Agent skill

Promptbase

by kid-sid in kid-sid/claude-spellbook

A skill your agent uses when writing, reviewing, or adapting a Claude Code skill for sale on PromptBase — checking scope, audience breadth, rejection risk, description quality, examples, and setup…

MITAuto-check passed

Install Promptbase

skills CLI
$ npx skills add kid-sid/claude-spellbook --skill promptbase -a claude-code

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

GitHub CLI
$ gh skill install kid-sid/claude-spellbook promptbase --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/kid-sid/claude-spellbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/promptbase .claude/skills/promptbase && 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
promptbase
GitHub stars
189
Token cost
~2.3k tokens
SKILL.md length
1,084 words
Files
1
Skills in repo
52
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when writing, reviewing, or adapting a Claude Code skill for sale on PromptBase — checking scope, audience breadth, rejection risk, description quality, examples, and setup…

  • Works in 3 steps: One sentence on the problem it solves → 4–6 bullet points on what Claude knows… → One line on format and installation
  • Adapting a Claude Code skill for sale on PromptBase — checking scope
  • SKILL.md covers When to Activate, The Core Test: Would a…, Rejection Reasons and Fixes and Scope Rules, plus 3 more sections
  • Calls python

What it does

Promptbase is an agent skill from kid-sid/claude-spellbook. Use when writing, reviewing, or adapting a Claude Code skill for sale on PromptBase — checking scope, audience breadth, rejection risk, description quality, examples, and setup instructions.

Its SKILL.md is about 2.3k 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: A curated collection of skills, prompts, and workflows that extend Claude's capabilities — your personal grimoire for AI-powered development. The licence is MIT.

When your agent uses it

  • Adapting a Claude Code skill for sale on PromptBase — checking scope
  • Audience breadth
  • Description quality
  • Setup instructions

Example prompts

  • “/promptbase”

Requirements

  • Python 3

Workflow steps

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

  1. One sentence on the problem it solves
  2. 4–6 bullet points on what Claude knows after activation
  3. One line on format and installation

What it can do on your machine

Read from SKILL.md and the folder at commit a7c2ac9. 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:

    • python

    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

Promptbase loads about 2.3k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 1,084 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

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 kid-sid/claude-spellbook at commit a7c2ac9, republished under its MIT licence (© kid-sid). 1,084 words, ~2,331 tokens.

Download SKILL.mdSave it as .claude/skills/promptbase/SKILL.md (or your agent's skills folder).
name
promptbase
description
Use when writing, reviewing, or adapting a Claude Code skill for sale on PromptBase — checking scope, audience breadth, rejection risk, description quality, examples, and setup instructions.

PromptBase Skill Publishing

Patterns for writing Claude Code skills that pass PromptBase review and sell well.

When to Activate

  • Writing a new skill intended for sale on PromptBase
  • Reviewing an existing skill before submission
  • Adapting a rejected skill after a "too specific" or "too simple" ruling
  • Writing listing copy — title, description, examples, setup instructions
  • Deciding whether a skill idea is worth submitting at all

The Core Test: Would a Stranger Pay For This?

Before writing a single line, answer three questions:

QuestionGreen lightRed light
Who is the buyer?Any Python/TS/Go developerUsers of one specific internal platform
What problem does it solve?A hard, non-obvious problem they hit oftenSomething a quick search answers
Could they reproduce it from the title alone?No — the value is in the patternsYes — the title explains everything

If any answer is red, fix the concept before writing the skill.


Rejection Reasons and Fixes

Too Specific (most common rejection)

What it means: The skill only works for users of a niche platform, private SDK, or internal framework. The audience is too small to justify listing it.

Signs your skill is too specific:

  • It imports from a private package (from mycompany.lib import ...)
  • It references internal tool names, ports, config files, or env vars no outsider would know
  • It combines more than 3 niche ideas (e.g. "LangGraph + Agentex + custom state machine")
  • The target framework has fewer than ~5k GitHub stars

Fix: generalize the layer

REJECTED:  Temporal + Agentex ADK + adk.state + adk.messages + FastACP
APPROVED:  Temporal + Python temporalio SDK — standard patterns any developer can use

Strip the platform-specific layer. Keep the hard, transferable patterns underneath.


Too Simple / Guessable

What it means: A buyer could recreate the skill by reading the title and thinking for 30 seconds. The value isn't there.

Signs your skill is too simple:

  • The entire skill is one pattern or one code snippet
  • It documents official defaults (e.g. "how to create a FastAPI route")
  • It has no decision tables, no red flags, no non-obvious gotchas
  • Word count is low AND there are no patterns that require explanation

Fix: add depth

  • Add a decision table (when to use X vs Y)
  • Add a Red Flags section (7–10 anti-patterns with explanations)
  • Add the non-obvious gotchas — things that only experience teaches
  • Add a pre-ship checklist

No Use Case

What it means: The skill has no practical application for real work — it's a demo, experiment, or overly academic topic.

Fix: Anchor every section to a real scenario a working developer would face. If you can't name a concrete task the skill helps complete, the concept needs rethinking.


Scope Rules

ScopeVerdictNotes
Standard open-source framework (FastAPI, Redis, Temporal)✅ GoodBroad audience
Cloud provider service (AWS S3, Azure Blob)✅ GoodLarge user base
Niche but popular tool (LangGraph, Pydantic v2)✅ OKActive community
Combination of 2 standard tools✅ OKKeep each section useful standalone
Combination of 3+ niche tools⚠️ RiskMay be rejected as too specific
Private/internal SDK or platform❌ RejectUseless to outsiders
Single well-known function/pattern❌ RejectToo simple

The 3-niche rule: PromptBase rejects skills that combine more than 3 niche ideas. A "niche idea" is any tool, pattern, or concept that a developer might not already know. Standard Python, SQL, and REST are not niche. LangGraph, Temporal, and a custom state machine pattern together are three niche ideas — borderline.


Writing the Listing

Title
# BAD — platform-specific, tiny audience
Agentex Temporal Agent Skill

# BAD — too vague, no value signal
Python Async Skill

# GOOD — specific problem, broad audience
Crash-Proof AI Agents: Temporal Workflow Skill for Claude Code

Formula: [Outcome the buyer wants]: [Technology] Skill for Claude Code

Description (keep it under 100 words)

Structure:

  1. One sentence on the problem it solves
  2. 4–6 bullet points on what Claude knows after activation
  3. One line on format and installation
markdown
Your Temporal workflows break in ways that are invisible until production.
This skill teaches Claude the patterns that prevent it.

- Workflow vs activity split and determinism rules
- Retry policies, timeouts, and heartbeats
- State management across replays
- Signal handling and `wait_condition`
- 7 red flags that silently break Temporal agents

One `.md` file. Drop in `~/.claude/skills/` — activates automatically.
When to Use (activation description)

Write this as a single sentence starting with "Use when" that describes triggering conditions — not a summary of topics:

# BAD — topic summary, not a trigger
Use when working with Temporal, workflows, activities, signals, and state.

# GOOD — triggering condition
Use when building or debugging Temporal workflows in Python — structuring
activities, enforcing determinism, handling retries, or diagnosing replay failures.
Examples (2 required)

Each example is a realistic user message + a sample Claude response showing the skill in action.

Example 1 (shown as preview on store page): Pick the sharpest, most impressive demo — the problem that would make a buyer think "I need this right now."

Example 2: Show a different use case from Example 1. Don't demonstrate the same pattern twice.

# BAD example pair — same pattern twice
Example 1: "How do I add a retry to my activity?"
Example 2: "How do I set a timeout on my activity?"

# GOOD example pair — different concerns
Example 1: "My workflow stops receiving signals after the first message."
Example 2: "Can I call httpx directly inside my workflow?"
Show full SKILL.md (418 more words)Show less
Setup Instructions

Keep it to 3 steps maximum:

markdown
1. Download `skill.md`
2. Place it at `~/.claude/skills/<skill-name>/skill.md`
3. Restart Claude Code

No MCP servers, env vars, or dependencies required.

If the skill requires external tools (MCP server, API key), list them explicitly. Buyers who can't set up the skill will leave bad reviews.

Skill Body (the SKILL.md content)

PromptBase asks for the body only — everything after the YAML frontmatter. The frontmatter is generated on their end. Paste starting from the first # heading.


Pre-Submission Checklist

  • Skill uses only publicly available, open-source tools — no private SDKs
  • Topic is not reproducible from the title alone — real value is in the patterns
  • Combines at most 3 niche ideas
  • Has at least one decision/comparison table
  • Has a ## Red Flags section with 6–10 domain-specific anti-patterns
  • Has a ## Checklist section with 8–12 pre-ship items
  • Title follows [Outcome]: [Tech] Skill for Claude Code formula
  • Description is under 100 words and leads with the problem
  • description frontmatter starts with "Use when" and describes trigger conditions only
  • Two examples show different use cases, not the same pattern twice
  • Setup instructions have 3 steps or fewer
  • Skill body pasted without frontmatter (PromptBase generates it)
  • No references to internal systems, private repos, or proprietary env vars

Red Flags

  • Private SDK imports in examples — any from yourcompany.internal import ... immediately signals the skill is platform-locked; reviewers reject these without reading further; replace with the standard open-source equivalent
  • Title that gives away the entire skill — if the title is "Use retry_policy=RetryPolicy(maximum_attempts=3) in Temporal", a buyer can reproduce it without purchasing; titles should name the outcome, not the solution
  • Description longer than 150 words — PromptBase listing descriptions overflow on mobile and store pages; buyers skim; if you need 200 words the concept isn't focused enough
  • Examples that demonstrate the same pattern — two examples showing retry configuration are one example, not two; reviewers flag this as low variety; each example must address a distinct concern
  • Setup instructions that require a paid API key or private access — buyers who hit a wall during setup leave negative reviews; if the skill requires external services, state it prominently in the listing before purchase
  • "Use when" description that summarizes topics instead of triggers — "Use when working with Redis, caching, pub/sub, and streams" is a topic list; "Use when choosing a Redis data structure, implementing rate limiting, or debugging slow commands" is a trigger list; only triggers activate the skill correctly
  • Submitting a skill that is a thin wrapper around official docs — if every pattern in the skill appears verbatim in the framework's own documentation, it adds no value; the skill must contain non-obvious patterns, gotchas, and decisions that experience teaches

© kid-sid, 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 skills/promptbase of kid-sid/claude-spellbook.

Open the folder on GitHubat commit a7c2ac9

Compare with similar skills

Promptbase 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.

Promptbase compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Promptbase this skillkid-sid/claude-spellbook189—~2.3kAutomated safety check: PassMIT
Sales Enablementcoreyhaines31/marketingskills54k—~5.2kAutomated safety check: PassMIT
SalesXiaomiMiMo/MiMo-Code14k—~637Automated safety check: PassMIT
Agent Adaptive Coordinatorruvnet/ruflo74k2 repos~4kAutomated safety check: PassMIT
Pod Salesruvnet/ruflo74k1 repos~774Automated safety check: NotesMIT
Sales Accountingsickn33/agentic-awesome-skills47k1 repos~6.4kAutomated safety check: PassMIT

Similar skills

  • Sales Enablement

    coreyhaines31/marketingskills

    When the user wants to create sales collateral, pitch decks, one-pagers, objection handling docs, or demo scripts.

    54k GitHub stars~5.2k tokensUpdated today
    Sales & SupportAuto-check passed
  • Sales

    XiaomiMiMo/MiMo-Code

    A skill your agent uses whenever Sales is explicitly invoked or the task involves customer meeting preparation, call follow-up, account prioritization, account signals, deal strategy, business…

    14k GitHub stars~637 tokensUpdated 5 days ago
    Sales & SupportAuto-check passed
  • Agent skill for adaptive-coordinator - invoke with $agent-adaptive-coordinator

    74k GitHub starsUsed in 2 repos~4k tokens
    Data & AnalyticsAuto-check passed
  • Pod Sales

    ruvnet/ruflo

    Run one tick of the sales business-pod (ADR-164 §4.1, Phase 2).

    74k GitHub starsUsed in 1 repo~774 tokens
    DevelopmentAuto-check: notes
  • Sales Accounting

    sickn33/agentic-awesome-skills

    Sales register: customer, invoice, gross amount, discount, VAT and TDS, net receivable, credit terms and balance.

