agentleFS
ProvableHQProvableHQ/snarkVM/.claude/skills/snarkvm-fix/SKILL.md

snarkvm-fix

Skill1.2k starsChanged 21 days agoApache-2.0View on GitHub

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.

Trending

More talk lately.about the whole repository

Dec 2025: 2 mentionsJan 2026: 2 mentionsFeb 2026: 1 mentionMar 2026: 1 mentionApr 2026: 1 mentionMay 2026: 3 mentionsJun 2026: 4 mentionsJul 2026: 3 mentionsAug 2026: 7 mentionsSep 2026: 7 mentionsOct 2026: 8 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the ProvableHQ/snarkVM repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about ProvableHQ/snarkVM

The biggest 5 of 50 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 50

Talked about on GitHub (50 times).

On GitHub · 50

45 more on GitHub

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If you disagree with a review comment:

    line 111
  2. Distinctive:

    Never silently ignore review feedback.

    line 116

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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:

  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:LineReviewerRequestTypeRisk

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:

#LocationChangeTestRisk

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 behavior
  2. Verify it fails: cargo test -p <crate> -- test_name --nocapture
  3. Implement minimal fix — match existing code style
  4. 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:

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

Never silently ignore review feedback.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.