree/main/.agents/skills/strategy-replay-iteration into .agents/skills/strategy-replay-iteration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "strategy-replay-iteration", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Torch1230/CombatSolver --skill strategy-replay-iteration -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Torch1230/CombatSolver strategy-replay-iteration --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Torch1230/CombatSolver.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/strategy-replay-iteration .cursor/skills/strategy-replay-iteration && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "strategy-replay-iteration" agent skill from https://github.com/Torch1230/CombatSolver/tree/main/.agents/skills/strategy-replay-iteration into .cursor/skills/strategy-replay-iteration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "strategy-replay-iteration", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Torch1230/CombatSolver.git --path .agents/skills/strategy-replay-iteration--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Torch1230/CombatSolver --skill strategy-replay-iteration -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Torch1230/CombatSolver strategy-replay-iteration --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Torch1230/CombatSolver.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/strategy-replay-iteration .gemini/skills/strategy-replay-iteration && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "strategy-replay-iteration" agent skill from https://github.com/Torch1230/CombatSolver/tree/main/.agents/skills/strategy-replay-iteration into .gemini/skills/strategy-replay-iteration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "strategy-replay-iteration", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Torch1230/CombatSolver strategy-replay-iterationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Torch1230/CombatSolver --skill strategy-replay-iteration -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Torch1230/CombatSolver.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/strategy-replay-iteration .github/skills/strategy-replay-iteration && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "strategy-replay-iteration" agent skill from https://github.com/Torch1230/CombatSolver/tree/main/.agents/skills/strategy-replay-iteration into .github/skills/strategy-replay-iteration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "strategy-replay-iteration", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Torch1230/CombatSolver --skill strategy-replay-iteration -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Torch1230/CombatSolver strategy-replay-iteration --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Torch1230/CombatSolver.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/strategy-replay-iteration .opencode/skills/strategy-replay-iteration && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "strategy-replay-iteration" agent skill from https://github.com/Torch1230/CombatSolver/tree/main/.agents/skills/strategy-replay-iteration into .opencode/skills/strategy-replay-iteration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "strategy-replay-iteration", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
strategy-replay-iteration- GitHub stars
- 120
- Token cost
- ~614 tokens
- SKILL.md length
- 105 words
- Files
- 1
- Skills in repo
- 8
- Repo updated
- First seen
- Licence
- MIT
At a glance
批量回放 CombatSolver 的“找到更优世界线”报告，筛出同根、可比较且扣除药水成本后仍成立的策略缺口，并按小批次完成定位、改进和数字记录；不用于普通语义错误分诊或全量性能审计。
- Works in 4 steps: 小批次入口 → 有效策略缺口 → 定位与改进 → …
- Development work in your project
- SKILL.md covers 适用边界, 1. 小批次入口, 2. 有效策略缺口 and 3. 定位与改进, plus 1 more section
- Calls pwsh
What it does
Strategy Replay Iteration is an agent skill from Torch1230/CombatSolver. 批量回放 CombatSolver 的“找到更优世界线”报告，筛出同根、可比较且扣除药水成本后仍成立的策略缺口，并按小批次完成定位、改进和数字记录；不用于普通语义错误分诊或全量性能审计。
Its SKILL.md is about 610 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development. The repository describes itself as: Slay the Spire 2 single-player combat route solver mod. The licence is MIT.
When your agent uses it
- Development work in your project
Example prompts
- “找到更优世界线”
- “/strategy-replay-iteration”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 5c773ca. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pwsh
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Strategy Replay Iteration loads about 614 tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 105 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Torch1230/CombatSolver at commit 5c773ca, republished under its MIT licence (© Torch1230). 105 words, ~614 tokens.
