Skip to main content
ClaudeWave
ES, Spanish
Slash Command403 estrellas del repoactualizado 4mo ago

log

The log slash command displays recent Git commits in a concise format and correlates them with the current working directory state. Run it with an optional numeric argument to control how many commits appear (defaults to 5 if omitted or invalid), and it automatically flags potential conflicts between staged changes and recently modified code areas. Use this when you need quick context on what's been committed recently and how it relates to uncommitted work.

Instalar en Claude Code
Copiar
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/syahiidkamil/Software-Engineer-AI-Agent-Atlas/HEAD/.claude/commands/git/log.md -o ~/.claude/commands/log.md
Después abre una sesión nueva de Claude Code; el slash command carga automáticamente.

log.md

Run `git log` to show recent commits, then add a short summary and any context that links those commits to the current working state.

Argument: $ARGUMENTS

- If `$ARGUMENTS` is a positive integer, use it as the commit count.
- Otherwise (empty, non-numeric, or zero/negative), default to **5**.

## Steps

1. Run these in parallel via the Bash tool:
   - `git log -n {count} --oneline --decorate` — the commit list
   - `git status --short` — current working / staging state
   - `git diff --stat HEAD` — what's changed since HEAD (staged + unstaged)

2. **Show the raw `git log` output first**, verbatim. Do not paraphrase commits.

3. **Summary** (2–4 bullets max). Cluster the commits by theme (feature area, refactor, chore, bug fix). Lead with what changed, not the commit subjects. Skip if the commits are unrelated noise.

4. **Continual context** — only include if there is a real link between recent commits and the current working/staging state. For each linked file or area:
   - Name the commit(s) that last touched it
   - Note whether the current change extends, reverts, or diverges from that direction
   - Flag risks: e.g. "commit X just refactored this file; staged change re-edits the same lines — check for conflicts with the new structure"

   If nothing in the working tree relates to the shown commits, write a single line: `No overlap between recent commits and current working state.` and stop.

## Rules

- Keep it tight. The summary and context together should rarely exceed 10 lines.
- Don't speculate. If a connection isn't clear from the diff + log, don't invent one.
- Don't restate the commit subjects in the summary — Boss already sees them.
- Don't run extra commands (file reads, blame, etc.) unless the overlap is ambiguous and Boss would otherwise be misled.
abstraction-powerSkill

Activate ATLAS pattern recognition mode. Identify repeated patterns, extract essential characteristics, and create reusable abstractions from concrete examples.

adversarial-reviewSkill

Adversarially review something just built — presume it is broken and find where. Use after implementing a feature, finishing a build, or before shipping, or whenever ATLAS or Boss wants a hostile second opinion on a diff, a running app, or a whole codebase. Spawns clean-context reviewers with opposing lenses (correctness, security, empty-world) and reproduces every finding by running the target before believing it. Distinct from /code-review, which statically reads a diff and never runs the app.

algorithmic-artSkill

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

anthropic-product-knowledgeSkill

Stop and consult this skill whenever your response would include specific facts about Anthropic's products. Covers: Claude Code (how to install, Node.js requirements, platform/OS support, MCP server integration, configuration), Claude API (function calling/tool use, batch processing, SDK usage, rate limits, pricing, models, streaming), and Claude.ai (Pro vs Team vs Enterprise plans, feature limits). Trigger this even for coding tasks that use the Anthropic SDK, content creation mentioning Claude capabilities or pricing, or LLM provider comparisons. Any time you would otherwise rely on memory for Anthropic product details, verify here instead — your training data may be outdated or wrong.

canvas-designSkill

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

change-core-selfSlash Command

Interview Boss about the project, then reason from first principles to design the ideal ATLAS operating identity/system-prompt for it — free to drop KISS/YAGNI/DRY/clean-architecture entirely when the project (and the LLM's own distribution) calls for a different mindset

code-architectSubagent

Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences

code-explorerSubagent

Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development