Generate a sprint review changelog from GitHub pull requests. Lists PRs by a given author since a given date, groups them into Features and Fixes, and writes a markdown summary.
Scanned 5/28/2026
Install via CLI
openskills install rhesis-ai/rhesis---
name: sprint-review
description: Generate a sprint review changelog from GitHub pull requests. Lists PRs by a given author since a given date, groups them into Features and Fixes, and writes a markdown summary.
disable-model-invocation: true
---
# Sprint Review
Generate a markdown changelog from GitHub PRs for sprint review meetings.
## Defaults
- **Time range**: last two weeks (14 days from today)
- **Author**: the current GitHub user -- detect automatically via `gh api user --jq .login`
Both can be overridden if the user explicitly provides a different author or date.
## Workflow
1. **Detect the current user** (unless explicitly provided):
```bash
gh api user --jq .login
```
2. **Collect PRs** using GitHub CLI (default: last 14 days):
```bash
gh pr list --author <username> --state all --search "created:>=<date>" --limit 100 \
--json number,title,state,createdAt,body,url \
| jq -r '.[] | "\(.number)|\(.title)|\(.state)|\(.createdAt)|\(.url)"'
```
3. **Fetch PR bodies** for context on what each PR does (use `--json body`).
4. **Group PRs** into two sections:
- **Features** -- new capabilities, refactors, new providers, new APIs
- **Fixes** -- bug fixes, dependency patches, config corrections, minor chores
5. **Consolidate similar PRs** under a single description when they share the same goal (e.g. two PRs making different parts of the SDK async-first).
6. **Write the markdown file** to `docs/changelog-<username>.md` using this format:
```markdown
## PR Changelog -- <username> (<start date> -- <end date>)
### Features
**Short heading**
One-to-two sentence description.
- [#<number> -- <title>](<url>)
- [#<number> -- <title>](<url>) *(open/draft if not merged)*
### Fixes
**Short heading**
One sentence description.
- [#<number> -- <title>](<url>)
```
## Formatting rules
- Section headings: `###` for Features / Fixes
- Entry headings: **bold text** (not a markdown heading)
- Descriptions: 1-2 sentences max, focus on what changed and why it matters
- PR links: bulleted list with `#<number> -- <title>` as link text
- Mark non-merged PRs with *(open)* or *(draft)*
- No emojis
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...