skill-builder

A guide for creating, checking, and improving agent skills, which are reusable instruction packages for coding agents. It covers their structure, required knowledge, triggers, supporting files, and tests.

In plain words
What is it for?
Use it to design or refine SKILL.md files, reference materials, prompts, validation checks, and realistic usage tests.
Why use it?
It helps turn an idea into a focused skill with clear activation rules and a consistent layout, while catching naming, formatting, and design problems.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/existential-birds/beagle/skill-builder
Any agent
npx skills add existential-birds/beagle --skill skill-builder
Clone the repo
git clone --depth 1 https://github.com/existential-birds/beagle

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 490 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.00490
Opus 5 $0.00016 $0.00245
Sonnet 5 $0.00006 $0.00098
Haiku 4.5 $0.00003 $0.00049

Measured 3d ago against content hash 03c3c47d21f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-builder scanned grade A with 0 findings 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 3d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/beagle-core/skills/skill-builder/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Builder

Create, validate, and refine Agent Skills.

Quick Start

  1. Gather the capability, triggers, and required domain knowledge.
  2. Choose a simple single-file skill or a multi-file skill with references.
  3. Write SKILL.md with concise, trigger-focused instructions.
  4. Add reference files only for detail that would otherwise bloat SKILL.md.
  5. Validate YAML frontmatter, file layout, and naming.
  6. Test the skill with the natural language users are likely to say.

Workflow

  • Start with requirements and scope control.
  • Design the structure before writing content.
  • Keep descriptions in third person and include trigger keywords.
  • Use progressive disclosure for long examples, templates, and validation details.

Gates

Follow in order. Pass means a check you can satisfy with concrete artifacts (written bullets, paths, line counts, parsed YAML)—not an internal sense of “done.”

  1. RequirementsPass: Capability, triggers, and any required domain knowledge (or explicit “none”) are written down or confirmed from the user.
  2. StructurePass: Single-file vs SKILL.md + references/ is chosen; heavy detail lives in references, not inlined in SKILL.md.
  3. DraftPass: Frontmatter is valid YAML with name and description; SKILL.md is ≤ 500 lines; every relative link from SKILL.md resolves to a path that exists under this skill directory; each allowed-tools entry (if present) is justified.
  4. Trigger checkPass: At least one natural-language user phrase plausibly matching the description is identified for a quick invocation test.

Validation

  • Keep SKILL.md under 500 lines.
  • Prefer one-level reference links.
  • Avoid time-sensitive guidance.
  • Confirm frontmatter is valid YAML.
  • Check that any allowed-tools entries are necessary and correct.

Advanced Reference

For the full workflow, templates, examples, and validation checklist, see references/skill-builder-guide.md.

Read the full file on GitHub · 47 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. 3d ago First seen · 47 lines · 32 tokens per session scan A 03c3c47d21f0

Subscribe to this mod's changes

skill-builder is a skill published in the GitHub repository existential-birds/beagle (79 stars, last pushed 23d ago), licensed Apache-2.0. It adds 32 tokens to every session and 490 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens