Agent
curator
Periodic consolidation pass — fold narrow agent-created skills into class-level umbrellas. Proposes intents only, never writes to…
@tigerless-labsInstall AgentClaude Code agents for Skill Authoring
Flowy lists 93 subagents for Skill Authoring, and the most-starred are curator (from the 10,512-star autoharness plugin), reflector (from the 10,512-star autoharness plugin) and gentle-ai-explore (from the 8,057-star gentle-ai plugin). The newest push among those Skill Authoring subagents, on October 28, 2026, went to the autoharness plugin.
curator @tigerless-labsInstall Agentreflector Agentreflector
Distill a finished episode into skill changes aligned with the existing library. Compare-first preference, generation stays open;…
@tigerless-labsInstall Agentgentle-ai-explore Agentgentle-ai-explore
You are the read-only explorer for generic ODD work.
@gentleman-programmingInstall Agentgentle-ai-verify Agentgentle-ai-verify
You are the read-only technical verifier for generic ODD work. Read-only means no edits to the repository or its git state.
@gentleman-programmingInstall Agentgentle-ai-worker Agentgentle-ai-worker
You are the package-owned implementation writer for Gentle AI.
@gentleman-programmingInstall Agentascii-ui-mockup-generator Agentascii-ui-mockup-genera…
Use this agent when you need to visualize UI concepts through ASCII mockups before implementation. Examples: <example>Context:…
@softaworksInstall Agentcodebase-pattern-finder Agentcodebase-pattern-finde…
codebase-pattern-finder is a useful subagent_type for finding similar implementations, usage examples, or existing patterns that…
@softaworksInstall Agentcommunication-excellence-coach Agentcommunication-excellen…
PROACTIVELY use when reviewing communication drafts or preparing difficult conversations. Provides email refinement, tone…
@softaworksInstall Agentskill-auditor Agentskill-auditor
Expert skill auditor for Claude Code Skills. Use when auditing, reviewing, or evaluating SKILL.md files for best practices…
@glittercowboyInstall Agentslash-command-auditor Agentslash-command-auditor
Expert slash command auditor for Claude Code slash commands. Use when auditing, reviewing, or evaluating slash command .md files…
@glittercowboyInstall Agentsubagent-auditor Agentsubagent-auditor
Expert subagent auditor for Claude Code subagents. Use when auditing, reviewing, or evaluating subagent configuration files for…
@glittercowboyInstall Agentcode-reviewer Agentcode-reviewer
Reviews code for quality, security, and convention compliance. Use when user asks to review, check, or verify code
@https-deeplearning-aiInstall Agenttest-generator-runner Agenttest-generator-runner
Runs tests and generates them if missing for commands or functions. Use when user asks to test, run tests, and/or verify code…
@https-deeplearning-aiInstall Agentcodebase-search Agentcodebase-search
Use this agent when the user needs to find files, locate code implementations, or discover where specific functionality exists in…
@jarrodwattsInstall Agentmedia-interpreter Agentmedia-interpreter
Use this agent when you need to extract or interpret information from media files that cannot be read as plain text. This…
@jarrodwattsInstall Agentopen-source-librarian Agentopen-source-librarian
Use this agent when the user needs to understand open-source libraries, find implementation details in codebases, locate specific…
@jarrodwattsInstall Agentanalyzer Agentanalyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
@marketingjuliancongdanh79-pixelInstall Agentcomparator Agentcomparator
Compare two outputs WITHOUT knowing which skill produced them.
@marketingjuliancongdanh79-pixelInstall Agentgrader Agentgrader
Evaluate expectations against an execution transcript and outputs.
@marketingjuliancongdanh79-pixelInstall Agentagent-creator Agentagent-creator
Use this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", or…
@fazxesInstall Agentagent-sdk-verifier-py Agentagent-sdk-verifier-py
Use this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation…
@fazxesInstall Agentagent-sdk-verifier-ts Agentagent-sdk-verifier-ts
Use this agent to verify that a TypeScript Agent SDK application is properly configured, follows SDK best practices and…
@fazxesInstall Agentaction Agentaction
Conditional action executor - performs actions only when specific conditions are met
@melvynxInstall Agentexplore-codebase Agentexplore-codebase
Use this agent whenever you need to explore the codebase to realize a feature.
@melvynxInstall Agentexplore-docs Agentexplore-docs
Use this agent to research library documentation and gather implementation context using Context7 MCP
@melvynxInstall Agentanalyzer Agentanalyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
@antongulinInstall Agentcomparator Agentgrader Agentarchitecture-advisor Agentarchitecture-advisor
System design and architecture specialist that combines skills across API design, databases, infrastructure, and observability.…
@randInstall Agentpolyglot-engineer Agentpolyglot-engineer
Multi-language expert specializing in Rust, Python, Zig, Go, TypeScript, and Swift. Use for cross-language projects, porting…
@randInstall Agentskill-creator Agentskill-creator
Generate spec-compliant skills for the cc-polymath library. Takes a topic/domain and produces a well-structured SKILL.md with…
@randInstall Agentanalyst Agentanalyst
Clean-context multi-perspective reviewer of an SDD feature's candidate approaches. Use during specify's ideation pass (hard…
@genkovichInstall Agentcritic Agentcritic
Clean-context coherence critic for SDD artifacts (a spec or a SAD). Use after a Socratic pass to detect cross-section drift,…
@genkovichInstall Agentdevils-advocate Agentdevils-advocate
Clean-context adversary for SDD. Three modes, selected by the dispatch prompt. (A) Ambiguity hunt over a written spec — used by…
@genkovichInstall Agentskill-forge-analyzer Agentskill-forge-analyzer
Benchmark analysis agent that surfaces patterns in eval results that aggregate stats might hide. Identifies failure clusters,…
@agricidanielInstall Agentskill-forge-architect Agentskill-forge-architect
Architecture design specialist for Claude Code skills. Analyzes use cases, determines complexity tier (1-4), plans file…
@agricidanielInstall Agentskill-forge-comparator Agentskill-forge-comparator
Blind comparison agent for A/B testing skill versions. Evaluates outputs from two skill versions without knowing which is "new"…
@agricidanielInstall Agentdecider Agentdecider
Haiku 5.5 decision sampler for the deciding-with-confidence skill. Answers one sample prompt from `decide.py emit --agent…
@oaustegardInstall Agentcode-reviewer Agentcode-reviewer
Reviews code for bugs, security, performance, and spec compliance. Run in fresh context without implementation bias.
@artemiimillierInstall Agentchecker Agentchecker
Cross-artifact consistency checker for NL programming artifacts. Checks reference integrity, detects orphans, finds behavioral…
scanner Agentscanner
Discover and classify all NL programming artifacts in a repository — the current directory or a given project path — with…
scorer Agentscorer
Scores NL programming artifacts on a 100-point scale using deterministic penalties. Use this agent when scoring plugin artifacts,…
skill-documenter Agentskill-documenter
Generates concise documentation for skills, focusing on usage examples and trigger phrases
@luongnv89Install Agentskill-packager Agentskill-reviewer Agentskill-reviewer
Reviews skill files for quality, best practices, and adherence to skill creation guidelines
@luongnv89Install Agentplanner Agentqa Agentqa
QA specialist that tests running web applications against acceptance criteria
@espennilsenInstall Agentreviewer Agent
Questions
What is the best Skill Authoring subagent for Claude Code?
By the GitHub stars of the plugin each ships in (Flowy does not rate quality), the best Skill Authoring subagent for Claude Code is curator (from the 10,512-star autoharness plugin), level on stars with reflector (from the 10,512-star autoharness plugin), ahead of gentle-ai-explore (from the 8,057-star gentle-ai plugin).
How many Skill Authoring subagents are there?
Flowy lists 93 subagents for Skill Authoring, and this page draws the top 48 Skill Authoring subagents.
Skill Authoring in other kinds
Other subagent categories
- Development5,722
- Agent Orchestration1,436
- AI & Agents809
- Automation687
- Security424
- Testing280
- Content233
- Marketing192
- Productivity191
- Monitoring143
- Writing128
- Product103
- Research91
- Design74
- Agent Workspaces72
- Data72
- Agent Memory67
- Documentation61
- Mobile59
- Business57
- Operations54
- Finance47
- Machine Learning41
- Education39
- Cloud & Infrastructure38
- Legal29
- MCP Servers25
- Code Generation22
- Code Review21
- Spec-Driven Development18
- Databases16
- Backend11
- SEO10
- Video & Audio10
- Debugging9
- Deployment9
- Frontend9
- Career8
- Data Science6
- Presentations6
- Sales6