Context Compression
guanyang/open-agent-hub
This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve…
A skill your agent uses when a complex task will span turns or sessions and needs structured working notes to survive context compression or handoff; short single-turn work does not trigger it.
Install Iteration Work Notes
$ npx skills add Peiiii/nextclaw --skill iteration-work-notes -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Peiiii/nextclaw iteration-work-notes --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/Peiiii/nextclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/wiki/skills/process/iteration-work-notes .claude/skills/iteration-work-notes && 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 "iteration-work-notes" agent skill from https://github.com/Peiiii/nextclaw/tree/master/.agents/wiki/skills/process/iteration-work-notes into .claude/skills/iteration-work-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iteration-work-notes", 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/Peiiii/nextclaw/tree/master/.agents/wiki/skills/process/iteration-work-notesType 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 Peiiii/nextclaw --skill iteration-work-notes -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Peiiii/nextclaw iteration-work-notes --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Peiiii/nextclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/wiki/skills/process/iteration-work-notes .agents/skills/iteration-work-notes && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "iteration-work-notes" agent skill from https://github.com/Peiiii/nextclaw/tree/master/.agents/wiki/skills/process/iteration-work-notes into .agents/skills/iteration-work-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iteration-work-notes", 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 Peiiii/nextclaw --skill iteration-work-notes -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Peiiii/nextclaw iteration-work-notes --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Peiiii/nextclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/wiki/skills/process/iteration-work-notes .cursor/skills/iteration-work-notes && 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 "iteration-work-notes" agent skill from https://github.com/Peiiii/nextclaw/tree/master/.agents/wiki/skills/process/iteration-work-notes into .cursor/skills/iteration-work-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iteration-work-notes", 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/Peiiii/nextclaw.git --path .agents/wiki/skills/process/iteration-work-notes--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 Peiiii/nextclaw --skill iteration-work-notes -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Peiiii/nextclaw iteration-work-notes --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Peiiii/nextclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/wiki/skills/process/iteration-work-notes .gemini/skills/iteration-work-notes && 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 "iteration-work-notes" agent skill from https://github.com/Peiiii/nextclaw/tree/master/.agents/wiki/skills/process/iteration-work-notes into .gemini/skills/iteration-work-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iteration-work-notes", 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 Peiiii/nextclaw iteration-work-notesInstalls 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 Peiiii/nextclaw --skill iteration-work-notes -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Peiiii/nextclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/wiki/skills/process/iteration-work-notes .github/skills/iteration-work-notes && 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 "iteration-work-notes" agent skill from https://github.com/Peiiii/nextclaw/tree/master/.agents/wiki/skills/process/iteration-work-notes into .github/skills/iteration-work-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iteration-work-notes", 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 Peiiii/nextclaw --skill iteration-work-notes -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Peiiii/nextclaw iteration-work-notes --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Peiiii/nextclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/wiki/skills/process/iteration-work-notes .opencode/skills/iteration-work-notes && 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 "iteration-work-notes" agent skill from https://github.com/Peiiii/nextclaw/tree/master/.agents/wiki/skills/process/iteration-work-notes into .opencode/skills/iteration-work-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "iteration-work-notes", 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
iteration-work-notes- GitHub stars
- 260
- Token cost
- ~509 tokens
- SKILL.md length
- 134 words
- Files
- 3 (incl. references)
- Skills in repo
- 70
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when a complex task will span turns or sessions and needs structured working notes to survive context compression or handoff; short single-turn work does not trigger it.
- Works in 9 steps: 当前目标 → 当前事实 → 关键约束 / 不变量 → …
- A complex task will span turns
- SKILL.md covers 概述, 何时使用, 默认落点 and 推荐结构, plus 6 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Iteration Work Notes is an agent skill from Peiiii/nextclaw. Use when a complex task will span turns or sessions and needs structured working notes to survive context compression or handoff; short single-turn work does not trigger it.
Its SKILL.md is about 510 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/major-delivery-records.md`).
It sits in AI & LLM Engineering, covering LLM cost and token optimization. The repository describes itself as: A human-centered long-term AI partner—not a task-centered assistant. The licence is MIT.
When your agent uses it
- A complex task will span turns
- Sessions and needs structured working notes to survive context compression
- Short single-turn work does not trigger it
Example prompts
- “/iteration-work-notes”
Workflow steps
9 steps, taken from the first numbered list in SKILL.md.
- 当前目标
- 当前事实
- 关键约束 / 不变量
- 证据 / 观察点
- 活跃假设
- 已排除项
- 关键决策
- 下一步
- 剩余缺口 / 交接提醒
What it can do on your machine
Read from SKILL.md and the folder at commit 973722e. 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
No scripts in the folder and no shell commands in SKILL.md.
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
Iteration Work Notes loads about 509 tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 49 tokens; SKILL.md has 134 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 Peiiii/nextclaw at commit 973722e, republished under its MIT licence (© Peiiii). 134 words, ~509 tokens.
Download SKILL.mdSave it as
.claude/skills/iteration-work-notes/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- iteration-work-notes
- description
- Use when a complex task will span turns or sessions and needs structured working notes to survive context compression or handoff; short single-turn work does not trigger it.
Iteration Work Notes
概述
大型交付或查找/恢复已有大型交付时，先读取大型交付记录协议：新建默认 current-state.md，包含入口发现、当前状态与持续日志；旧入口兼容。下文是普通跨轮任务的轻量方法，不再并建一份记录。
这个 skill 用来把复杂任务和复杂 debug 的“易丢失上下文”外部化到项目已有的任务或迭代记录中。
目标不是写第二份 README.md，而是保证在以下场景里不会失忆：
- 上下文压缩
- 多次对话
- 长时间等待
- 中途交接
- 多轮实验后需要回看证据
何时使用
当任务满足以下任一特征时使用：
- 会跨多个阶段或多次对话
- 复杂 debug / 长链路排查
- 需要较长时间等待构建、发布、回归或线上观察
- 需要记录多条假设、证据、已排除路径与下一步
- 用户明确要求“记笔记”“保留过程”“避免上下文丢失”
以下情况通常不需要：
- 小而直接、单阶段、低风险的改动
- 纯措辞调整、轻量文档修补
默认落点
优先使用项目已有的任务记录目录；没有约定目录时使用 docs/work/YYYY-MM-DD-<task-slug>/working-notes.md，并从当前计划或设计链接它。日期取创建日，同任务跨天保持目录，已有记录不为日期前缀迁移。
规则：
- 默认先只用一个
working-notes.md - 只有当内容明显分叉或持续膨胀时，才拆出更多文件
- 不要仅为了记笔记提前新建新的迭代目录
已有任务目录时直接更新；不为了笔记新建版本发布目录。若项目已有更严格的迭代命名合同，采用项目路径。
推荐结构
working-notes.md 默认至少包含以下模块：
当前目标当前事实关键约束 / 不变量证据 / 观察点活跃假设已排除项关键决策下一步剩余缺口 / 交接提醒
其中：
当前事实只写已经确认的事实，不混入猜测活跃假设只保留仍未被证伪的路径已排除项用来防止上下文压缩后重复踩同一个坑下一步应该足够具体，让下一轮直接接上
更新时机
至少在以下时刻更新一次：
- 进入新阶段前
- 做完一轮关键实验后
- 改变主要判断或主要方案后
- 进入长时间等待前
- 结束当前会话前
记录原则
- 记录事实、分歧点、决策和下一步，不写流水账
- 优先写“为什么现在相信 X / 不再相信 Y”
- 优先链接文件、路径、命令或结果摘要，不粘贴大段原始输出
- 保持当前真相源，不要让旧结论和新结论混在一起
- 如果某条结论过期，直接改掉或标注失效，不要堆版本噪音
何时拆分
只有出现下面情况时再拆更多文件：
- 证据量很大，
working-notes.md已明显过长 - 同时存在两个以上稳定子问题域
- 需要把 handoff、evidence、decision log 分开维护
推荐拆分方式：
work/evidence.mdwork/decision-log.mdwork/handoff.md
拆分后仍要遵循一个原则：
- 当前计划、设计或任务入口必须链接这些文件
与任务 owner 的配合
- 本 skill 只负责跨轮事实载体，不反向编排调查或实施流程。
- 复杂多阶段实施：和主方案文档一起用。
- 需要交接：在
剩余缺口 / 交接提醒中留下最小接手上下文。
反模式
- 把
work/写成第二份完整计划或迭代 README - 把原始日志整段粘进去，几百行也不整理
- 只记现象，不记已排除项和下一步
- 关键决策只留在聊天里，不落到
work/ - 任务已经转向，但笔记仍停留在旧阶段
完成标准
只有满足以下条件，才算这份工作笔记真的有用：
- 下一轮对话不看历史长聊天，也能快速接上
- 已排除项和活跃假设是清楚分开的
- 当前决策与下一步是可执行的
- 当前任务入口能找到这份笔记
© Peiiii, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in .agents/wiki/skills/process/iteration-work-notes of Peiiii/nextclaw.
- SKILL.md
- agents/openai.yaml
- references/major-delivery-records.md
Open the folder on GitHubat commit 973722e
Compare with similar skills
Iteration Work Notes 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 |
|---|---|---|---|---|---|---|
| Iteration Work Notes this skillPeiiii/nextclaw | 260 | — | ~509 | Automated safety check: Pass | MIT | |
| Context Compressionguanyang/open-agent-hub | 975 | 2 repos | ~4.6k | Automated safety check: Pass | MIT | |
| Bounty Hunter1sadjlk/bounty-hunter-skill | 282 | 1 repos | ~761 | Automated safety check: Pass | MIT | |
| Skill Shortenerluongnv89/asm | 953 | — | ~3.8k | Automated safety check: Notes | MIT | |
| Fleet Auditoralexgreensh/token-optimizer | 2.5k | — | ~1.7k | Automated safety check: Pass | Custom licence | |
| Headroommomori777/Artemis | 377 | — | ~562 | Automated safety check: Pass | MIT |
Similar skills
Bounty Hunter
1sadjlk/bounty-hunter-skill
A professional AI bounty hunter persona named Atlas. An agent skill from 1sadjlk/bounty-hunter-skill.
