anthril
OrganizationA curated collection of reusable AI skills, prompts, and agent configurations. Portable across AI coding assistants and agent frameworks.
Categories
Indexed Skills (49)
plan-completion-audit
Audit a project plan against the actual implementation — verifying code, types, security, and Supabase backend alignment.
skill-creator
Create, review, rebuild, validate, and package Claude Code skills or plugins. Use when the user asks to make a skill, improve an existing skill, convert a workflow into a skill, design a plugin, scaffold plugin agents/hooks/MCP/LSP integrations, or prepare an uploadable Claude extension.
business-data-model-designer
Design complete Supabase/PostgreSQL data models with ERD, SQL migrations, RLS policies, indexes, and triggers for business applications
erd-generator
Generate an ERD as Mermaid + DBML from domain narrative or live Supabase schema, with cardinality, optionality, FKs, and a notation legend.
index-strategy-planner
Index recommendations from query patterns, EXPLAIN ANALYZE excerpts, and table sizes. Includes partial / covering / GIN / BRIN guidance for Postgres / Supabase.
migration-plan-builder
Staged migration plan (additive → backfill → dual-write → cutover → cleanup) for Postgres / Supabase, with rollback gates, observability checkpoints, and db-reviewer agent review.
postgres-schema-audit
Audit any Postgres schema (Supabase via MCP or any Postgres 13+ via read-only connection) for structural and relational design quality. Produces a markdown report, ER diagram, JSON sidecar, and draft migrations-suggested.sql. Use for database design, schema audit, FK/constraint/trigger/RPC review, or pre-migration cleanup.
rls-policy-designer
Generate a Supabase Row-Level-Security policy bundle from an access-model description. Outputs SQL + test queries + admin-impersonation patterns.
supabase-schema-bootstrap
Bootstrap a complete Supabase schema from a domain spec — tables, RLS, triggers, indexes, seeds, type generation. Wraps erd / rls / index skills for new-project setup.
cicd-pipeline-audit
Audit CI/CD pipelines (GitHub Actions, GitLab CI, CircleCI, Azure Pipelines, Jenkins, Bitbucket) for security, reliability, reproducibility, supply chain, and deploy safety. One sub-agent per workflow. Static, live, apply, and runtime modes.
container-audit
Audit Dockerfiles and docker-compose files for base image, user privileges, secret leaks, layer efficiency, signal handling, healthchecks, and compose safety. One sub-agent per Dockerfile. Static, live (Trivy/Grype), and apply modes.
devops-needs-assessment
Plain-language DevOps triage for non-experts. Given an app path or description, scores nine dimensions on a 0”“3 scale and names the top three fixes. Jargon-free output with pointers into the other eight DevOps skills.
devsecops-supply-chain-audit
Audit software supply chain across every ecosystem (npm, pip, Go, Ruby, Cargo, Maven, Docker, Terraform) — pinning, vulnerabilities, secrets, SBOM, signing, branch protection, CODEOWNERS. One sub-agent per ecosystem. Three modes.
iac-terraform-audit
Audit Terraform, OpenTofu, Terragrunt, and Pulumi modules for state, provider pinning, security (Checkov/tfsec), module hygiene, environment separation, drift, and cost. One sub-agent per module. Static, live, and apply modes.
kubernetes-manifest-audit
Audit Kubernetes manifests, Helm charts, and Kustomize overlays against CIS Kubernetes Benchmark and NSA/CISA hardening — pod security, resources, probes, RBAC, networking, secrets, availability. Static, live, apply, runtime modes.
observability-audit
Score observability across the four pillars — logs, metrics, traces, and alerts/dashboards — with per-service coverage heatmap. Cross-cutting synthesis. Static, live (Prometheus/Grafana/OTel/Datadog), and runtime (synthetic alert) modes.
release-readiness-audit
Pre-production go/no-go gate. Given a branch or diff, assesses migration safety, rollback path, config drift, runbook coverage, monitoring coverage, and deploy strategy fit. Static, live, and runtime (canary smoke) modes.
sre-reliability-audit
Assess Site Reliability maturity across five dimensions — SLOs/SLIs, runbooks, on-call, postmortems, game days — with per-dimension commentary and uplift path. Static, live (PagerDuty/Opsgenie), and runtime (game day) modes.
cli-ux-audit
Audit any CLI tool for terminal user experience — help text, command structure, error messages, output formatting, discoverability, and accessibility — produces a scored report with actionable fixes
npm-package-audit
Audit npm packages for publishing quality, cross-OS compatibility, type declarations, build config, security, and CI/CD — produces a scored report with actionable fixes
changelog-generator
Generate CHANGELOG.md entries from git log + diff between two refs, Conventional Commits aware, following Keep a Changelog format.
