with one click
describe-changes
// Describe very high level changes required to implement discussed functionality (functionality, test, docs)
// Describe very high level changes required to implement discussed functionality (functionality, test, docs)
Use this skill whenever you are about to run any write `gh` CLI command — `gh pr edit`, `gh pr create`, `gh issue edit`, `gh issue create`, `gh pr comment`, `gh issue comment`, `gh pr close`, `gh pr merge`, `gh release create`, or similar. High-level `gh` commands sometimes fail with "missing required scopes" auth errors even though the underlying GitHub REST API works fine with the same token. This skill makes you automatically fall back to `gh api` instead of stopping to ask the user to re-authenticate. Always invoke before running any mutating `gh` command.
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).
Export a detailed phased implementation plan for a GitHub issue to a file, reading all applicable rules from .cursor/rules before planning
Use to implement a structured implementation plan (e.g. temp/impl_plans/issue-*.md) phase by phase. Trigger when the user asks to implement, execute, realize, or "do" an implementation-plan file. Orchestrates a phase-developer subagent and a plan-correspondence-verifier subagent for each phase, commits each verified phase, then walks the Final Checklist. Invoke explicitly — it makes commits and spawns many subagents.
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.
Generate a structured bug report for GitHub issues based on conversation context about bugs, errors, or broken functionality
| 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: