Agent skill

Kb

by evidentloop in evidentloop/sopify

Manage long-lived .sopify/ knowledge, including bootstrap, progressive materialization, reads, retention, and knowledgesync policy.

Apache-2.0Auto-check passed

Install Kb

skills CLI
$ npx skills add evidentloop/sopify --skill kb -a claude-code

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

GitHub CLI
$ gh skill install evidentloop/sopify kb --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/evidentloop/sopify.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/en/skills/sopify/kb .claude/skills/kb && 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
kb
GitHub stars
372
Token cost
~901 tokens
SKILL.md length
359 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
Apache-2.0

At a glance

Manage long-lived .sopify/ knowledge, including bootstrap, progressive materialization, reads, retention, and knowledgesync policy.

  • Works in 4 steps: project.md → user/preferences.md → blueprint/README.md → …
  • SKILL.md covers Directory responsibilities, Bootstrap and progressive…, Knowledge context reads and Retention and updates, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Kb is an agent skill from evidentloop/sopify. Manage long-lived .sopify/ knowledge, including bootstrap, progressive materialization, reads, retention, and knowledgesync policy.

Its SKILL.md is about 900 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Resumable, traceable AI coding — plans, handoffs, and evidence stay with the repo across hosts. The licence is Apache-2.0.

Example prompts

  • “/kb”

Workflow steps

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

  1. project.md
  2. user/preferences.md
  3. blueprint/README.md
  4. Relevant parts of blueprint/background.md, design.md, and tasks.md

What it can do on your machine

Read from SKILL.md and the folder at commit 9d9b319. 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 yaml).

    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

Kb loads about 901 tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 359 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~901

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 evidentloop/sopify at commit 9d9b319, republished under its Apache-2.0 licence (© evidentloop). 359 words, ~901 tokens.

Download SKILL.mdSave it as .claude/skills/kb/SKILL.md (or your agent's skills folder).
name
kb
description
Manage long-lived `.sopify/` knowledge, including bootstrap, progressive materialization, reads, retention, and knowledge_sync policy.

Knowledge Base Management

KB owns long-lived knowledge. It does not make Analyze, Design, or Develop decisions, and it does not manage the active plan, handoff, receipts, or finalize directly. Document structures come from Templates; protocol state is managed through sopify_writer.

Directory responsibilities

text
.sopify/
├── project.md              # reusable technical conventions
├── user/                   # long-term preferences and raw feedback
├── blueprint/              # long-term goals, design boundaries, open work, and index
├── plan/                   # current plan semantic files
├── history/                # archived plans and index
└── state/                  # local protocol state

blueprint/README.md keeps only status, maintenance guidance, current goal, current focus, and reading links. Put detailed content in the relevant blueprint file.

Bootstrap and progressive materialization

kb_init: full creates project.md, user/preferences.md, user/feedback.jsonl, and the four blueprint files on first use. It does not pre-create plan content, history, or empty directories.

kb_init: progressive is the default:

  • First real project use: create project.md, user/preferences.md, and blueprint/README.md.
  • First plan lifecycle: add blueprint/background.md, blueprint/design.md, blueprint/tasks.md, and the current plan directory.
  • First explicit ~go finalize: let the protocol flow create history/index.md and the archive directory.
  • First explicit long-term feedback: create user/feedback.jsonl when needed.

Knowledge context reads

The host completes the governing Protocol entry for a managed plan, handoff, and receipts before invoking KB. This section defines only KB's long-lived context order:

  1. project.md
  2. user/preferences.md
  3. blueprint/README.md
  4. Relevant parts of blueprint/background.md, design.md, and tasks.md

Consult and quick fix do not fail when deep blueprint files are absent. Read history/ only for trace-back or finalize.

Show full SKILL.md (158 more words)Show less

Retention and updates

Keep information only when it remains useful across tasks:

  • project.md: reusable technical conventions.
  • background.md: long-term goals, scope, and non-goals.
  • design.md: module, host, directory, and consumption contracts.
  • tasks.md: unfinished long-term work and explicit deferrals with a revisit condition.
  • preferences.md: explicit long-term user preferences.

Do not store one-off implementation details, current-plan task breakdowns, temporary tradeoffs, completed tasks, or copies of history content. When code and documentation conflict, verify the code and then correct the documentation. Current user instructions override historical preferences.

knowledge_sync

yaml
knowledge_sync:
  project: skip|review|required
  background: skip|review|required
  design: skip|review|required
  tasks: skip|review|required
  • skip: do not inspect that file for this plan.
  • review: decide whether it needs an update before finalize.
  • required: update it before the delivery candidate; block finalize while incomplete.

KB applies the plan's sync policy without changing the plan lifecycle. Update the narrowest long-lived location and avoid duplicating the same content across files.

Output

After bootstrap or sync, state the actual result, list Changes, and end with Next:. Use Changes: 0 files when nothing changed.

© evidentloop, Apache-2.0. 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 skills/en/skills/sopify/kb of evidentloop/sopify.

Open the folder on GitHubat commit 9d9b319

Compare with similar skills

Kb 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.

Kb compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Kb this skillevidentloop/sopify372—~901Automated safety check: PassApache-2.0
Live DashboardNousResearch/hermes-agent252k—~2.1kAutomated safety check: PassMIT
Bootstrap Soulbytedance/deer-flow83k2 repos~1.2kAutomated safety check: PassMIT
Live Dashboardnexu-io/open-design100k—~2.1kAutomated safety check: PassApache-2.0
Audit Livenessben-manes/caffeine18k—~501Automated safety check: PassApache-2.0
Living Docs Governanceaffaan-m/ECC274k1 repos~2.1kAutomated safety check: PassMIT

Similar skills

  • Live Dashboard

    NousResearch/hermes-agent

    Build self-updating dashboards from live sources. An agent skill from NousResearch/hermes-agent.

    252k GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Bootstrap Soul

    bytedance/deer-flow

    Runs a short adaptive conversation with you and writes a personalized SOUL.md that defines your AI partner's name, personality, communication style and boundaries.

    83k GitHub starsUsed in 2 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Live Dashboard

    nexu-io/open-design

    Notion-style team dashboard rendered as a Live Artifact. An agent skill from nexu-io/open-design.

    100k GitHub stars~2.1k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Audit Liveness

    ben-manes/caffeine

    Analyze the cache for liveness defects (progress, termination, starvation)

    18k GitHub stars~501 tokensUpdated 2 days ago
    Auto-check passed
  • Keep a long-lived project's documentation from rotting by assigning existing project docs clear constitution, map, status, and history roles, then wiring the active agent harness to those canonical…

    274k GitHub starsUsed in 1 repo~2.1k tokens
    DevelopmentAuto-check passed
  • Progressive Jpeg

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing image assets, markup, and CDN or build transforms related to Use progressive JPEG encoding.

    74k GitHub stars~426 tokensUpdated yesterday
    Auto-check passed

More from evidentloop/sopify

All 8 skills in this repo
  • Analyze

    evidentloop/sopify

    Analyze phase entry. An agent skill from evidentloop/sopify.

    372 GitHub stars~486 tokensUpdated 1 mo ago
    Auto-check passed
  • Design

    evidentloop/sopify

    Design phase entry. An agent skill from evidentloop/sopify.

    372 GitHub stars~442 tokensUpdated 1 mo ago
    Auto-check passed
  • Develop

    evidentloop/sopify

    Develop phase entry; routes task execution, state updates, KB sync, and plan close-out through references/assets/scripts.

    372 GitHub stars~484 tokensUpdated 1 mo ago
    Auto-check passed
  • Analyze

    evidentloop/sopify

    需求分析阶段入口;聚合评分、追问与范围判定规则,按需加载 references/assets/scripts. An agent skill from evidentloop/sopify.

    372 GitHub stars~268 tokensUpdated 1 mo ago
    Auto-check passed
  • Design

    evidentloop/sopify

    方案设计阶段入口;聚合方案分级、任务拆分与方案包输出规则,按需加载 references/assets/scripts。

    372 GitHub stars~241 tokensUpdated 1 mo ago
    Auto-check passed
  • Develop

    evidentloop/sopify

    开发实施阶段入口;聚合任务执行、状态更新、知识库同步与收尾状态规则,按需加载 references/assets/scripts。

    372 GitHub stars~274 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Kb

What does Kb do?

Manage long-lived .sopify/ knowledge, including bootstrap, progressive materialization, reads, retention, and knowledgesync policy. Kb is an agent skill from evidentloop/sopify.sopify/ knowledge, including bootstrap, progressive materialization, reads, retention, and knowledgesync policy.

How do I install Kb in Claude Code?

Run `npx skills add evidentloop/sopify --skill kb -a claude-code`. Or copy the skill folder (skills/en/skills/sopify/kb in evidentloop/sopify) into .claude/skills/kb in your project. Claude Code loads it when a task matches its description.

How do I install Kb in Codex?

Run `npx skills add evidentloop/sopify --skill kb -a codex`. Or copy the skill folder (skills/en/skills/sopify/kb in evidentloop/sopify) into .agents/skills/kb in your project. Codex loads it when a task matches its description.

Can I use Kb 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 evidentloop/sopify --skill kb -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kb, .gemini/skills/kb, .github/skills/kb and .opencode/skills/kb in your project.

What does Kb need to run?

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

Does Kb 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 Kb 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 Kb use?

Kb is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Kb use?

About 901 tokens (SKILL.md is roughly 3.6k 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 Kb?

Skills that share tags, products or a category with Kb: Live Dashboard (NousResearch/hermes-agent, 252k stars), Bootstrap Soul (bytedance/deer-flow, 83k stars), Live Dashboard (nexu-io/open-design, 100k stars) and Audit Liveness (ben-manes/caffeine, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kb?

evidentloop (a GitHub organization) maintains it in evidentloop/sopify, which has 372 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on August 30, 2026.

Source: evidentloop/sopify on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.