Niekcandaele Claude Helpers
niekcandaele-claude-helpers is a Claude Code plugin pack for the Ship phase that adds four specialized agents and commands for rigorous review, investigation, and coaching sessions.
by niekcandaele · github.com/niekcandaele/claude-helpers
Install four specialized Claude Code agents and commands for adversarial review, root-cause investigation, coaching, and curated evidence gathering during hard problems.
Add it to Claude Code
Install the plugin in Claude Code. One command, paste-ready.
/plugin install niekcandaele-claude-helpers@niekcandaele/claude-helpersBuilt to be called by your agent
Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.
Retrieve this entry with skillselion.get_details("plugin:niekcandaele/claude-helpers") and the paste-ready config with skillselion.get_install_config("plugin:niekcandaele/claude-helpers").
What it does
niekcandaele-claude-helpers is a compact Claude Code plugin pack offering specialized agents and commands for software builders who want structured investigation, adversarial review, and coaching inside the terminal agent. Solo developers hitting subtle bugs, contentious design choices, or talk-prep depth can invoke helper modes that gather evidence, challenge assumptions, and iterate until an outcome is explicitly approved—matching a Ship-phase review mindset while still helping during Build debugging and Operate incident postmortems. The repo advertises four plugins and vocabulary around CATA-style cause analysis, player-coach dynamics, and curated technical content. It is an agent command bundle, not a single automation for one API. Expect intermediate familiarity with Claude Code sessions and willingness to run multi-step helper workflows instead of fast codegen-only prompts.
Highlights
- 4 specialized Claude Code plugins: agents plus commands for disciplined workflows
- Adversarial critic and investigator patterns with evidence gathering and root-cause focus
- Coach-oriented sessions for structured cooperation until conclusions are approved
- Curator-style filtering and depth for conference or KubeCon-scale technical narratives
- Iterates with rigor rather than one-shot answers—verify and review loops
Why builders use it
Agent-assisted debugging and design reviews often stay shallow—without adversarial critique, evidence trails, or structured iteration until you trust the conclusion.
You gain reusable helper agents that run deeper reviews and investigations in Claude Code until findings are evidence-backed and explicitly approved.
At a glance
- Type - Plugin in Development Tools.
- Adoption - 0 installs, 5 stars, 0 votes.
FAQ
Who is niekcandaele-claude-helpers for?
It is for Claude Code users—often senior-ish solo devs—who want helper agents for critique, investigation, curation, and coaching on complex software work.
When should I use niekcandaele-claude-helpers?
Use it when you are stuck on root cause, need adversarial review before merge or release, or are preparing deep technical narratives—not for boilerplate scaffolding.
How do I add niekcandaele-claude-helpers to my agent?
Add the niekcandaele/claude-helpers plugin source in Claude Code, then invoke the bundled commands and specialized agents per each helper’s documentation.
Comments
Share how you use niekcandaele-claude-helpers, gotchas, or tips for other indie builders.
No comments yet - be the first to share how you use it.