How do I install the Snarkvm Fix skill?

Run npx skillmds@latest add provablehq/snarkvm-fix in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Snarkvm Fix safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Snarkvm Fix?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Snarkvm Fix free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Snarkvm Fix?

provablehq (@provablehq) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Snarkvm Fix by provablehq — Agent Skill

Name: Snarkvm Fix
Author: provablehq

Snarkvm Fix

Fix GitHub issues or PR review feedback in snarkVM using TDD workflow. WHEN: User says "fix issue", "fix #123", "fix pr", "fix PR feedback", "address review comments", "resolve review threads", or wants to fix a bug/feature request from GitHub issues or address reviewer requests. WHEN NOT: Doing security review (use snarkvm-review), fetching context only (use snarkvm-github), or working on non-snarkVM code.

provablehq 06c80af 3.2 KB Updated Sep 17, 2026

File contents

Fix Issue or PR Feedback

Fix snarkVM GitHub issues or PR review comments using test-driven development.

Usage

/snarkvm-fix issue <number>
/snarkvm-fix pr <number>

Setup

MODE="${ARGUMENTS%% *}"   # "issue" or "pr"
NUM="${ARGUMENTS#* }"     # the number
WS=".claude/workspace"
SKILL_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../snarkvm-github" && pwd)"

1. Load Context

For issues:

if [[ ! -f "$WS/state-issue-$NUM.md" ]]; then
  "$SKILL_DIR/scripts/fetch-issue.sh" "$NUM"
fi

Review: $WS/state-issue-$NUM.md and recent comments.

For PRs:

if [[ ! -f "$WS/state-pr-$NUM.md" ]]; then
  "$SKILL_DIR/scripts/fetch-pr.sh" "$NUM"
fi
"$SKILL_DIR/scripts/refresh-threads.sh" "$NUM"

Review: $WS/state-pr-$NUM.md, $WS/unresolved-pr-$NUM.json, and $WS/handoff-pr-$NUM.md if present.

2. Investigate

For issues — search for related code. Answer:

What is the expected vs actual behavior?
Where does the code path go wrong?
What are the edge cases?

For PRs — analyze each unresolved comment:

#	Path:Line	Reviewer	Request	Type	Risk

Where to look:

Console type bugs -> console/ (types, program, network)
Circuit bugs -> circuit/ (must stay in sync with console)
Synthesizer bugs -> synthesizer/ (program execution, VM, process)
Crypto bugs -> algorithms/ (Poseidon, Marlin, Polycommit)
Serialization bugs -> check ToBytes/FromBytes/Serialize/Deserialize impls

Think hard. Do not proceed until you understand the root cause or each request.

3. Plan (APPROVAL REQUIRED)

Present a concrete plan:

#	Location	Change	Test	Risk

Use AskUserQuestion to get explicit approval before proceeding.

4. Implement (TDD)

For each change:

Write failing test that reproduces the bug or covers the new behavior
Verify it fails: cargo test -p <crate> -- test_name --nocapture
Implement minimal fix — match existing code style
Verify it passes: cargo test -p <crate> -- test_name --nocapture

For pure style/nit fixes (no behavioral change), batch them without tests.

5. Final Validation

Validate affected crates per AGENTS.md.

6. Report

**Target**: #NUM — [title]
**Root cause**: [brief explanation]
**Fix**: [what changed and why]
**Test**: [what the test verifies]
**Files changed**:
- path/to/file.rs — [change description]

Do not commit unless explicitly asked.

Handling Disagreements (PR mode)

If you disagree with a review comment:

Explain your reasoning with evidence
Propose an alternative if applicable
Use AskUserQuestion to discuss before proceeding

Never silently ignore review feedback.

---name: snarkvm-fixdescription: Fix GitHub issues or PR review feedback in snarkVM using TDD workflow. WHEN: User says "fix issue", "fix #123", "fix pr", "fix PR feedback", "address review comments", "resolve review threads", or wants to fix a bug/feature request from GitHub issues or address reviewer requests. WHEN NOT: Doing security review (use snarkvm-review), fetching context only (use snarkvm-github), or working on non-snarkVM code.---# Fix Issue or PR FeedbackFix snarkVM GitHub issues or PR review comments using test-driven development.## Usage```/snarkvm-fix issue <number>/snarkvm-fix pr <number>```## Setup```bashMODE="${ARGUMENTS%% *}" # "issue" or "pr"NUM="${ARGUMENTS#* }" # the numberWS=".claude/workspace"SKILL_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../snarkvm-github" && pwd)"```## 1. Load Context**For issues:**```bashif [[ ! -f "$WS/state-issue-$NUM.md" ]]; then "$SKILL_DIR/scripts/fetch-issue.sh" "$NUM"fi```Review: `$WS/state-issue-$NUM.md` and recent comments.**For PRs:**```bashif [[ ! -f "$WS/state-pr-$NUM.md" ]]; then "$SKILL_DIR/scripts/fetch-pr.sh" "$NUM"fi"$SKILL_DIR/scripts/refresh-threads.sh" "$NUM"```Review: `$WS/state-pr-$NUM.md`, `$WS/unresolved-pr-$NUM.json`, and `$WS/handoff-pr-$NUM.md` if present.## 2. Investigate**For issues** — search for related code. Answer:1. What is the expected vs actual behavior?2. Where does the code path go wrong?3. What are the edge cases?**For PRs** — analyze each unresolved comment:| # | Path:Line | Reviewer | Request | Type | Risk ||---|-----------|----------|---------|------|------|**Where to look:**- Console type bugs -> `console/` (types, program, network)- Circuit bugs -> `circuit/` (must stay in sync with console)- Synthesizer bugs -> `synthesizer/` (program execution, VM, process)- Crypto bugs -> `algorithms/` (Poseidon, Marlin, Polycommit)- Serialization bugs -> check `ToBytes`/`FromBytes`/`Serialize`/`Deserialize` impls**Think hard. Do not proceed until you understand the root cause or each request.**## 3. Plan (APPROVAL REQUIRED)Present a concrete plan:| # | Location | Change | Test | Risk ||---|----------|--------|------|------|**Use AskUserQuestion to get explicit approval before proceeding.**## 4. Implement (TDD)For each change:1. **Write failing test** that reproduces the bug or covers the new behavior2. **Verify it fails**: `cargo test -p <crate> -- test_name --nocapture`3. **Implement minimal fix** — match existing code style4. **Verify it passes**: `cargo test -p <crate> -- test_name --nocapture`For pure style/nit fixes (no behavioral change), batch them without tests.## 5. Final ValidationValidate affected crates per AGENTS.md.## 6. Report```**Target**: #NUM — [title]**Root cause**: [brief explanation]**Fix**: [what changed and why]**Test**: [what the test verifies]**Files changed**:- path/to/file.rs — [change description]```**Do not commit unless explicitly asked.**## Handling Disagreements (PR mode)If you disagree with a review comment:1. Explain your reasoning with evidence2. Propose an alternative if applicable3. **Use AskUserQuestion** to discuss before proceedingNever silently ignore review feedback.

Frequently asked questions