zeikar/hyperclaude / .claude/skills/cc-changelog
cc-changelog
VerifiedThis skill should be used when the user asks to check for new Claude Code releases, "what changed in Claude Code", "any Claude Code updates", "check the changelog", "diff the Claude Code version", or wants the Claude Code changelog reviewed for changes relevant to THIS repo (the hyperclaude plugin). Reads a locally-stored last-checked version, fetches the official changelog, reports plugin-relevant changes grouped by actionability, and offers to advance the stored version.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.3 KB |
| get-changelog.mjs | script | 3.2 KB |
| get-changelog.test.mjs | script | 3.5 KB |
get-changelog.test.mjs
View on GitHub// Tests for get-changelog.mjs — the cc-changelog slice helper. Pure-logic only
// (no network): version compare + changelog slicing against a fixed fixture.
// Run: node --test .claude/skills/cc-changelog/get-changelog.test.mjs
import { test } from 'node:test';
import assert from 'node:assert/strict';
import { spawnSync } from 'node:child_process';
import { fileURLToPath } from 'node:url';
import { dirname } from 'node:path';
import { cmp, sliceChangelog } from './get-changelog.mjs';
// Fixture: descending, with a skipped number (205 absent) and a preamble line.
const FIXTURE = `# Changelog
## 2.1.207
- entry a
## 2.1.206
- entry b
## 2.1.204
- entry c (205 was skipped)
## 2.1.200
- entry d
`;
// ---------- cmp ----------
test('cmp: greater / lesser / equal', () => {
assert.equal(cmp('2.1.207', '2.1.206'), 1);
assert.equal(cmp('2.1.206', '2.1.207'), -1);
assert.equal(cmp('2.1.207', '2.1.207'), 0);
});
test('cmp: numeric, not lexicographic (2.1.100 > 2.1.99)', () => {
assert.equal(cmp('2.1.100', '2.1.99'), 1);
});
test('cmp: minor and major dominate patch', () => {
assert.equal(cmp('2.2.0', '2.1.999'), 1);
assert.equal(cmp('3.0.0', '2.9.9'), 1);
});
test('cmp: skipped-number ordering (2.1.193 > 2.1.192)', () => {
assert.equal(cmp('2.1.193', '2.1.192'), 1);
});
// ---------- sliceChangelog ----------
test('slice: baseline present → keeps only strictly-newer, verbatim, newest first', () => {
const { latest, slice } = sliceChangelog(FIXTURE, '2.1.204');
assert.equal(latest, '2.1.207');
assert.match(slice, /^## 2\.1\.207/); // newest first
assert.ok(slice.includes('## 2.1.206'));
assert.ok(slice.includes('- entry a'));
assert.ok(!slice.includes('## 2.1.204'), 'baseline itself excluded');
assert.ok(!slice.includes('## 2.1.200'), 'older excluded');
assert.ok(!slice.includes('# Changelog'), 'preamble excluded');
});
test('slice: skipped baseline (205 never a header) stops at first ≤ baseline', () => {
const { latest, slice } = sliceChangelog(FIXTURE, '2.1.205');
assert.equal(latest, '2.1.207');
assert.ok(slice.includes('## 2.1.207'));
assert.ok(slice.includes('## 2.1.206'));
assert.ok(!slice.includes('## 2.1.204'), '204 ≤ 205 → excluded');
});
test('slice: baseline == latest → empty slice, latest still reported', () => {
const { latest, slice } = sliceChangelog(FIXTURE, '2.1.207');
assert.equal(latest, '2.1.207');
assert.equal(slice, '');
});
test('slice: baseline newer than latest → empty slice', () => {
const { slice } = sliceChangelog(FIXTURE, '2.1.999');
assert.equal(slice, '');
});
test('slice: low baseline keeps all real entries but never the baseline gap', () => {
const { slice } = sliceChangelog(FIXTURE, '2.1.200');
assert.ok(slice.includes('## 2.1.207'));
assert.ok(slice.includes('## 2.1.204'));
assert.ok(!slice.includes('## 2.1.200'), '200 == baseline → excluded');
});
test('slice: no headers at all → latest null, empty slice', () => {
const { latest, slice } = sliceChangelog('just prose, no versions\n', '2.1.0');
assert.equal(latest, null);
assert.equal(slice, '');
});
// ---------- import safety ----------
test('importing get-changelog.mjs does not run main()', () => {
const dir = dirname(fileURLToPath(import.meta.url));
const res = spawnSync(
process.execPath,
['-e', 'import("./get-changelog.mjs").then(()=>process.stdout.write("IMPORTED_NO_OUTPUT"))'],
{ cwd: dir, encoding: 'utf8' }
);
assert.equal(res.status, 0);
assert.equal(res.stdout, 'IMPORTED_NO_OUTPUT'); // no LATEST=/fetch output leaked
});
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: 472k | 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: 198k | 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: 198k | 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: 198k | Updated | Claude CodeCodex | Verified | Install |