Analyze PR changes and comments, create a plan, and implement feedback
Upload HTML docs to the team's GitHub Pages archive for permanent browsing and sharing. Use when the user says "archive this", "upload to archive", or /archive.
Explore requirements and approaches through collaborative dialogue before planning
Simplify and refine recently modified code for clarity and maintainability while preserving behavior. Use for requests like "simplify this", "clean this up", "reduce complexity", or readability-focused refactors.
Document a recently solved problem to compound your knowledge
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code skills for the Ardent team.
From inside Claude Code, run:
/plugin marketplace add ardent-ai/ardent-claude-plugins
/plugin install ardent@ardent
To update after changes:
/plugin marketplace update ardent
Or add to your project's .claude/settings.json for automatic setup:
{
"extraKnownMarketplaces": {
"ardent": {
"source": { "source": "github", "repo": "ardent-ai/ardent-claude-plugins" }
}
},
"enabledPlugins": {
"ardent@ardent": true
}
}
Skills show up as /<skill-name> with (ardent) label in the autocomplete.
| Skill | Command | Description |
|---|---|---|
| brainstorm | /brainstorm | Explore requirements and approaches through collaborative dialogue |
| shaping | /shaping | Shape Up methodology for ambiguous features |
| plan-ardent | /plan-ardent | Transform feature descriptions into structured plans |
| deepen-plan | /deepen-plan | Enhance plans with parallel research agents |
| design-review | /design-review | Validate high-level design before building |
| document-review | /document-review | Structured review rubric for plans and docs |
| Skill | Command | Description |
|---|---|---|
| work | /work | Execute work plans with quality gates |
| lfg | /lfg | Full autonomous pipeline: plan, deepen, build, review, fix |
| tdd | /tdd | Test-driven development with red-green-refactor |
| rethink | /rethink | Redesign a system area from first principles |
| Skill | Command | Description |
|---|---|---|
| review-ardent | /review-ardent | Adaptive code review, scales from single-pass to 9-agent swarm |
| security-scan | /security-scan | STRIDE-based security analysis |
| cleanup | /cleanup | Simplify code for clarity and maintainability |
| address_pr_feedback | /address_pr_feedback | Analyze and implement PR review feedback |
| Skill | Command | Description |
|---|---|---|
| fixup | /fixup | Fold fixes into the correct earlier commits |
| split-commits | /split-commits | Clean up commit history into atomic commits |
| pr | /pr | Create a PR end-to-end: description, humanize, link Linear issues |
| Skill | Command | Description |
|---|---|---|
| compound | /compound | Document a solved problem as a searchable solution |
| pick-up | /pick-up | Morning briefing from the most recent wrap-up |
| wrap-up | /wrap-up | End-of-day summary of all in-flight work |
| Skill | Command | Description |
|---|---|---|
| humanizer | /humanizer | Remove AI writing patterns from text |
| visual-explainer | /visual-explainer | Generate self-contained HTML technical diagrams |
| Skill | Command | Description |
|---|---|---|
| archive | /archive | Upload HTML docs to the team's GitHub Pages archive |
| webcomic | /webcomic | Generate a webcomic page from a feature or diff |
Several skills (planning, review, compound, wrap-up) write documents to .untracked/ in the project root. Make sure .untracked/ is in your .gitignore.
npx claudepluginhub ardent-ai/ardent-claude-plugins --plugin ardentDevelopment toolkit for Claude Code — plan, implement, ship, review, and assess features with AI-assisted workflows. Progressive zero-config init: auto-configures with sensible defaults on first skill invocation, no upfront ceremony required. Three-tier ceremony model: swift (lightweight), standard (mid-ceremony spec-plan-execute), and thorough (full pipeline) with severity-aware scope routing. Five entry points: arn-planning (scope router, spec, plan), arn-implementing (execute plans, swift, or standard changes), arn-shipping (commit, push, PR), arn-reviewing-pr (PR feedback), arn-assessing (codebase health). Includes arn-code-sketch for UI preview, arn-code-swift for quick implementations, and arn-code-standard for mid-ceremony changes. Includes arn-code-catch-up for retroactive documentation of out-of-pipeline commits. Pipeline preference persistence for streamlined repeat sessions. Batch pipeline: arn-code-batch-planning (multi-feature planning), arn-code-batch-implement (parallel worktree execution), arn-code-batch-merge (conflict-aware merge), arn-code-batch-simplify (cross-feature quality).
Focused agentic engineering workflow: design-doc, spec, plan, implement, tdd, refactor, review, address-pr-feedback, browser-verify, explain-visually, compress, branch, and commit.
5つの専門エージェント(コード調査・依存分析・パターン分析・ソリューション設計・計画書作成)がチームでコードベースを調査・議論・合意形成し、Plan Modeで実装計画を作成する。調査エージェントはExploreサブエージェントを無制限に並列起動可能
Helder's personal SDLC toolbelt for AI coding agents — from PRD to ship. Bundles the tracer-bullet workflow alongside TDD, code review, audits, and shipping skills.
Implementation planning, execution, and PR creation workflows with multi-agent collaboration
No description provided.