doc-link-validator
Find broken internal and external links in markdown docs. Reports HTTP status + suggested replacements via link-check.py helper.
env-var-auditor
Audit env var usage vs .env.example and code references — surface drift, unused vars, missing docs, and security risks.
pr-description-writer
Draft a pull request description from git diff — summary, why, risk assessment, test plan, screenshot placeholders.
repo-snapshot
Produce a repository snapshot — folder tree, top files by LOC, dependency surface, contributor map, framework detection — for handoff or onboarding.
codebase-profiler
Generate a comprehensive codebase profile — architecture topology, dependency graph, code quality metrics, security surface, test posture, and infrastructure snapshot. Stack-agnostic. Outputs to .anthril/codebase-profile.md.
dead-code-audit
Audit a codebase for dead code — unused exports, orphaned files, dead dependencies, unreachable branches, abandoned flags, unused CSS — across multiple languages. Produces a confidence-scored report with cleanup actions. Use for dead code, code cleanup, bundle bloat, pre-refactor analysis.
plan-orchestrator
Turns a bullet list of tasks/issues/bugs into one ordered plan with full coverage verification. Fans out specialist sub-agents in parallel. Designed for Claude Code Plan Mode. Read-only — produces a plan, never edits.
write-path-mapping
Map the write path of a project across multiple frameworks — entry points, validation, auth, persistence, side-effects. Outputs report, Mermaid diagrams, JSON sidecar. Flags unauth writes, missing RLS, cache gaps. Use for write path, mutation audit, RLS audit.
brand-guidelines
Compile comprehensive brand guidelines covering logo, colour, typography, imagery, voice, and do's/don'ts — produces a complete brand book ready for design handoff
brand-identity
Generate core brand identity — mission, vision, values, voice, tone, and personality framework — producing a foundational brand identity document grounded in archetypes
color-palette
Generate brand colour palettes with primary, secondary, semantic, and neutral colours — including HEX/RGB/HSL/OKLCH values and WCAG-validated contrast pairs
competitor-analysis
Analyse competitor brands across positioning, visual identity, messaging, pricing, and audience — producing a differentiation map and white-space opportunity report
design-tokens
Generate design token systems exportable to CSS variables, Tailwind config, JSON, and Style Dictionary — covering colour, typography, spacing, radius, shadow, and motion
legal-disclaimers
Generate legal disclaimers, privacy notices, cookie banners, and terms-of-service templates customised for industry, jurisdiction, and use case
logo-brief
Create comprehensive logo design briefs with concept directions, references, constraints, and deliverables — ready for human designers or AI image generators
target-audience
Build buyer personas, ICPs, and audience segments with psychographics, demographics, jobs-to-be-done, channel preferences, and objection mapping
website-copy
Generate website copy for homepage, about, features, pricing, and contact pages aligned to brand voice — SEO-aware, conversion-focused, with meta descriptions and CTAs
daily-wellness-stack
Design a daily wellness habit stack (hydration / movement / sunlight / breathwork) anchored to existing routines via the habit-stacker pattern. Low effort, high frequency.
move-more-plan
Design an N-week strength, endurance, or hybrid training program with progressive overload, deload weeks, equipment-tier substitutions, and recovery cues.
sleep-tune-up
Audit current sleep pattern, prescribe a 14-day routine + environment + light/caffeine timing protocol, with a re-measurement checklist.
smart-supplement-stack
Build an evidence-rated supplement stack with timing, dose, cycling, and interaction warnings. Food-first; flags risky combinations and pregnancy/medication concerns.
week-of-meals
Build a 7-day meal plan with macro targets, prep-day workflow, AUD shopping list grouped by aisle, and 3 fallback options per day.
adulting-checklist
Quarterly life-admin sweep tailored to life stage — renewals, audits, reviews — so admin items don't drift into emergencies.
home-tlc-calendar
Annual home-maintenance calendar by home type (apartment / freestanding / period / coastal), AU-state-specific compliance tasks (smoke alarms, gutters, pool).
thoughtful-gifts-plan
Annual gift plan from relationship inventory, budget envelope per recipient, lead-time alerts, and "memorable not expensive" prompts.
trip-day-by-day
Build a multi-day travel itinerary with logistics (transfers, check-ins, must-book windows), pacing rules tuned to party composition, rest days, and a packing list.
debt-knockout-plan
Compare avalanche vs snowball debt payoff strategies, scan refinance options, build a payoff timeline, and produce a behavioural staircase plan for AU debt holders.
future-me-projection
Retirement projection with Australian super, sensitivity analysis (FIRE scenarios, market-return scenarios, contribution scaling). Calls projection-analyst agent for narrative depth.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.