jtenniswood/espcontrol / .agents/skills/updates
updates
VerifiedSummarize user-facing project changes from the last 7 days. Use when the user says "/updates", asks for recent updates, wants a changelog-style summary, or wants the most important feature changes from the past week.
/updates
Summarize what changed in this project over the last 7 days, focusing on user-facing features and behavior rather than implementation details.
Workflow
1. Collect Recent Changes
Use the current date as the endpoint and inspect commits from the last 7 days.
git status --short --branch
git fetch origin --prune
git log --since="7 days ago" --date=short --pretty=format:'%h %ad %s' --decorate
git log --since="7 days ago" --name-only --pretty=format:'commit %h %ad %s' --date=short
If the local branch is behind or stale, note that the summary is based on the available local history unless a fetch succeeded.
2. Understand User Impact
For each meaningful change, inspect enough context to explain what a user can now do, see, configure, or rely on.
Useful commands:
git show --stat <commit>
git show --name-only <commit>
git show -- <path>
Prioritize these as user-facing:
- New visible UI behavior, controls, screens, or settings
- Firmware capabilities, device support, setup, update, or reliability changes
- Documentation that helps users operate, configure, or troubleshoot the project
- Release, install, or build changes that affect how users receive the project
Usually skip these unless they clearly affect users:
- Internal refactors
- Formatting-only changes
- Test-only changes
- CI-only maintenance
- Dependency bumps without a visible change
3. Order by Importance
Sort the summary by practical user impact:
- New or expanded capabilities
- Fixes for broken or confusing user workflows
- Reliability, compatibility, or update improvements
- Documentation or setup improvements
- Minor polish
When importance is close, put broader changes before narrow device- or page-specific changes.
4. Write the Update
Use one sentence per item in this format:
Feature: description of the user-facing change.
Rules:
- Keep each item to one sentence.
- Use approachable, non-developer language.
- Mention the feature or area first, then the benefit.
- Avoid commit hashes, file names, and developer terms unless the user asks.
- Combine related commits into one item when they deliver the same user-facing outcome.
- If there were no user-facing changes, say that clearly and mention that recent work appears to be internal maintenance.
Output Format
Updates from <start date> to <end date>:
- Feature: <one-sentence description>
- Feature: <one-sentence description>
If the 7-day window is ambiguous, use exact dates in the heading.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 197k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |