skill-library-builder

skill-library-builder is a skill for Claude Code from randommonicle/claude-skills. It costs 141 tokens per session (2,430 once invoked), scanned A, original, Apache-2.0.

A project-specific collection of skills and engineering guidance built from a real repository. It captures experienced developers' practical knowledge so other developers or coding agents can work with the codebase more effectively.

In plain words
What is it for?
Use it to build, update, or audit a skill library or engineering playbook for a codebase. It is intended to record project conventions, decisions, and working practices.
Why use it?
Important project knowledge is often undocumented or known only by a few people. A shared skill library preserves that knowledge before it is lost.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the ash plugin — 43 skills, 3 hooks shipped together

Good fit Use it to build, update, or audit a skill library or engineering playbook for a codebase. It is intended to record project conventions, decisions, and working practices.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/randommonicle/claude-skills/skill-library-builder
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add randommonicle/claude-skills --skill skill-library-builder
Clone the repo
git clone --depth 1 https://github.com/randommonicle/claude-skills

Made for: Claude Code.

Or install ash, the plugin that ships this one along with the rest of its 43 skills, 3 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-library-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/randommonicle/claude-skills/skill-library-builder/github.svg)](https://agentmods.dev/skills/randommonicle/claude-skills/skill-library-builder)
Your own site
<a href="https://agentmods.dev/skills/randommonicle/claude-skills/skill-library-builder"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/skill-library-builder/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill-library-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/randommonicle/claude-skills/skill-library-builder"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/skill-library-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,430 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00141 $0.02430
Opus 5 $0.00071 $0.01215
Sonnet 5 $0.00028 $0.00486
Haiku 4.5 $0.00014 $0.00243

Measured 10d ago against content hash 4f33931c3c35, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

skill-library-builder scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Enumerates other installed skillslowAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

| Unslop scanners installed | `ls ~/.claude/skills \| grep unslop` | `unslop-text`, `unslop-code`, `unslop-ui` |

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skill-library-builder/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill library builder

Turn a repository into a project-specific skill library: what the system is, what must not break, how it is set up, run and tested, how it fails, how to prove a fix is real, and how to change it safely. The output is a set of focused runbooks under .claude/skills/, not generic documentation. Reject any skill that only restates the README.

This skill is the method behind the PropOS library (16 skills authored by Fable, reviewed by Sonnet and a domain reviewer, fixed by Opus, on 2026-07-02). The PropOS artefacts docs/PLAN_fable_skill_library.md and docs/FABLE_PROMPT_skill_library.md are a full worked instance of everything below.

When this applies

Load this when the task is to build or refresh a library of operating knowledge for a repository, especially before a knowledgeable engineer leaves, when onboarding, or when a codebase needs to be workable by a cheaper model. Do not load it to author one skill on a subject you already understand: write that directly. Do not load it to change product code: this is a read-and-author job.

Non-negotiables

  1. Discover before you author. No skill is written until its facts are verified against the repo.
  2. Write only under the skills root (.claude/skills/). The rest of the repo is read-only unless the user explicitly asks for code changes.
  3. Ground truth only. Verify every command, flag, path and claim against the repo before stating it. Do not invent commands, flags, paths, ownership, history or success claims. Label inference as inference.
  4. Verify provenance with git, not memory. Dates, PR and commit numbers, and "who added what when" are the claims most likely to be wrong. Confirm each with git log --follow <path> or git show <sha> before writing it. This is the single most common authoring error: the technical facts (function names, config keys, error codes) verify cleanly while the story of when and why a thing landed drifts, especially when two similar artefacts exist.
  5. Do not route around the project's change-control. Nothing you write may tell a reader to bypass the project's gates.
  6. Do not present candidate work as proven. Open, deferred or experimental items stay labelled open.
  7. Put volatile facts behind re-verification commands and date-stamp them.
  8. No mutating git and no side effects. Forbidden without explicit authorisation: reset, checkout, switch, clean, commit, push, pull, merge, rebase, publish, deploy, and any database or production write.

Read the full file on GitHub · 132 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 132 lines · 141 tokens per session scan A 4f33931c3c35

Subscribe to this mod's changes

skill-library-builder is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 3d ago), licensed Apache-2.0. It adds 141 tokens to every session and 2,430 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens