#87 by GitHub stars
snarktank/ralph
Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/prd/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6c53cb0b831e → 6c53cb0b831e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6c53cb0b831e
No earlier version was observed for comparison.
skills/ralph/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6c53cb0b831e → 6c53cb0b831e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6c53cb0b831e
No earlier version was observed for comparison.
Verified commit 6c53cb0b831ebe8739c6a003e22af14902d8b0b5
git clone --filter=blob:none --no-checkout https://github.com/snarktank/ralph.git .hotskills/snarktank-ralph && git -C .hotskills/snarktank-ralph checkout --detach 6c53cb0b831ebe8739c6a003e22af14902d8b0b5
# Copy each selected skill directory from .hotskills/snarktank-ralph into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/snarktank/ralph.git .hotskills/snarktank-ralph && git -C .hotskills/snarktank-ralph checkout --detach 6c53cb0b831ebe8739c6a003e22af14902d8b0b5
# Copy each selected skill directory from .hotskills/snarktank-ralph into .agents/skills/<skill-name>/Heat
4.5- Star growth, last 7 daysAhead of 50% of tracked repositories
- Star growth, last 24 hoursAhead of 69% of tracked repositories
- Rank movement, last 7 daysAhead of 68% of tracked repositories
- Commits, last 30 daysAhead of 0% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
How it works
prd
When your agent uses it
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,684 tokensWhen the skill is activated
Reference documents
1,818 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The Job
- Step 1: Clarifying Questions
- Step 2: PRD Structure
- Writing for Junior Developers
- Output
- Example PRD
- Checklist
Files
../../.claude-plugin/marketplace.jsonasset604 bytes../../.claude-plugin/plugin.jsonasset344 bytesSKILL.mdcore7,223 bytes../ralph/SKILL.mddoc7,508 bytes
Read SKILL.md
# PRD Generator
Create detailed Product Requirements Documents that are clear, actionable, and suitable for implementation.
---
## The Job
1. Receive a feature description from the user
2. Ask 3-5 essential clarifying questions (with lettered options)
3. Generate a structured PRD based on answers
4. Save to `tasks/prd-[feature-name].md`
**Important:** Do NOT start implementing. Just create the PRD.ralph
When your agent uses it
Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
1,818 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The Job
- Output Format
- Story Size: The Number One Rule
- Story Ordering: Dependencies First
- Acceptance Criteria: Must Be Verifiable
- Conversion Rules
- Splitting Large PRDs
- Example
- Archiving Previous Runs
- Checklist Before Saving
Files
SKILL.mdcore7,508 bytesSKILL.mdcore7,508 bytes
Read SKILL.md
# Ralph PRD Converter
Converts existing PRDs to the prd.json format that Ralph uses for autonomous execution.
---
## The Job
Take a PRD (markdown file or text) and convert it to `prd.json` in your ralph directory.
---
## Output Format
Skills included
- prd
- ralph
Repository facts
- License
- MIT
- Created
- Jan 7, 2026
- Last pushed
- Feb 2, 2026
- Forks
- 2,093
- Open issues
- 35
- Project activity
- Slowing
Rank over the last 12 weeks
Now #87 · best #75 · down 4 in 30 days
- #86 from Oct 30 to Oct 31
- #85 from Nov 1 to Nov 2
- #86 on Nov 3
- #85 on Nov 4
- #86 on Nov 5
- #87 since Nov 6
14 earlier periods
- #70 on Aug 2
- #71 on Aug 7
- #72 from Aug 8 to Aug 12
- #73 on Aug 13
- #75 from Aug 14 to Aug 17
- #78 from Aug 18 to Aug 26
- #79 from Aug 27 to Aug 29
- #80 from Aug 30 to Aug 31
- #81 from Sep 1 to Sep 9
- #82 from Sep 10 to Sep 25
- #83 from Sep 26 to Oct 24
- #84 on Oct 25
- #84 on Oct 28
- #85 on Oct 29
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 2, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1 note
skills/ralph/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- No network access
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/prd/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/prd/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/prd/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/prd/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/snarktank-ralph/)