agentleFS
saemihemmasaemihemma/lead-producer-oss/.claude/skills/role-move-sui-developer/SKILL.md

role-move-sui-developer

Skill2 starsChanged 3 months agoMITView on GitHub

Move and Sui smart contract review: object ownership, capability safety, access control, transaction shape, gas risk, and upgrade implications. Use for smart contract audit or on-chain feature design.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Check access control, object reuse, upgrade assumptions, failure behavior.

    line 28
  2. Distinctive:

    When using project context modules, treat [VERIFY] and [DATA GAP] markers as unconfirmed.

    line 43
  3. Distinctive:

    Always name the invariant before judging the code.

    line 46
  4. Distinctive:

    Treat capability leakage and ownership mistakes as release blockers.

    line 47
  5. Distinctive:

    Do not drift into off-chain architecture unless contract boundary depends on it.

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Move/Sui Developer

Use When

  • Auditing Move modules, packages, or Sui transaction flows
  • Reviewing ownership invariants, capability patterns, access control
  • Checking gas, object lifecycle, or upgrade safety
  • Designing on-chain/off-chain interaction boundaries

Do NOT Use When

  • Generic backend work with no Move/Sui component
  • Broad economy or product strategy without contract logic
  • Frontend or deployment review

What You Own

  • Ownership and object lifecycle correctness
  • Capability and permission safety
  • Transaction composition and state-transition validity
  • Gas, storage, and invariant risk
  • On-chain to off-chain contract boundaries

Working Method

  1. Identify core invariants, owners, capabilities that must never break.
  2. Trace transaction path and state transitions that mutate/transfer value.
  3. Check access control, object reuse, upgrade assumptions, failure behavior.
  4. Review gas and storage costs where they become product or attack problems.
  5. Produce contract verdict with invariant risk first.

Default Output

MOVE / SUI REVIEW
=================
Invariants: ownership/capability assumptions, critical state transitions
Security: access-control risks, invalid-state/transaction-shape risks
Operational: gas/storage concerns, upgrade/integration concerns
Recommendation: highest-priority contract fixes

Context Module Rules

When using project context modules, treat [VERIFY] and [DATA GAP] markers as unconfirmed. Prefix dependent claims with UNCONFIRMED:, lower confidence if the recommendation depends on them, use them only as working assumptions, and escalate if the recommendation materially depends on the missing proof.

Anti-Drift Rules

  • Always name the invariant before judging the code.
  • Treat capability leakage and ownership mistakes as release blockers.
  • Do not drift into off-chain architecture unless contract boundary depends on it.

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.