Agent skill

Nextclaw Iteration Log Governance

by Peiiii in Peiiii/nextclaw

A skill your agent uses when a commit/release, cross-module delivery, important root-cause fix, red-zone change, large governance rewrite, NPM release, work note, or goal anchor may require…

MITAuto-check passedDevelopment

Install Nextclaw Iteration Log Governance

skills CLI
$ npx skills add Peiiii/nextclaw --skill nextclaw-iteration-log-governance -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Peiiii/nextclaw nextclaw-iteration-log-governance --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Peiiii/nextclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/wiki/skills/governance/nextclaw-iteration-log-governance .claude/skills/nextclaw-iteration-log-governance && rm -rf skills-src

Use ~/.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/

Facts

Skill name
nextclaw-iteration-log-governance
GitHub stars
260
Token cost
~1.4k tokens
SKILL.md length
486 words
Files
1
Skills in repo
70
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when a commit/release, cross-module delivery, important root-cause fix, red-zone change, large governance rewrite, NPM release, work note, or goal anchor may require…

  • Works in 6 steps: ## 迭代完成说明 → ## 测试/验证/验收方式 → ## 发布/部署方式 → …
  • A commit/release
  • SKILL.md covers When To Use, Decision Rules, Thought / Design / Plan / Loop… and Same-Batch Rule, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Nextclaw Iteration Log Governance is an agent skill from Peiiii/nextclaw. Use when a commit/release, cross-module delivery, important root-cause fix, red-zone change, large governance rewrite, NPM release, work note, or goal anchor may require docs/logs; ordinary small edits do not trigger it.

Its SKILL.md is about 1.4k 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, covering Root cause analysis. It works with npm. 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 commit/release
  • Cross-module delivery
  • Important root-cause fix
  • Red-zone change

Example prompts

  • “/nextclaw-iteration-log-governance”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. ## 迭代完成说明
  2. ## 测试/验证/验收方式
  3. ## 发布/部署方式
  4. ## 用户/产品视角的验收步骤
  5. ## 可维护性总结汇总
  6. ## NPM 包发布记录

What it can do on your machine

Read from SKILL.md and the folder at commit 4d9d500. 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 (its code samples are markdown).

    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

Nextclaw Iteration Log Governance loads about 1.4k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 486 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 4d9d500, republished under its MIT licence (© Peiiii). 486 words, ~1,363 tokens.

Download SKILL.mdSave it as .claude/skills/nextclaw-iteration-log-governance/SKILL.md (or your agent's skills folder).
name
nextclaw-iteration-log-governance
description
Use when a commit/release, cross-module delivery, important root-cause fix, red-zone change, large governance rewrite, NPM release, work note, or goal anchor may require docs/logs; ordinary small edits do not trigger it.

NextClaw Iteration Log Governance

When To Use

普通任务在收尾时判断是否需要日志。大型交付执行启动即建立或复用进行中日志,及时保存关键决定、实验、失败、返工和集成结果;最后汇总,不等全部完成才补写。纯讨论/设计继续原文档,不自动启动实现。

Decision Rules

Record commit/release batches, cross-module or long deliveries, important root causes/red-zone changes, large governance changes, material history corrections and package publication state.

Ordinary uncommitted edits, isolated small fixes/tests/styles/refactors and metadata/discussion-doc edits do not require new logs. Large-delivery execution still records progress. Reuse a related active batch instead of creating one record per correction; explicit user requests override this gate.

Thought/design/plan/PRD documents stay in their own directories; logs link them.

Thought / Design / Plan / Loop Date Prefix

The iteration mechanism requires dated anchors and dotted role suffixes for thought, design, plan, and loop deposits:

  • files under docs/thoughts must use YYYY-MM-DD-<topic>.thought.md,
  • files under docs/designs must use YYYY-MM-DD-<topic>.design.md,
  • files under docs/plans must use YYYY-MM-DD-<topic>.plan.md,
  • files under docs/loops must use YYYY-MM-DD-<topic>.loop.md,
  • this rule applies even when the work does not need a docs/logs iteration record.

Same-Batch Rule

If the work is a micro-adjustment, verification fix, or follow-up in the same problem domain and same closing window as the most recent related iteration, update that iteration README.md.

Create a new iteration only when the goal has changed, impact expanded, a new independent batch started, a release/commit loop closed, or the user explicitly asked for separate traceability.

If a tiny new iteration was created by mistake, merge its useful content back into the related iteration and remove the mistaken directory.

目录命名

同时支持日期和版本号前缀,新建默认日期:

text
docs/logs/YYYY-MM-DD-<slug>/README.md
docs/logs/v<semver>-<slug>/README.md

日期取记录创建日,同批跨天保持目录,同日独立批次使用可区分的 slug。已有版本号记录原地续写;明确采用版本号形式时才比较现有合法版本并递增,日期目录不参与版本分配。目录号不是 NPM 发布号,不为同批建立日期/版本两份副本,也不批量迁移旧记录。

README Required Sections

Every iteration README.md must contain:

  1. ## 迭代完成说明
  2. ## 测试/验证/验收方式
  3. ## 发布/部署方式
  4. ## 用户/产品视角的验收步骤
  5. ## 可维护性总结汇总
  6. ## NPM 包发布记录

进行中日志保留这些章节,尚未交付/验证如实标明;大型交付另保存原始输入与约束、关联入口与过程记录。普通进展直接追加简短事件,长详情按需拆分,具体方法复用大型交付记录协议,不另建一套模板。日志中的交付摘要不覆盖整体合同和当前工作状态。

If the task is a fix, incident, root-cause investigation, or abnormal-behavior cleanup, the completion section must record:

  • root cause,
  • how it was confirmed,
  • why the fix targets the root cause rather than only the symptom.

