Gougoubi Claim All Rewards

Claim all Gougoubi rewards for one or more addresses, including winner rewards, governance rewards, and LP rewards. Use when users want one-click claiming wi...

Security Scan

The skill's description matches its goal (one‑click reward claiming) but its instructions reference local Node scripts and blockchain transactions while providing no install mechanism, no shipped script files, and no guidance or declared credentials for signing transactions — these mismatches are concerning.

Purpose & Capability

The name/description and SKILL.md claim a one‑click reward claimer (winner, governance, LP) which is coherent. However the skill references several local Node script entrypoints (scripts/*.mjs) that are not included in the package. The manifest points to a GitHub repo, but there is no install spec; it's unclear where the runtime code comes from.

Instruction Scope

Runtime instructions tell the agent to run node scripts to perform on‑chain claims and to record tx hashes. The SKILL.md does not explain how transactions are to be signed (no wallet/key provider, no RPC endpoints), nor where recorded data is stored. Because the instructions direct potentially destructive on‑chain actions but omit signing and storage details, the scope is underspecified and risky.

Install Mechanism

There is no install specification in the registry (instruction‑only skill). INSTALL.md and clawhub.json reference copying from a local skills folder or installing from a GitHub repo, but those are documentation only — the registry package contains no scripts. This mismatch means the agent or user would have to obtain code externally before the skill is functional.

Credentials

Claiming on‑chain normally requires signing credentials (private key, wallet, or delegated signer) and an RPC endpoint; the skill declares no required env vars or primary credential and does not describe how signing is handled. Requiring no credentials while performing transactions is disproportionate and unexplained.

Persistence & Privilege

The skill is not marked always:true, requests no persistent environment access, and provides no install hooks. There is no evidence it requests elevated or permanent privileges in the registry metadata.

What to consider before installing

Do not install or run this skill without clarifying missing pieces. Before proceeding: 1) Verify the referenced GitHub repository and inspect the scripts (scripts/*.mjs) — they are not included in the package. 2) Confirm how transactions are signed: never supply private keys directly to an untrusted skill; prefer hardware signing or an audited signer service. 3) Ask the author to provide an explicit install spec or include the scripts in the package, and a clear description of RPC endpoints, storage for tx hashes, and dry‑run behavior. 4) If you must test, run only in a sandbox/testnet environment and use --dry-run to avoid unintended on‑chain transactions. If the repository and scripts are not verifiable, treat the skill as unsafe.

Use this skill for one-click reward claiming across one or multiple addresses.

Use This Skill When

• The user wants to claim all rewards for one address or multiple addresses.
• The user explicitly wants the profile-style fast path.
• The user wants winner, governance, and LP rewards claimed together.

Do Not Use This Skill When

• The user wants to inspect missing results before claiming. Use gougoubi-recovery-ops.
• The user wants proposal activation or LP staking. Use activation skills instead.

Input

{
  "addresses": ["0x...", "0x...", "0x..."],
  "method": "profile|quick|full-scan"
}

Defaults:

• method=profile

Pipeline

Step 1: Validate all addresses.

Step 2: Pick claim method:

• profile: match the reward-detail modal behavior.
• quick: fast direct claim path.
• full-scan: exhaustive fallback only when needed.

Step 3: Run claim for each address.

Step 4: Record all tx hashes and per-type claim status when available.

Step 5: Return a full summary.

Checkpoints

• Prefer profile unless the user explicitly asks otherwise.
• Do not force slow condition scanning when the user asked for one-click claim.
• Safe re-run behavior is required.

Output

{
  "ok": true,
  "method": "profile",
  "addresses": ["0x..."],
  "claimedTxCount": 0,
  "results": [
    {
      "address": "0x...",
      "winnerRewardClaimed": true,
      "governanceRewardClaimed": true,
      "lpRewardClaimed": true,
      "txHashes": ["0x..."]
    }
  ],
  "warnings": []
}

Failure:

{
  "ok": false,
  "stage": "validation|claim|confirm",
  "error": "reason",
  "retryable": true
}

Project Scripts

• scripts/pbft-claim-rewards-profile-method.mjs
• scripts/pbft-claim-rewards-quick.mjs
• scripts/pbft-claim-three-address-rewards.mjs

Script Entry Points

• Preferred profile path: scripts/pbft-claim-rewards-profile-method.mjs
• Fast one-click path: scripts/pbft-claim-rewards-quick.mjs
• Deep scan path: scripts/pbft-claim-three-address-rewards.mjs
• node scripts/pbft-claim-rewards-profile-method.mjs --help
• node scripts/pbft-claim-rewards-profile-method.mjs --dry-run
• node scripts/pbft-claim-rewards-quick.mjs --dry-run
• node scripts/pbft-claim-three-address-rewards.mjs --dry-run

Boundaries

• Claim all three reward classes together when available.
• Keep the method explicit in the output.