    47k GitHub starsUsed in 1 repo~6.4k tokens
    Business, Finance & HRAuto-check passed
  • Create Agent Adapter

    paperclipai/paperclip

    Create or modify Paperclip agent adapters across server, UI, and CLI surfaces.

    99k GitHub stars~8k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from kid-sid/claude-spellbook

All 52 skills in this repo
  • Accessibility

    kid-sid/claude-spellbook

    A skill your agent uses when building or reviewing UI components for keyboard and screen reader compatibility, adding ARIA to custom widgets, auditing a page for WCAG AA conformance, or preparing…

    189 GitHub stars~3.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Agentex

    kid-sid/claude-spellbook

    A skill your agent uses when building, wiring, or debugging an Agentex agent — choosing agent type, configuring acp.py and manifest.yaml, using adk.messages or adk.state, or resolving…

    189 GitHub stars~2.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • AI Engineer

    kid-sid/claude-spellbook

    A skill your agent uses when building production LLM applications — designing RAG pipelines, choosing vector databases, implementing agent orchestration, optimizing cost, or adding AI safety…

    189 GitHub stars~3.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Angular

    kid-sid/claude-spellbook

    A skill your agent uses when building or refactoring Angular applications — choosing between signals, RxJS, and NgRx for state, configuring routing with guards and lazy loading, optimizing change…

    189 GitHub stars~5k tokensUpdated 2 mo ago
    Auto-check passed
  • API Design

    kid-sid/claude-spellbook

    A skill your agent uses when designing new REST endpoints, reviewing an existing API contract, adding pagination or filtering, planning a versioning strategy, or building a public or partner-facing…

    189 GitHub stars~3.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Auth

    kid-sid/claude-spellbook

    A skill your agent uses when implementing login flows, issuing or validating JWTs, setting up OAuth2/OIDC with a provider, designing role-based or attribute-based access control, securing API…

    189 GitHub stars~3.2k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Promptbase

What does Promptbase do?

A skill your agent uses when writing, reviewing, or adapting a Claude Code skill for sale on PromptBase — checking scope, audience breadth, rejection risk, description quality, examples, and setup…. Promptbase is an agent skill from kid-sid/claude-spellbook. Use when writing, reviewing, or adapting a Claude Code skill for sale on PromptBase — checking scope, audience breadth, rejection risk, description quality, examples, and setup instructions.

When should I use Promptbase?

Promptbase fits situations like: adapting a Claude Code skill for sale on PromptBase — checking scope; audience breadth; description quality; setup instructions.

How do I install Promptbase in Claude Code?

Run `npx skills add kid-sid/claude-spellbook --skill promptbase -a claude-code`. Or copy the skill folder (skills/promptbase in kid-sid/claude-spellbook) into .claude/skills/promptbase in your project. Claude Code loads it when a task matches its description.

How do I install Promptbase in Codex?

Run `npx skills add kid-sid/claude-spellbook --skill promptbase -a codex`. Or copy the skill folder (skills/promptbase in kid-sid/claude-spellbook) into .agents/skills/promptbase in your project. Codex loads it when a task matches its description.

Can I use Promptbase 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 kid-sid/claude-spellbook --skill promptbase -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/promptbase, .gemini/skills/promptbase, .github/skills/promptbase and .opencode/skills/promptbase in your project.

What does Promptbase need to run?

Going by SKILL.md and its folder, Promptbase needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Promptbase 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 Promptbase 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 Promptbase use?

Promptbase 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 Promptbase use?

About 2.3k tokens (SKILL.md is roughly 9.3k 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 Promptbase?

Skills that share tags, products or a category with Promptbase: Sales Enablement (coreyhaines31/marketingskills, 54k stars), Sales (XiaomiMiMo/MiMo-Code, 14k stars), Agent Adaptive Coordinator (ruvnet/ruflo, 74k stars) and Pod Sales (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Promptbase?

kid-sid (a GitHub user) maintains it in kid-sid/claude-spellbook, which has 189 GitHub stars. The repository holds 52 skills in this directory. The repository was last updated on August 5, 2026.

Source: kid-sid/claude-spellbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.