By akyachtsman
Operational commands, auto-skills, QA/data agents, and guard hooks from the claude.directives company standard. Version is intentionally omitted: updates track this repo's main via git SHA.
Audit current repo for drift between directive files and actual code, a full recursive code-correctness sweep, and structural soundness — always weighing whether re-organizing files would make the layout clearer and more error-proof
Lock answers to Chromebook browser-only constraints
Manual backup trigger for the pre-push verification directive (run tests, lint, CI checks before committing)
Run a command against any public GitHub repo via gh api — inspect, compare, or audit without cloning
Full environment readiness check — session context, git health, CI status, validation gates, directive freshness, a connectors/tools inventory, and the scope.chk repo-scope verification
Independent code quality reviewer for changed files. Use before PR or merge to assess maintainability, architecture, readability, tests, and implementation risk. This agent must not rewrite code unless explicitly asked.
Final PR readiness gate. Use after implementation, verification, review, and fixes to confirm tests, lint/build, required reports, unresolved issues, and CI readiness before opening or merging a PR.
Runs the full QA pipeline in sequence — test-verifier, ui-tester, code-reviewer, security-reviewer (if relevant), and pr-readiness-reviewer. Orchestrates a feedback loop with ui-tester until all UI scenarios pass or human escalation is required.
Security-focused reviewer for code changes. Use for features touching auth, user input, data access, file handling, secrets, dependencies, infrastructure, or sensitive data. This agent must not modify code unless explicitly asked.
Focused Supabase specialist. Use to apply schema migrations via Supabase MCP, query tables and verify row counts, inspect RLS policies, run the project's scheduled data script manually, and validate that Supabase secrets/variables are correctly configured. Follows the data directive — RLS always on, service-role key server-side only.
Use whenever asked to compare two documents: produce a self-contained side-by-side HTML diff (strikethrough deletions, red-underline additions, margin notes only for substantive changes).
Use BEFORE discussing, offering, or promising work on any repository other than the one this session is scoped to. Verifies the session's TRUE repo scope (GitHub MCP scope, add_repo/list_repos availability) so cross-repo access is never overclaimed.
Standard procedure for ANY change that updates a GitHub Pages site. Use AUTOMATICALLY whenever an edit touches a Pages-served file (root index.html, docs/*.html, served CSS/assets) or Pages config: run gates, push, watch the deploy to a terminal state, and report live/stuck/failed proactively.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
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.
Uses power tools
Uses power tools
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
Consolidated home for the company-wide Claude Code agent directives.
The exported, downstream-imported directives live in directives/:
directives/global.md — global agent behavior standarddirectives/design.md — UI design systemdirectives/test.md — test / QA directivedirectives/data.md — data / backend directive (backend provider, keys, RLS, MCP config)Repo-internal operating instructions are in CLAUDE.md, and project bootstrap
lives in NEW-REPO-USER-INSTRUCTIONS.md. Supporting directories:
.claude/skills/ — personal skills, invoked by typing the skill name (type
my.list for the menu); bootstrapped fresh from this repo each session.claude/agents/ — agent definitions in purpose-based subfolders (qa/, data/)docs/ — reference material, including the rendered design system reference at
docs/design-system.htmltemplates/ — installable workflows, agents, and the Playwright test kitLive demos: https://akyachtsman.github.io/claude.directives/ — rendered UI references, including the design system reference.
npx claudepluginhub akyachtsman/claude.directives --plugin directives-toolkitComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.