Download SKILL.mdSave it as
.claude/skills/strategy-replay-iteration/SKILL.md (or your agent's skills folder).- name
- strategy-replay-iteration
- description
- 批量回放 CombatSolver 的“找到更优世界线”报告，筛出同根、可比较且扣除药水成本后仍成立的策略缺口，并按小批次完成定位、改进和数字记录；不用于普通语义错误分诊或全量性能审计。
CombatSolver 策略样例快速迭代
适用边界
本 skill 接续 issue-bundle-triage 已整理好的新旧报告，处理搜索质量。包协议和旧包恢复问题先修复日志/Testing 入口；出现 actual/simulated 差异、根状态漂移或动作无法合法回放时，转 combat-semantic-change；确认是展开、保路、终局排序或预算问题后，按 search-performance-optimization 的职责边界改动。
用户结束当前样例批次时立即停止，不继续挖掘未处理报告。
1. 小批次入口
- 每轮默认取排序最靠前的
3份，先Preflight再RestoreOnly，需要搜索或完整部署时显式选择SearchOnly/DeploySolver。不并发启动游戏。 - 统一入口
tools/replay/run-checkpoint-batch.ps1/.sh。输入接受 ZIP、目录、汇总 ZIP 和已解压旧包。 - 原包政策默认生效；缺项由显式政策文件补齐。每请求最多
120 s，不自动提高档位、Beam 或预算。 - 工具按玩家备注优先、已知减战损降序排队。排除包与小于 5 HP 的策略样例由当前任务清单决定，不硬编码玩家包 ID。
- 输出写入
.local/checkpoint-batch/，JSONL、JSON、CSV、Markdown 和逐请求证据同时保存；-Resume复用身份一致的已完成请求，-RetryFailures重试失败项。原始包、结果和日志不提交。
示例：
pwsh -NoProfile -File tools/replay/run-checkpoint-batch.ps1 `
-InputPath .local/issue-bundles/<batch>/raw/reports `
-ManifestPath .local/strategy-batch/<batch>.json `
-MaxReports 3 `
-ReplayMode Preflight执行恢复时改为 -ReplayMode RestoreOnly 并提供 -Sts2GameRoot。整场入口用 -CheckpointSelector start，不能从回合数猜测。完整使用方法见 docs/CHECKPOINT_REPLAY.md。
2. 有效策略缺口
只有以下条件同时成立，才进入求解器优化：
- 报告恢复到同一检查点，完整
ContinuationStamp、牌序和 RNG 严格一致； - 求解器与人工数字覆盖同一比较区间；中途根不冒充整场战损；
- 人工路线合法并实际存活，备注不是无效强制路线或错误人工计算；
- 人工路线的优势扣除额外药水后仍成立。
药水默认按每瓶 9 HP 计机会成本。人工多用 N 瓶时，只有省血至少 9 × N 才算更优；持有石化蟾蜍后每场生成的石头药按可再生资源处理，不要求为它保留 9 HP。比较时记录实际药水身份和数量，不能只看最终 HP。
预检阻塞、严格状态不一致、超时、无效人工基线和扣除药水成本后不成立的结果只记状态，然后继续下一份。遇到首个有效质量缺口后停止本轮余下样例，先完成一次可解释改进。
3. 定位与改进
当前逐包优化每次只处理一个包。从开始排查该包起累计计时；40 分钟仍未追平人工时，记录已有数字和未解决的问题，标记跳过并继续下一包。超时包直接跳过。此上限覆盖诊断、修改和验证，不因重新启动搜索而重置。
按目标路线消失的位置处理：
- 合法动作未进入候选：检查展开与单节点分支容量；
- 候选已出现但中途丢失：检查显式策略通道、Beam 保路、转置和支配；
- 完整路线仍在但没被选中：检查终局实际胜负、战损、药水与卖血排序；
- 只有提高预设才能找到：记录为预算差异，再判断是否属于档位容量，而不是先改权重。
能力、跨回合资源、卡牌联动、药水窗口和卖血必须用可兑现的后验验证。前验只负责让代表路线活到兑现点；最终结果继续按真实整场结果比较。优先修共享机制，不按遭遇或单卡硬编码路线，也不靠单纯拉宽 Beam 掩盖错误通道。 玩家的出牌记录用于定位遗漏的机制。不得把某份包的具体多牌出牌顺序或固定卡名组合写成生产搜索规则；按效果、状态、费用和兑现时机提炼能覆盖同类卡牌的候选或保路条件，再用完整路线验证。
每轮只保留一个可解释因素。目标改善后跑同一目标和一个受影响的不可退化哨兵；失败实验撤回，不累积互相抵消的参数。
4. 数字记录与收口
docs/archive/strategy/STRATEGY_OPTIMIZATION_LOG.md 只维护两张表：
- 汇总：日期、样例、玩家备注、优化前求解器、当前求解器、人工、优化幅度、相对人工、是否更优；
- 待处理：样例、当前数字或阻塞证据、状态。
不写正文复盘，不维护 docs/performance/PERFORMANCE_FIXTURES.md。搜索行为变化同步 docs/DEVELOPMENT_NOTES.md 与 docs/TEST_MATRIX.md；提交只包含本轮源码、最小 fixture 和文档。下一批从上批未处理项继续，不重跑已经取得直接证据的样例。
© Torch1230, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/strategy-replay-iteration of Torch1230/CombatSolver.