If root cause is not fully known, explicitly write 根因未完全定位 with current gaps and next actions.

Show full SKILL.md (185 more words)Show less

NPM Release Record

Always fill this section.

If no package release is involved, write 不涉及 NPM 包发布.

If release is involved, list:

  • whether release is needed and why,
  • exact package names,
  • current published/unpublished state for each package,
  • 待统一发布 status when a package must follow a later batch release,
  • external blockers or trigger conditions.

Maintainability Summary

Always state simplification/reuse, sprawl and owner-boundary impact, file-organization compliance, guard findings and whether they triggered subjective review. If code maintainability is inapplicable, state the reason. Do not invent improvement to fill the section.

Work Notes

Loop 批次与逐轮记录

明确执行 .loop.md 任务时,其合同约定的逐轮可追踪性构成日志需求,可在启动时建立批次记录,不受“普通小改动不建日志”限制。复用上述命名,默认 docs/logs/YYYY-MM-DD-<slug>/README.md,也支持版本号;一次批次一个目录,同批返工不新建目录,不覆盖旧批次。普通大型交付不因有持续日志就自动进入 loop 或强制逐轮表格。

  • README 复用上述六个必需章节,在完成说明内维护批次状态、合同相对链接与版本(commit;未提交修订用只读快照或补丁固定)、授权、基准/当前最佳、预算起点/实耗、轮次索引及下一步/停止原因;运行中明确“进行中”,不得预填完成。运行状态使用 draft / active / paused / blocked / stopped / completed,只有明确启动或恢复才设为 active。
  • 每轮使用 work/YYYY-MM-DD-<topic>-round-<NNN>.md,日期为该轮开始日期,轮次在批次内递增;返工写回同一文件。沿用 work notes 的 .md,不新增文档类型或平行日志根目录。
  • 批次 README 顶部提供逐轮优化概览,兼作轮次索引:使用表格或列表直接写明“轮次/详情链接、优化前问题、本轮实际变化、验证结果与限制、保留/放弃决定”,不得只列标题和状态。每轮结束同步摘要,失败、无改动与返工如实列出,基线已有改进不计为本轮成果;用户无需逐个打开日志即可看懂改了什么。摘要引用详细记录,不重复维护实验过程。
  • 轮次记录包含问题证据、假设与预设判定、实际改动/返工、结果证据、保留/放弃依据、可测成本及限制。动手前记录判定,结束后补结果;失败也保留,事后补录必须注明来源及未知,禁止编造时间、指标或过程。
  • 图片、报告等新附件放批次 artifacts/,使用 YYYY-MM-DD-round-<NNN>-<description>.<ext> 并相对链接;既有 evidence/ 不迁移。材料是否证明结论由记录注明,不把临时绝对路径当长期记录。
  • 合同只定义设计;当前恢复状态唯一归 README,逐轮历史归轮次文件。完成记录不随新实验改写,纠错追加说明;合同修订只影响明确采用新版本的后续轮次。恢复默认读取合同、批次摘要及最近相关轮次。

新建大型交付以 docs/work/YYYY-MM-DD-<slug>/current-state.md 为恢复入口,日志回链。旧 working-notes 或迭代内入口原地续写,不复制第二份。普通跨轮任务沿共享轻量方法,不为笔记单独造日志目录。迭代内既有布局例如:

text
docs/logs/v<semver>-<slug>/work/working-notes.md

日志 README 链接唯一工作记录;loop 的当前状态若已归 README,仍以该入口为准,不再建立另一当前状态表。

Red-Zone Touches

If source red-zone files are touched, add:

md
## 红区触达与减债记录

### <repo-path>

- 本次是否减债:
- 说明:
- 下一步拆分缝:

Use the maintainability guard output and scripts/governance/maintainability/maintainability-hotspots.mjs as the source of truth.

Closing Output

At final response time, state:

  • whether an iteration record was required,
  • the reason,
  • the iteration path if created or updated,
  • why no record was needed if skipped.

© 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

Just SKILL.md in .agents/wiki/skills/governance/nextclaw-iteration-log-governance of Peiiii/nextclaw.

Open the folder on GitHubat commit 4d9d500

Compare with similar skills

Nextclaw Iteration Log Governance 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.

Nextclaw Iteration Log Governance compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nextclaw Iteration Log Governance this skillPeiiii/nextclaw260—~1.4kAutomated safety check: PassMIT
Debugging and Error Recoveryaddyosmani/agent-skills105k1 repos~2.6kAutomated safety check: PassMIT
Octocode Code Researchbgauryy/octocode949—~1.5kAutomated safety check: PassMIT
Binlog Generationmicrosoft/testfx1k2 repos~824Automated safety check: PassMIT
Debug Appmicrosoft/power-platform-skills984—~22kAutomated safety check: NotesMIT
Orca Run Replayiflytek/skillhub5.2k4 repos~3kAutomated safety check: PassApache-2.0

Similar skills

  • Debugging and Error Recovery

    addyosmani/agent-skills

    Applies a stop-the-line rule and a step-by-step triage when tests fail, builds break or something stops working, aiming at the root cause instead of guesses.

    105k GitHub starsUsed in 1 repo~2.6k tokens
    DevelopmentAuto-check passed
  • Octocode Code Research

    bgauryy/octocode

    Researches code with evidence: traces callers, imports and cross-repo links, diagnoses failures and reports findings with exact file and line references and a confidence label.

    949 GitHub stars~1.5k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Binlog Generation

    microsoft/testfx

    Official

    Generate MSBuild binary logs (binlogs) for build diagnostics and analysis.

    1k GitHub starsUsed in 2 repos~824 tokens
    DevelopmentAuto-check passed
  • Debug App

    microsoft/power-platform-skills

    Official

    A skill your agent uses when the user has finished building a mobile app, started Metro with npm run dev, and wants the running app monitored for runtime errors AND silent failures (empty lists…

    984 GitHub stars~22k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Orca Run Replay

    iflytek/skillhub

    Answers questions about a past agent run from its recording, using causal graphs and replay, instead of reconstructing events from memory.

    5.2k GitHub starsUsed in 4 repos~3k tokens
    Agent WorkflowsAuto-check passed
  • Nx Run Tasks

    nomcopter/react-mosaic

    Helps with running tasks in an Nx workspace. An agent skill from nomcopter/react-mosaic.

    4.8k GitHub starsUsed in 8 repos~613 tokens
    DevelopmentAuto-check passed

More from Peiiii/nextclaw

All 70 skills in this repo
  • Nextclaw 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…

    260 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • 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…

    260 GitHub stars~802 tokensUpdated yesterday
    Auto-check passed
  • 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。

    260 GitHub stars~801 tokensUpdated yesterday
    Auto-check passed
  • 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…

    260 GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • 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…

    260 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed
  • Curate NextClaw skill resources, including OpenClaw and community sources.

    260 GitHub stars~479 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Nextclaw Iteration Log Governance

What does Nextclaw Iteration Log Governance do?

A skill your agent uses when a commit/release, cross-module delivery, important root-cause fix, red-zone change, large governance rewrite, NPM release, work note, or goal anchor may require…. Nextclaw Iteration Log Governance is an agent skill from Peiiii/nextclaw. Use when a commit/release, cross-module delivery, important root-cause fix, red-zone change, large governance rewrite, NPM release, work note, or goal anchor may require docs/logs; ordinary small edits do not trigger it.

When should I use Nextclaw Iteration Log Governance?

Nextclaw Iteration Log Governance fits situations like: A commit/release; cross-module delivery; important root-cause fix; red-zone change.

How do I install Nextclaw Iteration Log Governance in Claude Code?

Run `npx skills add Peiiii/nextclaw --skill nextclaw-iteration-log-governance -a claude-code`. Or copy the skill folder (.agents/wiki/skills/governance/nextclaw-iteration-log-governance in Peiiii/nextclaw) into .claude/skills/nextclaw-iteration-log-governance in your project. Claude Code loads it when a task matches its description.

How do I install Nextclaw Iteration Log Governance in Codex?

Run `npx skills add Peiiii/nextclaw --skill nextclaw-iteration-log-governance -a codex`. Or copy the skill folder (.agents/wiki/skills/governance/nextclaw-iteration-log-governance in Peiiii/nextclaw) into .agents/skills/nextclaw-iteration-log-governance in your project. Codex loads it when a task matches its description.

Can I use Nextclaw Iteration Log Governance 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 nextclaw-iteration-log-governance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nextclaw-iteration-log-governance, .gemini/skills/nextclaw-iteration-log-governance, .github/skills/nextclaw-iteration-log-governance and .opencode/skills/nextclaw-iteration-log-governance in your project.

What does Nextclaw Iteration Log Governance need to run?

SKILL.md names no scripts, command-line tools or credentials: Nextclaw Iteration Log Governance is instructions for the agent only.

Does Nextclaw Iteration Log Governance 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 Nextclaw Iteration Log Governance 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 Nextclaw Iteration Log Governance use?

Nextclaw Iteration Log Governance 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 Nextclaw Iteration Log Governance use?

About 1.4k tokens (SKILL.md is roughly 5.5k 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 Nextclaw Iteration Log Governance?

Skills that share tags, products or a category with Nextclaw Iteration Log Governance: Debugging and Error Recovery (addyosmani/agent-skills, 105k stars), Octocode Code Research (bgauryy/octocode, 949 stars), Binlog Generation (microsoft/testfx, 1k stars) and Debug App (microsoft/power-platform-skills, 984 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nextclaw Iteration Log Governance?

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 9, 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.