원클릭으로
describe-changes
Describe very high level changes required to implement discussed functionality (functionality, test, docs)
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Describe very high level changes required to implement discussed functionality (functionality, test, docs)
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | describe-changes |
| description | Describe very high level changes required to implement discussed functionality (functionality, test, docs) |
| disable-model-invocation | true |
This skill composes a concise description of changes required to implement the feature or fix the issue discussed in the conversation. The purpose is to confirm the agent's understanding of the scope and what files will be modified.
When invoked, this skill generates a structured description of all changes needed to address the discussed issue/feature. This description serves as a confirmation that the agent:
MANDATORY: Before listing ANY file in the changes description, you MUST read that file first using the Read tool.
Why this matters:
Verification checklist before including a file:
If you have NOT read a file, you MUST read it before including it in the description.
Identify from the conversation:
Before proceeding, use the Read tool to examine:
DO NOT SKIP THIS STEP. Reading files is not optional - it's the core purpose of this skill to ensure accurate understanding.
Create a Markdown document with the following sections:
## Changes Description
### Functional Changes
[List each file with a brief description of what will change]
- `path/to/file.py`: [What will be modified and why]
- `path/to/another_file.py`: [What will be modified and why]
### Test Changes
[List unit test files that need to be created or modified]
- `tests/tools/category/test_feature.py`: [New tests or modifications needed]
### Integration Test Changes
[List integration test files if applicable, or state "No integration test changes required"]
- `tests/integration/category/test_feature_real.py`: [New tests or modifications needed]
### Documentation Changes
[List documentation files including AI-coding agent artifacts]
- `SPEC.md`: [What sections need updating]
- `AGENTS.md`: [Project structure updates if applicable]
- `.cursor/rules/xxx.mdc`: [Rule file changes if applicable]
- `API.md`: [API documentation updates if applicable]
### Project Artifacts
[List non-functional project files like configuration]
- `pyproject.toml`: [Dependency or metadata changes if needed]
- Other configuration files as applicable
## Changes Description
### Functional Changes
- `blockscout_mcp_server/tools/transaction/get_pending_txs.py`: New tool implementation for fetching pending transactions with pagination support
- `blockscout_mcp_server/tools/common.py`: Add helper function for pending transaction status normalization
- `blockscout_mcp_server/server.py`: Register the new `get_pending_txs` tool
### Test Changes
- `tests/tools/transaction/test_get_pending_txs.py`: Unit tests covering success scenarios, error handling, pagination, and edge cases
### Integration Test Changes
- `tests/integration/transaction/test_get_pending_txs_real.py`: Integration tests with real network calls to verify pending transaction retrieval
### Documentation Changes
- `AGENTS.md`: Add new tool module to project structure
- `SPEC.md`: Document the new tool's behavior and API contract
- `.cursor/rules/110-new-mcp-tool.mdc`: No changes needed (existing rule covers new tools)
### Project Artifacts
- No changes required
When the user says:
/describe-changes
You should:
Validate review findings about an implementation plan against the codebase and repo rules, fix the valid ones in the plan, and write a feedback file noting what changed and what was rejected (and why). For plan-review findings, not code-review findings.
Expert review of an implementation plan against a GitHub issue/enhancement description (provided as a local file or a GitHub issue URL) and the current repository codebase. Use when asked to critique a plan for correctness, completeness, codebase alignment, risks, and test/rollout readiness (do not implement).
Manually review a feedback file produced after implementation-plan review findings were addressed. Use when the user asks to read a findings-feedback file and verify that the plan changes correctly close, correctly reject, or fail to close the original implementation-plan-review findings, while checking for newly introduced or newly exposed plan problems. Writes only new findings to the plan-id findings directory and replies with the output file path or a concise no-new-findings status.
Use this skill whenever the agent needs to deploy a smart contract to Sepolia testnet via Foundry (`forge create` or `forge script --broadcast`), routed through the Blockscout PRO API's JSON-RPC gateway instead of a third-party RPC provider. Trigger on requests like "deploy this contract to Sepolia", "deploy via Foundry", "broadcast this Foundry deployment script", or any `forge create`/`forge script` invocation that needs a signer and an RPC endpoint for Sepolia (chain id 11155111) in this project. Also consult it to find which local Foundry keystore to sign with — this project stores test signing keys as encrypted keystores under `.ai/wallet/`, never as a plain private key in `.env`. Do not use this for reads (balances, transaction history, contract info) — use the connected Blockscout MCP tools for those directly; this skill is specifically about broadcasting a deployment.
Enter the worktree of a GitHub PR, validate the code-review comments raised on it against what the code actually does and the repo rules, fix the valid ones directly in the PR's source/tests, and report in chat — a brief note per closed comment and a detailed plain-language explanation of every comment left unclosed and why. For code-review comments on a PR. Invoke manually.
TRIGGER CONDITIONS - invoke this skill when ANY of these apply: User-triggered (explicit request): - User mentions "specification", "SPEC", "SPEC.md", "spec requirements" - User asks to "verify with spec", "confirm with specification", "check requirements" - User requests "authoritative requirements" or "source of truth" Agent self-triggered (during reasoning): - Before implementing any feature or making code changes - When verifying technical requirements or constraints - When making architectural or design decisions - When you need unbiased guidance not influenced by current implementation - When encountering conflicting information and need ground truth PURPOSE: Consults SPEC.md through an isolated subagent that ONLY reads the specification, never implementation code. This ensures guidance is based on authoritative requirements, not potentially incorrect existing code.