By swell-agents
Eleven engineering skills + five parallel-review agents + seven slash commands for Claude Code.
Implement one PR-stack block from Spec Kit `tasks.md` end-to-end — TDD-strict subagent, five-pass review, language-appropriate gates, push, PR, CI fix loop. Use on a Spec Kit project; pass the block name verbatim or `next` to pick the next ready block.
Create one "Implement Block X" GitHub issue per Spec Kit tasks.md PR-stack block, with a minimal body pointing at tasks.md as the source of truth.
Append the engineering-skills block to existing instruction files (CLAUDE.md / .cursorrules).
Commit + PR via committing-changes skill (hooks, lint, gh pr create).
Design architecture for $ARGUMENTS (wraps designing-architecture skill).
Acceptance pass — does the diff solve the linked issue / PR / Spec Kit Block?
AI-native-coding practices pass — R1..R8 rubric (comments, AGENTS.md, mocks, ADRs).
Architecture pass — architecture map, SOLID, layer boundaries, library reuse.
Code-quality review pass — KISS/YAGNI/DRY, SOLID, lint, test coverage. Read-only.
Security audit pass — OWASP Top 10 + dep-CVE scanners + Solidity-specific checks.
Commit via feature branch + PR + git hooks; never push main, never merge.
Generate one "Implement Block X" GitHub issue per Spec Kit tasks.md PR-stack block, with a minimal body pointing at tasks.md as the source of truth.
Design pre-implementation architecture: components, libraries, data flow, schema.
Apply KISS, YAGNI, DRY, SOLID, fail-fast, be-brief on every code decision.
Apply Go conventions — 1.25.x, vendored, golangci-lint v2, race-detector tests.
Uses power tools
Uses Bash, Write, or Edit tools
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.
Canonical Anthropic Agent Skills for software engineering — packaged in a portable, harness-agnostic format.
Each skill is a self-contained folder with SKILL.md (frontmatter + body), optional scripts/, and optional reference/. Skills are consumable by Claude Code, SkillNet, Cursor 2.0 (via MDC frontmatter), OpenAI Codex Skills, and the Microsoft Agent Framework with no transformation.
Claude Code consumers also get parallel-friendly agents under agents/ (e.g. @code-reviewer, @security-auditor, @architect-review) and slash commands under commands/ (e.g. /coding-skills:review, /coding-skills:tdd, /coding-skills:commit) that wrap the skills — same source of truth, richer harness ergonomics. Other harnesses ignore the agents/ and commands/ directories.
See INDEX.md for the full list. Two kinds:
running-tdd-cycles, reviewing-changes, designing-architecture, creating-block-issues (Spec Kit projects — one issue per tasks.md PR-stack block), committing-changes (also installs an optional PR-size CI gate that fails PRs over 1000 changed lines, excluding tests/docs/lockfiles/generated), implementing-blocks (Spec Kit projects — one PR-stack block end-to-end).python-conventions, go-conventions, solidity-conventions, shell-discipline, engineering-philosophy.Workflow skills cross-reference rule skills; agents activate the rule skill alongside the workflow skill when the file or language matches.
Every SKILL.md uses a hybrid of Anthropic Skills (required) + Cursor MDC (optional, for auto-activation in Cursor):
---
# Anthropic Skills
name: python-conventions
description: Apply Python project conventions ... Use when writing or reviewing Python code ...
allowed-tools: Read, Bash(uv *), Bash(uv run ruff *), ...
# Cursor MDC (ignored by Anthropic, used by Cursor)
globs: "**/*.py"
paths: "**/*.py"
---
Fields explicitly excluded from canonical SKILL.md frontmatter:
model: — Claude-Code-only; original agent model class is preserved as a one-line header in reference/<agent>.md.Inside any Claude Code session:
/plugin marketplace add swell-agents/coding-skills
/plugin install coding-skills@swell-agents
Then /reload-plugins. All 11 skills become available (auto-activated by description), plus 3 parallel-review agents and 7 slash commands:
| Slash command | Wraps |
|---|---|
/coding-skills:review [scope] | Three @code-reviewer + @security-auditor + @architect-review agents in parallel; aggregates into one Quality Gate Summary |
/coding-skills:commit [scope] | committing-changes skill |
/coding-skills:tdd [requirement|phase] | running-tdd-cycles skill |
/coding-skills:block-issues [feature|--dry-run|--label <name>|--no-label] | creating-block-issues skill — one "Implement Block X" GitHub issue per Spec Kit tasks.md PR-stack block (minimal body, dispatch label swa-impl-block) |
/coding-skills:design [topic] | designing-architecture skill |
/coding-skills:block-implement [block|next] | implementing-blocks skill — one Spec Kit PR-stack block end-to-end (TDD + review + PR + CI fix loop) |
/coding-skills:bootstrap | One-shot wiring: append engineering-skills block to existing CLAUDE.md / .cursorrules. Patch-only — never creates files; never touches AGENTS.md. |
Clone the repo and symlink individual skills into ~/.claude/skills/.
skillnet download https://github.com/swell-agents/coding-skills/tree/main/skills/<skill-name>
Add the repo path to your project's MDC source roots; the globs: / paths: frontmatter drives auto-activation.
Skills are description-matched at retrieval; that is good enough for most cases but not guaranteed. When a project should always apply the engineering principles — not just when the matcher fires — patch the project's instruction file once:
In Claude Code:
/coding-skills:bootstrap
In any other harness:
bash ~/.claude/plugins/swell-agents/coding-skills/scripts/bootstrap.sh
# or, after `git clone`:
bash scripts/bootstrap.sh
The script is patch-only. It never creates instruction files; it only appends the engineering-skills block to ones that already exist.
npx claudepluginhub swell-agents/coding-skills --plugin coding-skillsMulti-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.