[H1][AGENT-BUILDER]

SkillFiles & storage

Creates Claude Code agent files (.claude/agents/*.md) with YAML frontmatter, tool permissions, and system prompts. Use when building new agents, configuring agent frontmatter, writing agent system prompts, or setting agent tool permissions.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the [H1][AGENT-BUILDER] skill

What this skill tells your AI

The instructions your AI receives, as published by majiayu000/claude-skill-registry in skills/agent/agent-builder-bsamiee-parametric-portal/SKILL.md and read by ahel’s review.

Dictum: Structured frontmatter and scoped tools enable discoverable agents.

Specialized execution contexts for Claude Code subagent delegation. Frontmatter controls discovery and capabilities; markdown body encodes behavior.

Location: .claude/agents/ (project) or ~/.claude/agents/ (user). Higher priority wins: CLI flag > project > user > plugin.

Tasks:

  1. Read index.md — Reference file listing for navigation.
  2. Read frontmatter.md — Complete schema (11 fields), triggers, syntax.
  3. Read prompt.md — Structure patterns, constraint markers.
  4. Read workflow.md — 5-phase creation process.
  5. (prose) Load style-standards skill — Voice, formatting, constraints.
  6. Execute per workflow — UNDERSTAND, ACQUIRE, RESEARCH, AUTHOR, VALIDATE.
  7. Validate — Quality gate; see §VALIDATION.

Templates: →agent.template.md — Standard agent scaffold.

[REFERENCE]: index.md — Complete reference file listing.


[1][FRONTMATTER]

Dictum: Metadata enables discovery before load.

---
name: agent-name
description: >-
  Capability statement. Use when scenario-1, scenario-2, or scenario-3.
tools: Read, Glob, Grep
model: sonnet
skills:
  - style-standards
memory: user
---
[INDEX][FIELD][TYPE][REQ][CONSTRAINT]
[1]namestringYesKebab-case, max 64 chars, match filename
[2]descriptionstringYesThird person, active voice, "Use when" clause
[3]toolslistNoComma-separated allowlist; omit = inherit all
[4]disallowedToolslistNoDenylist; removed from inherited/allowed tools
[5]modelenumNohaiku, sonnet, opus, inherit
[6]permissionModeenumNodefault, acceptEdits, delegate, dontAsk, bypassPermissions, plan
[7]maxTurnsnumberNoMaximum agentic turns before subagent stops
[8]skillslistNoFull skill content preloaded at startup
[9]mcpServersobjectNoMCP servers available to this subagent
[10]hooksobjectNoScoped lifecycle hooks (all 14 events supported)
[11]memoryenumNouser, project, or local persistent scope

[IMPORTANT] Agent background color set interactively via /agents UI — not frontmatter field.


[2][DISCOVERY]

Dictum: Description quality determines invocation accuracy.

Reasoning matches description directly — no embeddings, no keyword matching.

[INDEX][PATTERN][EXAMPLE][MECHANISM]
[1]"Use when" clauseUse when building MCP serversDirect activation signal
[2]Proactive triggerUse proactively after code changesEncourages auto-invocation
[3]Imperative emphasisMUST BE USED before committingStrong delegation signal
[4]Enumerated list(1) creating, (2) modifyingParallel pattern matching
[5]Technology embedPython (FastMCP) or TypeScriptFramework-specific match

[CRITICAL]:

  • [NEVER] Hedging words: might, could, should, probably.
  • [ALWAYS] Include "Use when" clause — 3+ trigger scenarios.
  • [ALWAYS] Third person, active voice, present tense.

[3][TOOLS]

Dictum: Tool declarations scope permissions.

[INDEX][PATTERN][TOOLS][USE_CASE]
[1]Read-onlyRead, Glob, GrepAnalysis, review
[2]Write-capableRead, Edit, Write, Glob, BashImplementation
[3]OrchestrationTask(worker, researcher), ReadAgent dispatch
[4]Full access(omit field)Inherits all tools

Task restriction: Task(agent_type) limits spawnable subagent types (main thread only). Denylist: disallowedTools: Write, Edit removes tools from inherited or allowed set.


[4][MODELS]

Dictum: Model selection balances capability against latency and cost.

[INDEX][MODEL][STRENGTH][LATENCY][COST]
[1]opusComplex reasoningHighHigh
[2]sonnetBalanced performanceMediumMedium
[3]haikuFast, simple tasksLowLow
[4]inheritMatch main conversationSessionSession

[5][SYSTEM_PROMPT]

Dictum: Structured prompts constrain execution.

Markdown body follows frontmatter. Body encodes agent behavior; structure determines effectiveness. Subagents receive only this system prompt (plus environment details), NOT full Claude Code system prompt.


[6][NAMING]

Dictum: Naming conventions enable discovery.

[INDEX][PATTERN][EXAMPLE][USE_CASE]
[1]Role-basedcode-reviewerSpecialized function
[2]Action-basedgenerating-commitsGerund form preferred
[3]Domain-specificreact-specialistTechnology expertise

[CRITICAL]:

  • [NEVER] Generic names: helper, processor, agent.
  • [ALWAYS] Kebab-case — lowercase, hyphens only. Filename matches name field.

[7][VALIDATION]

Dictum: Validation gates prevent incomplete artifacts.

[VERIFY] Completion:

  • Workflow: All 5 phases executed (UNDERSTAND → VALIDATE).
  • Frontmatter: Valid YAML, description with "Use when" clause.
  • Tools: Matches type gate (readonly|write|orchestrator|full).
  • Prompt: Role line + H2 sections + constraint markers.
  • Quality: Kebab-case naming, filename matches name field.

[REFERENCE] Operational checklist: →validation.md.

Signals

GitHub stars
603
Forks
94
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
agent-builder-2
Source
github.com/majiayu000/claude-skill-registry