Skill Shortener
luongnv89/asm
Refactor a too-long SKILL.md by progressive disclosure: measure token cost, classify every section KEEP/CUT/MOVE, shorten the body into references/ and scripts/, verify nothing was lost.
Fleet Auditor
alexgreensh/token-optimizer
Cross-system agent token/cost audit (Claude Code, Codex, OpenClaw, Hermes, OpenCode): idle burns, model misrouting, config bloat, with dollar savings.
Headroom
momori777/Artemis
SmartCrusher + CCR context compression — crunch large JSON arrays, tool outputs, and search results to save tokens.
Context Audit
undefined-ui/second-brain-os
Audit an agent's context layout against the four places: system prompt, tools, history, tail.
More from Peiiii/nextclaw
All 70 skills in this repoNextclaw Skin Studio
Peiiii/nextclaw
A skill your agent uses when a user wants to browse, apply, inspect, create, refine, switch, or remove a NextClaw skin; wants a personal skin with arbitrary CSS, JavaScript, images, SVG, DOM…
Development Task Telemetry
Peiiii/nextclaw
A skill your agent uses when a development task needs visible phase tracing, task-level or phase-level Token measurement, model/effort comparison, or a deterministic usage report or local dashboard…
Nextclaw Product Visual Assets
Peiiii/nextclaw
当 NextClaw 产品更新后需要生成、替换、挑毛病或检查官网、GitHub README、用户文档或社交传播中的真实截图、AI 宣传视觉、整页 HTML 宣传预览、社区二维码等对外视觉资产时使用；也用于“更新截图”“重新截一批图”“做宣传页”“生成 campaign 页面”“视觉审稿”“五星挑刺法”或发布前检查视觉资产。普通站点布局开发或只写文章不触发。
UI UX Pro Max
Peiiii/nextclaw
A skill your agent uses when the user wants professional UI/UX design guidance, design-system generation, UX review, or stack-specific frontend guidance through a bundled local UI/UX Pro Max dataset…
Impeccable
Peiiii/nextclaw
A skill your agent uses when the user wants distinctive, production-grade frontend design, anti-generic AI aesthetics, UX critique, technical UI audits, or final polish through bundled Impeccable…
Nextclaw Skill Resource Hub
Peiiii/nextclaw
Curate NextClaw skill resources, including OpenClaw and community sources.
Related
Categories
Questions about Iteration Work Notes
What does Iteration Work Notes do?
A skill your agent uses when a complex task will span turns or sessions and needs structured working notes to survive context compression or handoff; short single-turn work does not trigger it. Iteration Work Notes is an agent skill from Peiiii/nextclaw. Use when a complex task will span turns or sessions and needs structured working notes to survive context compression or handoff; short single-turn work does not trigger it.
When should I use Iteration Work Notes?
Iteration Work Notes fits situations like: A complex task will span turns; sessions and needs structured working notes to survive context compression; short single-turn work does not trigger it.
How do I install Iteration Work Notes in Claude Code?
Run `npx skills add Peiiii/nextclaw --skill iteration-work-notes -a claude-code`. Or copy the skill folder (.agents/wiki/skills/process/iteration-work-notes in Peiiii/nextclaw) into .claude/skills/iteration-work-notes in your project. Claude Code loads it when a task matches its description.
How do I install Iteration Work Notes in Codex?
Run `npx skills add Peiiii/nextclaw --skill iteration-work-notes -a codex`. Or copy the skill folder (.agents/wiki/skills/process/iteration-work-notes in Peiiii/nextclaw) into .agents/skills/iteration-work-notes in your project. Codex loads it when a task matches its description.
Can I use Iteration Work Notes 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 Peiiii/nextclaw --skill iteration-work-notes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/iteration-work-notes, .gemini/skills/iteration-work-notes, .github/skills/iteration-work-notes and .opencode/skills/iteration-work-notes in your project.
What does Iteration Work Notes need to run?
SKILL.md names no scripts, command-line tools or credentials: Iteration Work Notes is instructions for the agent only.
Does Iteration Work Notes 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 Iteration Work Notes 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 Iteration Work Notes use?
Iteration Work Notes 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 Iteration Work Notes use?
About 509 tokens (SKILL.md is roughly 2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.3k tokens, read only when the agent opens those files.
What are the alternatives to Iteration Work Notes?
Skills that share tags, products or a category with Iteration Work Notes: Context Compression (guanyang/open-agent-hub, 975 stars), Bounty Hunter (1sadjlk/bounty-hunter-skill, 282 stars), Skill Shortener (luongnv89/asm, 953 stars) and Fleet Auditor (alexgreensh/token-optimizer, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Iteration Work Notes?
Peiiii (a GitHub user) maintains it in Peiiii/nextclaw, which has 260 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on October 7, 2026.
Source: Peiiii/nextclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.