Open the folder on GitHubat commit 5c773ca
Compare with similar skills
Strategy Replay Iteration next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Strategy Replay Iteration this skillTorch1230/CombatSolver | 120 | — | ~614 | Automated safety check: Pass | MIT | |
| Vercel Composition Patternssupabase/supabase | 111k | 58 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 4 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
More from Torch1230/CombatSolver
All 8 skills in this repoCombat Semantic Change
Torch1230/CombatSolver
修改 CombatSolver 的卡牌、Power、遗物、药水、球、怪物行动、死亡召唤、选择、RNG、Fork 或跨回合战斗状态时，选择正确语义层并验证根快照、分支状态和实际结算。
Release Gate
Torch1230/CombatSolver
用户要求准备或发布 CombatSolver 版本、生成 ZIP、创建版本标签、上传 Steam 创意工坊或夸克网盘、同步 GitHub、执行干净安装或完整发布验收时，按口令边界完成对应阶段；普通开发不触发外部发布。
Architecture Boundary Refactor
Torch1230/CombatSolver
重构 CombatSolver 的 Search、Runtime 会话、UI snapshot、无人测试编排或 mirror registry 职责边界时使用；目标是迁移所有权和依赖，同时保持战斗语义、路线政策与协议行为不变。
Combatsolver Community Tasks
Torch1230/CombatSolver
静态分析 CombatSolver 日志的首因与共同机制，每批发布五个主题、每主题一至两个代表包；重复主题删除服务器包并跳过，发布后清理暂存。用于故障与路线优化社区任务，客户端发版使用 release-gate。
Issue Bundle Triage
Torch1230/CombatSolver
收到 CombatSolver 玩家问题 ZIP、战斗日志、存档或复现包时，安全盘点证据、确认声明版本、定位首个差异并设计可执行 fixture；不把问题包存在等同于已经回放。
UI Localization
Torch1230/CombatSolver
新增或修改 CombatSolver 玩家可见 UI 文案、胶囊附加信息、提示与本地化时使用，维护中英双语和显示边界；创意工坊介绍与发包另用 release-gate。
Related
Categories
Questions about Strategy Replay Iteration
What does Strategy Replay Iteration do?
批量回放 CombatSolver 的“找到更优世界线”报告，筛出同根、可比较且扣除药水成本后仍成立的策略缺口，并按小批次完成定位、改进和数字记录；不用于普通语义错误分诊或全量性能审计。. Strategy Replay Iteration is an agent skill from Torch1230/CombatSolver.
When should I use Strategy Replay Iteration?
Strategy Replay Iteration fits situations like: development work in your project.
How do I install Strategy Replay Iteration in Claude Code?
Run `npx skills add Torch1230/CombatSolver --skill strategy-replay-iteration -a claude-code`. Or copy the skill folder (.agents/skills/strategy-replay-iteration in Torch1230/CombatSolver) into .claude/skills/strategy-replay-iteration in your project. Claude Code loads it when a task matches its description.
How do I install Strategy Replay Iteration in Codex?
Run `npx skills add Torch1230/CombatSolver --skill strategy-replay-iteration -a codex`. Or copy the skill folder (.agents/skills/strategy-replay-iteration in Torch1230/CombatSolver) into .agents/skills/strategy-replay-iteration in your project. Codex loads it when a task matches its description.
Can I use Strategy Replay Iteration in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Torch1230/CombatSolver --skill strategy-replay-iteration -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/strategy-replay-iteration, .gemini/skills/strategy-replay-iteration, .github/skills/strategy-replay-iteration and .opencode/skills/strategy-replay-iteration in your project.
What does Strategy Replay Iteration need to run?
Going by SKILL.md and its folder, Strategy Replay Iteration needs the command-line tools its instructions call (pwsh).
Does Strategy Replay Iteration access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Strategy Replay Iteration safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Strategy Replay Iteration use?
Strategy Replay Iteration is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Strategy Replay Iteration use?
About 614 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Strategy Replay Iteration?
Skills that share tags, products or a category with Strategy Replay Iteration: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Strategy Replay Iteration?
Torch1230 (a GitHub user) maintains it in Torch1230/CombatSolver, which has 120 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 7, 2026.
Source: Torch1230/CombatSolver on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.