gsarig

gsarig/skills

Skill Claude Code

Retires a finished plan document: establishes from artifacts what actually shipped, files it under plans/archive/ with that record, and decides whether its procedure is worth generalising.

gsarig/skills

Skill Claude Code

Computes the optimal Claude usage-window ping schedule from work hours and creates or reconciles the scheduled cloud routines that pin the window boundaries.

gsarig/skills

Skill Claude Code

Reviews changes to prose files (markdown, text, blog posts, docs). Focuses on voice, grammar, factual claims, dead links, and structure. Loads the project's voice or style guide when one exists. Skips linter and Actions hash verification.

gsarig/skills

Skill Claude Code

Full code review for large or security-sensitive changes. Gathers requirements first, loads all relevant language references, runs the linter where applicable, applies the full review checklist with security as the top priority.

gsarig/skills

Skill Claude Code

Reviews infrastructure changes: GitHub Actions workflows, Terraform, Dockerfiles, docker-compose, IaC. Focuses on supply-chain pinning, secret handling, least-privilege permissions, action versions, and CI failure modes. Always verifies action hash pins when present.

gsarig/skills

Skill Claude Code

Abbreviated code review for small or low-stakes code changes. Skips requirements gathering. Skips the linter in PR mode (CI runs it). Focuses on correctness against obvious intent, readability, and pattern consistency. For large or security-sensitive diffs, use code-review-deep instead.

gsarig/skills

Skill Claude Code

Orchestrator. Triages a PR, local diff, patch file, or staged/branch changes into one of four review types (content, code-lite, code-deep, infra) and dispatches to the matching child skill. Use this when you don't already know which depth or type of review you want. For a known type, invoke the child skill directly.

gsarig/skills

Skill Claude Code

Produces a one-shot devil's-advocate critique of a plan, design, or decision: steel-manned strengths first, then severity-tagged findings each with a concrete alternative, then a verdict.

gsarig/skills

Skill Claude Code

Interviews the user branch-by-branch about a plan or design, resolving dependent decisions one at a time and recommending an answer for each question.

gsarig/skills

Skill Claude Code

Investigates a question to a grounded conclusion in which every claim is either verified against a primary source or explicitly flagged as an untested hypothesis.

gsarig/skills

Skill Claude Code

Explains any target (a ticket, a file, a concept, or whatever is under discussion) the way you would explain it to a smart teenager, in a few plain sentences.

gsarig/skills

Skill Claude Code

Chart implementation reference for Obsidian dataviewjs blocks: YAML chart-block mode (phibr0 plugin) and direct window.renderChart (Chart.js v3, including a top-of-bar labels plugin), with the standard color palette and known pitfalls.

gsarig/skills

Skill Claude Code

Reduces a target to the tip of the inverted pyramid: its core conclusion in a short paragraph, dropping supporting detail and reasoning, then tightened to the fewest words.

gsarig/skills

Skill Claude Code

Guides writing or revising a behavioral rule in the instruction files so it lands in the right scope, doesn't duplicate or contradict an existing rule, and stays lean.

gsarig/skills

Skill Claude Code

Guides creation or update of a SKILL.md: chooses the right frontmatter fields (description vs whentouse, argument-hint, model, effort, allowed-tools, paths, disable-model-invocation, etc.), runs three pressure tests, and follows the approval flow before writing.

gsarig/skills

Skill Claude Code

Re-checks the immediately preceding reply for unverified claims, excess length, and overengineering, then re-issues a corrected reply.

gsarig/skills

Skill Claude Code

Runs a mechanical hygiene pass over a drafted Markdown artifact so it reads standalone and stays tight, amending presentation only and never touching the substance.

gsarig/skills

Skill Claude Code

Saves anything from the current session worth keeping for next time, then confirms it is safe to /exit.

gsarig/skills

Skill Claude Code

Before a plan or brief is drafted, raises up to three one-line hunches about how the approach could be simpler, so the user can pick any worth discussing before anything is written.