blockscout

Investigate the intended scope of a codebase topic through discussion with a human, propose a research-note outline, and only create a .memory-bank/research file after explicit human confirmation.

Turn an approved task analysis and selected solution into a technical design and coding-ready handoff under `tmp/tasks/<task-name>/`, with explicit human confirmation before the coding task is written.

Draft or refresh a reviewer-facing Markdown PR description from `tmp/tasks/<task-name>/` and the current implementation snapshot, covering functional scope, API/config, migration, testing, and follow-ups.

Investigate and clarify a reusable codebase topic through dialogue, then create or update a `.memory-bank/research` note only after explicit human confirmation.

Review applied changes against the original task and artifacts under `tmp/tasks/<task-name>/`, identify scope mismatches, regressions, and verification gaps, and write a review before handoff or merge.

Analyze a non-trivial task against the current codebase, persist task framing and viable solutions under `tmp/tasks/<task-name>/`, align tradeoff criteria with a human, and recommend a path.

Implement a prepared `tmp/tasks/<task-name>/coding-task-X.md` exactly, validating the result without inventing missing scope or design decisions.

Turn an approved task analysis and selected solution into a technical design and coding-ready handoff under `tmp/tasks/<task-name>/`, with explicit human confirmation before the coding task is written.

Create or finalize a pull request — three modes: placeholder draft PR at spec time, finalize a draft into ready-for-review, or a regular PR right away for work done outside the task workflow.

Create a GitHub deployment for the current branch using the deploy-review workflow

Land a finished product task — prune the working files (keep spec.md), flip the draft PR to ready, run the review loop, deploy the spec's demos, report.

Grill a product task (GitHub issue) into implementable work.

Close out review findings — adjudicate each one, fix what deserves fixing, then reply on the PR threads or in the task's review file.

Run the review loop on an open PR — a headless reviewer round, an autonomous resolver, a CI wait and fix, repeated until the review is cleared and CI is green; pauses only on a `needs-human` finding.

Turn the current conversation into a product-task spec and publish it as a draft PR: no interview, just synthesis of what you've already discussed.

Step-by-step checklist for adding a new NEXT_PUBLIC_* environment variable. Use when introducing any new runtime env var.

Export the survived comments from a completed implementation-plan review into a timestamped Markdown findings artifact. Use when the user asks to save, write, or export plan-review comments/findings under…

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,…

Manually review a feedback file produced after implementation-plan review findings were addressed. Use when the user asks to verify that plan changes correctly close, correctly reject, or fail to close the original findings, while checking for newly…

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.

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…

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…

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" -…

Describe very high level changes required to implement discussed functionality (functionality, test, docs)

Ensure that aliases are alphabetically ordered within their groups to maintain consistent code style and address Credo readability warnings.

Use when refactoring Elixir multi-clause functions, extracting helper functions, or fixing Credo readability warnings caused by placing `defp` helpers between clauses of the same function. Keeps function clauses contiguous and moves helpers below the full…

Create, adjust, or inspect OpenAPI declarations for Blockscout API v2 endpoints. