cesdperez

cesdperez/llmfiles

Command Claude Code

One day of my work as a short Slack-ready standup post, split into team and no-team work, plus private notes. Defaults to yesterday.

cesdperez/llmfiles

Command Claude Code

Autonomous multi-lens review of a GitLab MR. Fans out parallel read-only lens agents, then posts inline diff comments for findings scoring 7+ without asking. Re-invocation does a follow-up pass like a human reviewer: resolves what got fixed, answers what got questioned, reviews only what is new. Also the deep path…

cesdperez/llmfiles

Command Claude Code

Triage every MR waiting on my review, autopost review comments (never approvals), and brief me in one line per MR. Low-risk MRs get a single-agent fast review; high-risk MRs dispatch to /glablensedreview.

cesdperez/llmfiles

Command Claude Code

Multi-angle code audit of local changes. Fans out parallel read-only lens agents (correctness, tests, standards, reuse, security, performance), then synthesizes one scored report.

cesdperez/llmfiles

Command Claude Code

Build a Claude Code skill for a tech stack, library, or CLI tool.

cesdperez/llmfiles

Command Claude Code

That last message did not land. Re-pitch it in Simplified Technical English using the project's own vocabulary.

cesdperez/llmfiles

Skill Claude CodeCodex

GitLab CLI for merge requests and CI/CD pipelines. Use when creating MRs, reviewing merge requests, checking pipeline status, or when the user mentions glab, GitLab CLI, or merge request operations.

cesdperez/llmfiles

Skill Claude CodeCodex

Interact with the intervals.icu training platform API. Use when fetching activity history, cycling/running totals, workout library, race calendar, fitness chart (CTL/ATL/TSB), FTP/zones, wellness data, or when the user asks about their training, fitness, races, workouts, or intervals.icu data.

cesdperez/llmfiles

Skill Claude CodeCodex

LikeC4 architecture-as-code DSL for C4 models and views. Use whenever reading or editing a .likec4 or .c4 file, running the likec4 CLI, or drawing architecture, element, or dynamic views.

cesdperez/llmfiles

Skill Claude CodeCodex

Run operational tasks against Supabase Postgres databases in your own account using the Supabase CLI alone (no MCP server). Use when connecting to a Supabase project, running SQL queries against a remote/local database, inspecting DB health/performance, checking security & performance advisors, or when the user…

cesdperez/llmfiles

Skill Claude CodeCodex

Best practices for Svelte 5 and SvelteKit 2.9+ development. Use when writing Svelte components, using runes ($state, $derived, $effect, $props), creating SvelteKit routes, working with load functions, form actions, or when the user mentions Svelte, SvelteKit, .svelte files, or runes.

cesdperez/llmfiles

Skill Claude CodeCodex

Zitadel IAM API for orgs, projects, users, roles, service accounts, and instance settings. Use whenever a request, script, or config calls the Zitadel API or changes Zitadel state.

cesdperez/llmfiles

Agent Claude Code

Read-only search agent for broad fan-out searches across many files, directories, or naming conventions when only the conclusion is needed. Replaces the built-in Explore so it runs on the newest Sonnet at medium effort regardless of the session's own effort.

cesdperez/llmfiles

Agent Claude Code

General-purpose agent for multi-step tasks and research the other named agents do not fit. Replaces the built-in general-purpose so it runs on the newest Opus at high effort regardless of the session's own effort.

cesdperez/llmfiles

Agent Claude Code

Creates GitLab merge requests using glab CLI. Use when the user wants to create an MR, especially in the background after implementing a feature or fix.

cesdperez/llmfiles

Agent Claude Code

Read-only audit agent for findings that hinge on pattern recognition against stated rules (test health, code standards, reuse, ticket alignment, performance smells). Runs on the newest Opus at medium effort regardless of the session's own effort. Reports findings, never edits.

cesdperez/llmfiles

Agent Claude Code

Read-only audit agent for findings that hinge on reasoning about execution (correctness, security, cross-repo impact, verification by running tests). Runs on the newest Opus at high effort regardless of the session's own effort. Reports findings, never edits.

cesdperez/llmfiles

Agent Claude Code

Executor for mechanical chores where the steps are known up front (renames, formatting, boilerplate, small config edits, running a documented command). Runs on the newest Sonnet at medium effort regardless of the session's own effort.

cesdperez/llmfiles

Agent Claude Code

Executor for delegated implementation, debugging, or research that needs full reasoning. Runs on the newest Opus at medium effort regardless of the session's own effort. Use for code changes, multi-file investigations, and anything whose result the orchestrator will build on.

cesdperez/llmfiles

Skill Claude CodeCodex

Write and rewrite content in ASD-STE100 Simplified Technical English. Use when the user says /plainenglish or asks for simplified technical English.

cesdperez/llmfiles

Command Claude Code

Recommend how to run the task I am about to start: solo session, subagents, a Workflow, or an agent team. Says why, what it costs, and when to switch.

cesdperez/llmfiles

Command Claude Code

Research the latest Anthropic models (docs, benchmarks, user reports), then propose which model and effort each agent and the session in this repo should run. Adversarially reviewed. Outputs a today-vs-proposed table.

cesdperez/llmfiles

Skill Codex

Draft the llmfiles daily work recap from git, GitLab, Claude transcripts, and available Slack evidence when explicitly requested.

cesdperez/llmfiles

Skill Codex

Run the llmfiles multi-lens GitLab MR review and follow-up workflow when explicitly requested; supports dry-run.