Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 566 files from 1 758 authors, of which 61 913 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls…
Project health audit and health check — architecture, performance; Use when assessing overall project health…
Interactive briefing of a plan file — explains reasoning, schema; Use when developers need to understand a plan…
Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto…
Fix Elixir/Phoenix code until Codex CLI review comes back clean; Use when codex is installed and you want an external…
Capture solved problems as searchable solution docs. Use after fixing bugs, when "that worked", or after successful…
Audit Hex deps for supply-chain security risk — bidi chars; Use after mix deps.update, when checking if a package…
Document tested Elixir APIs; may update README/ADRs. Not for docs lookup, audits/reviews, or standalone decisions.
Update Hex dependencies safely. Use for upgrades; use $elixir-phoenix:phx-investigate for deps.get failures.
Record vetted Hex versions after security review. Use to approve audited dependencies, not to scan them.
Apply an advisory scope in this session. Use for read-only or directory-scoped work; no enforcement hook is installed.
Run portable end-to-end lifecycle with gates. Use for full features;
Initialize plugin in a project — install Iron Laws, auto-activation; Use when setting up or updating the plugin.
Recommend the right $elixir-phoenix:phx-* workflow. Use when choosing a plugin skill, not for Codex /help.
Walk through the Elixir/Phoenix plugin commands, workflow; Use when a new user wants to learn what the plugin offers…
Investigate Elixir/Phoenix bugs root-cause first. Reproduce failures, cite evidence; Codex subagents are optional.
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning…
Reduce mix output noise (5-15% token savings) by installing rtk; Use when long mix output floods context.
Analyze Elixir/Phoenix performance — N+1 queries, assign bloat, ecto; Use when slowness, timeouts, or high memory…
Recommend safe Bash permissions for Elixir mix commands in; Use when permission prompts slow workflow, "fix…
Plan features spanning multiple domains: billing (Stripe), auth; Use when designing interconnected systems…'
Address feedback left on a GitHub pull request: fetch unresolved; Use for a PR URL/number or reviewer comments.…'
Implement small Phoenix changes without planning — add validations; Use for single-file edits under 50 lines.
Research Elixir/Phoenix/Ecto topics or evaluate Hex libraries; Use when learning about libraries, patterns…
Recall prior work from past sessions — how a bug was fixed, what was; Use when asked 'have we done this before'…
Review changed Elixir/Phoenix code read-only. Check requirements, cite evidence, deduplicate, and return a verdict.
Analyze Elixir/Phoenix technical debt — duplicates, refactoring; Use when asked about code quality, cleanup, or what…
Trace Elixir call trees from entry points via mix xref. Use when debugging data flow, planning signature changes…
Triage review findings interactively — approve, skip, or prioritize;
Watch an Elixir/Phoenix PR for new review comments (bot + human); Use after opening a PR or pushing, while waiting on…
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs…
Execute Elixir/Phoenix plan tasks with progress tracking. Use after $elixir-phoenix:phx-plan to implement features…
Write or repair Elixir tests with ExUnit, sandbox isolation, async; Use for test files, test setup, or failing/flaky…
Enforce Elixir/Phoenix security — auth, OAuth, sessions, CSRF, XSS; Use when editing auth files, login flows, RBAC…
Tidewave MCP runtime tools — debugging, smoke testing, live state; Use when evaluating code in a running Phoenix app.
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
Route ambiguous or mixed Phoenix/LiveView/Ecto requests before choosing a workflow. Use when user is unsure where to start/how to approach work, asks for the right workflow, or combines intents such as fixing and refactoring. NOT for a clear task.
Inspect LiveView socket assigns for memory bloat — missing temporary_assigns, unused assigns, unbounded lists needing streams, memory estimates. Use when LiveView memory grows or you need to add temporary_assigns.
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
Interactive briefing of a plan file — explains reasoning, schema decisions, component choices. Use when developers need to understand a plan before approving.
Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.
Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.
Capture solved problems as searchable solution docs. Use after fixing bugs, when "that worked", or after successful /phx-review or /phx-investigate.
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (/phx-investigate).
Audit Hex deps for supply-chain security risk — bidi chars, compile-time exec, maintainer changes, typosquats, CVEs. Use after mix deps.update, when checking if a package upgrade is safe, or reviewing mix.lock PR diffs.
Record a vetted Hex package version in hex_vet.exs after a security review — manages the audit ledger, not the scanner. Use to approve a dep after /phx-deps-audit findings or to initialize hex_vet.exs.
Generate @moduledoc/@doc for tested Elixir features; may update their README section or ADR. Not for docs lookup, documentation audits/reviews, or capturing standalone decisions.
Apply an advisory edit scope in this session. Use for read-only or directory-scoped work; no enforcement hook is installed.
Run a portable sequential plan-work-verify-review-compound lifecycle. Use optional generic workers only when the runtime supports them.
Choose Phoenix review, plan, debug, or test command. Use when user asks which /phx-* command or plugin skill handles a task; do not route only to a domain skill. NEVER for bare /help; NOT for ambiguous requests (use intent-detection) or a plugin tour.
Investigate Elixir/Phoenix bugs root-cause first. Reproduce failures, cite evidence, and use optional native OpenCode subagents only when useful.
Initialize plugin in a project — install Iron Laws, auto-activation rules, and reference auto-loading into CLAUDE.md. Use when setting up or updating the plugin.
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
Walk through the Elixir/Phoenix plugin commands, workflow, and features in 6 interactive sections. Use when a new user wants to learn what the plugin offers or needs a refresher on available commands.
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
Analyze Elixir/Phoenix performance — N+1 queries, assign bloat, ecto optimization, genserver bottlenecks. Use when slowness, timeouts, or high memory reported.
Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks.'
Recommend safe Bash permissions for Elixir mix commands in settings.json. Use when permission prompts slow workflow, "fix permissions", "reduce prompts", "auto-allow mix".
Claude Skills — questions
Answers built from the skills we actually parsed.