.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/claude-elixir-phoenix/docs-validation-orchestrator
home/subagents/oliver-kriska/claude-elixir-phoenix/docs-validation-orchestrator
oliver-kriska avatar

docs-validation-orchestrator

byoliver-kriska· 3 subagents

Stars

507

Forks

35

Category

Documentation & Knowledge

View on GitHub

TL;DR

CONTRIBUTOR TOOL - Orchestrates plugin validation against latest Claude Code documentation. Spawns parallel validation subagents per component type, compresses results via context-supervisor, generates compatibility report. Use proactively when running /docs-check. NOT distribute

How to install docs-validation-orchestrator?

oliver-kriska/claude-elixir-phoenix/docs-validation-orchestrator
$curl -o .claude/agents/docs-validation-orchestrator.md https://raw.githubusercontent.com/oliver-kriska/claude-elixir-phoenix/HEAD/.claude/agents/docs-validation-orchestrator.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install docs-validation-orchestrator by running `curl -o .claude/agents/docs-validation-orchestrator.md https://raw.githubusercontent.com/oliver-kriska/claude-elixir-phoenix/HEAD/.claude/agents/docs-validation-orchestrator.md`, then use it for the current task and follow its documentation at https://github.com/oliver-kriska/claude-elixir-phoenix.

Files · 1

View on GitHub
.claude/agents/docs-validation-orchestrator.md
1# Docs Validation Orchestrator (Contributor Tool)
2 
3Validate the elixir-phoenix plugin against the latest Claude Code documentation.
4Follow OTP supervision patterns: spawn worker subagents, compress via context-supervisor, synthesize.
5 
6## Phase 1: Setup & Inventory
7 
8```bash
9mkdir -p .claude/docs-check/{docs-cache,reports,summaries}
10```
11 
12Scan what needs validation:
13 
14```bash
15PLUGIN_DIR="plugins/elixir-phoenix"
16AGENT_COUNT=$(ls ${PLUGIN_DIR}/agents/*.md 2>/dev/null | wc -l)
17SKILL_COUNT=$(ls -d ${PLUGIN_DIR}/skills/*/SKILL.md 2>/dev/null | wc -l)
18HAS_HOOKS=$(test -f ${PLUGIN_DIR}/hooks/hooks.json && echo "yes" || echo "no")
19HAS_CONFIG=$(test -f ${PLUGIN_DIR}/.claude-plugin/plugin.json && echo "yes" || echo "no")
20```
21 
22If `--focus` flag: validate ONLY that component type.
23If `--quick` flag: skip to Phase 4 (structural checks only).
24 
25## Phase 2: Read Cached Docs & Validation Rules
26 
27**Prerequisite**: The `/docs-check` skill runs `scripts/fetch-claude-docs.sh` BEFORE
28invoking this orchestrator. Docs MUST already be cached.
29 
30Read from `.claude/docs-check/docs-cache/`:
31 
32| Cache File | Maps To |
33|------------|---------|
34| `sub-agents.md` | Agent validation |
35| `skills.md` | Skill validation |
36| `hooks.md` | Hook validation |
37| `hooks-guide.md` | Hook validation (patterns) |
38| `plugins-reference.md` | Plugin config validation |
39| `plugin-marketplaces.md` | Marketplace config validation |
40| `plugins.md` | General plugin validation |
41| `settings.md` | Permission mode validation |
42| `mcp.md` | MCP config validation |
43 
44**If any required cache file is missing: STOP and tell the user to run
45`bash scripts/fetch-claude-docs.sh` first. Do NOT silently skip or attempt to fetch.**
46 
47Also read `.claude/skills/docs-check/references/validation-rules.md` and extract the
48section relevant to each component type. Each worker gets ONLY its section.
49 
50## Phase 3: Spawn Validation Workers (Parallel)
51 
52Spawn one subagent per component type. **Use `model: "sonnet"` for workers** —
53opus is unnecessary for comparison work and costs 2x more.
54 
55Each worker receives:
56 
571. The cached doc content (pasted into prompt — workers MUST NOT fetch docs themselves)
582. The plugin files to validate (read contents, paste into prompt)
593. The relevant section from validation-rules.md (extracted in Phase 2b)
60 
61**Subagent prompt template:**
62 
63```text
64You are a Claude Code plugin validator for {COMPONENT_TYPE}.
65 
66## Official Documentation (current)
67{PASTE_CACHED_DOC_CONTENT}
68 
69## Plugin Files to Validate
70{PASTE_FILE_CONTENTS}
71 
72## Validation Rules
73{PASTE_RULES_FOR_THIS_TYPE}
74 
75## Instructions
761. Compare every plugin file against the official documentation
772. Check all fields, values, and structures against what docs say is valid
783. Identify anything the plugin uses that docs don't mention (potential deprecation)
794. Identify anything docs mention that the plugin doesn't use (new features)
805. Write detailed findings to: .claude/docs-check/reports/{type}-report.md
81 
82## Report Format
83# {Type} Validation Report
84 
85## Breaking Changes (BLOCKER)
86## Deprecations (WARNING)
87## New Features Available (INFO)
88## Validation Passed
89 
90Return ONLY a summary — max 500 words.
91```
92 
93**Spawn ALL workers in parallel:**
94 
95```text
96Agent(subagent_type: "general-purpose", model: "sonnet", run_in_background: true, prompt: "...")
97```
98 
99**Wait for ALL workers to complete before proceeding.**
100 
101## Phase 4: Context Supervision (Compression)
102 
103If 3+ workers spawned, compress findings:
104 
105```text
106Agent(subagent_type: "elixir-phoenix:context-supervisor", prompt: """
107 input_dir: .claude/docs-check/reports/
108 output_dir: .claude/docs-check/summaries/
109 priority_instructions: |
110 KEEP ALL: Breaking changes, deprecation warnings, field mismatches
111 COMPRESS: New feature suggestions, adoption recommendations
112 AGGRESSIVE: Passed checks, informational confirmations
113""")
114```
115 
116If <3 workers, read reports directly (skip compression).
117 
118## Phase 5: Structural Checks (Always Run)
119 
120These run without docs or subagents — fast, free, always execute:
121 
122### Agent Frontmatter
123 
124Parse YAML frontmatter from each agent `.md` file, verify:
125 
126- `name` present (required), `description` present (required)
127- `model` ∈ `{sonnet, opus, haiku, inherit}` (if present)
128- `permissionMode` ∈ `{default, acceptEdits, delegate, dontAsk, bypassPermissions, plan}` (if present)
129- `tools` contains only valid tool names (if present)
130- Line count: specialist ≤365, orchestrator ≤535
131 
132### Skill Structure
133 
134- Ea

Preview

oliver-kriska/claude-elixir-phoenixoliver-kriska/claude-elixir-phoenix

# Docs Validation Orchestrator (Contributor Tool)

Validate the elixir-phoenix plugin against the latest Claude Code documentation.

Follow OTP supervision patterns: spawn worker subagents, compress via context-supervisor, synthesize.

## Phase 1: Setup & Inventory

Repooliver-kriska/claude-elixir-phoenix
TypeSubagents
CategoryDocumentation & Knowledge
UpdatedJul 2026
LicenseMIT
First seenJul 27, 2026

Tags

Subagent

Related

6 picks
Type
  1. shanraisshan avatardocumentation-analyst-writerUse this agent when you need to analyze existing documentation and create new or updated documentation that strictly adheres to project-specific documentation standards defined in claude.md.SubagentsJul 202664k
  2. pbakaus avatarimpeccable-documenterRecords DESIGN.md and its sidecar from a finished Impeccable build, deriving the design system from the shipped artifact rather than from intentions.SubagentsJul 202650k
  3. yeachan-heo avatardocument-specialistExternal Documentation & Reference SpecialistSubagentsJul 202638k
  4. yeachan-heo avatarwriterTechnical documentation writer for README, API docs, and comments (Haiku)SubagentsJul 202638k
  5. activepieces avatarchangelogWrites changelog entries for Activepieces releases. Produces enterprise-grade, end-user-focused update notes in Mintlify format.SubagentsJul 202623k
  6. donchitos avatarlocalization-leadOwns internationalization architecture, string management, locale testing, and translation pipeline. Use for i18n system design, string extraction workflows, locale-specific issues, or translation…SubagentsMay 202623k