Skill Cultivation Funnel

What it does

When your agent uses it

• Noticing a prompt or command chain you keep rebuilding by hand
• Patching a skill that lacks a key scenario
• Scaffolding a new local, project or community skill
• Running the safety scan before sharing a skill

Example prompts

• “I have typed the same release checklist three times, so turn it into a local skill.”
• “Improve my deploy skill so it handles rollback, and show me the diff.”
• “/cultivate-skill database migration review”

Requirements

• Node.js 18 or later, for scripts/skill_forge.js
• Compatibility (from SKILL.md): node>=18
• Pre-approved tools (allowed-tools): Bash, Read, Write, Edit, Grep

Workflow steps

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

1. 1frontmatter 合规：name kebab-case 唯一、description ≥ 40 字、user-invocable 显式声明
2. 2工具最小权限：allowed-tools 默认仅 Read；扩权（Bash/Write/Edit/WebFetch）必须有理由说明
3. 3无硬编码 secret（复用 analyzing-security 规则集）
4. 4无危险默认模板、无 prompt injection 反模式、scripts 单入口、引用文件存在

What it can do on your machine

Read from SKILL.md and the folder at commit 2544577. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • Write
  • Edit
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (JavaScript), which the agent can run.

  Shell commands in SKILL.md call:

  • node

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • telagod.github.io

  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.

• Compatibility

  node>=18

  From compatibility in the SKILL.md frontmatter.

Context cost

Skill Cultivation Funnel loads about 794 tokens when it runs, and up to ~4.6k if it reads all its reference files. Until then it costs about 95 tokens; SKILL.md has 127 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~95

When it runs · the whole SKILL.md, loaded when a task matches

~794

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.6k

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

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, Write, Edit, Grep

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); the scripts in this folder are not scanned.

SKILL.md

The full file from telagod/code-abyss at commit 2544577, republished under its MIT licence (© telagod). 127 words, ~794 tokens.

name

cultivating-skills

description

Distills repeated workflows into reusable skills, improves existing skills, and gates them through a three-tier publish funnel (local → project → community). Use when the agent or user notices a pattern worth crystallizing, when an existing skill is incomplete, or when something deserves community contribution. Default deny on dangerous tools and side effects.

allowed-tools

Bash, Read, Write, Edit, Grep

compatibility

node>=18

user-invocable

true

argument-hint

<distill|create|improve|publish> [topic-or-path]

aliases

forge-skill, cultivate-skill

<!-- safety-scan: ignore RM_RF_ROOT,CURL_PIPE_SH,PROMPT_INJECTION 本 skill 列举危险/注入模式作为反例，自身不执行 -->

<!-- safety-scan: ignore TOOLS_PRIVILEGED 特权理由：Bash 用于跑 forge 脚本；Write/Edit 用于在用户确认后落盘 skill 骨架；Grep 用于扫描重名 -->

L0 本地私有  ~/.claude/skills/local/         → 不入路由、显式调用、不审
L1 项目私有  <repo>/.claude/skills/          → 入 git、团队共享、强 lint
L2 社区贡献  GitHub Issue/PR + safety_scan   → 进入 upstream 候选池

# 脚手架：默认 L0 本地，可改 --tier project / community
node scripts/skill_forge.js init <slug> [--tier local|project|community]

# 本地校验（frontmatter + 引用 + 工具白名单）
node scripts/skill_forge.js lint <skill-dir>

# 安全扫描（落盘前必跑）
node scripts/skill_forge.js scan <skill-dir>

# 改进模式（生成 diff 草案）
node scripts/skill_forge.js improve <existing-skill-dir>

# 升级 tier
node scripts/skill_forge.js promote <skill-dir> --to project

© telagod, 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 6 other files (scripts, references) in skills/cultivating-skills of telagod/code-abyss.

• SKILL.md
• references/creation-workflow.md
• references/distillation-patterns.md
• references/improvement-workflow.md
• references/publishing-guide.md
• references/safety-review.md
• scripts/skill_forge.js

Open the folder on GitHubat commit 2544577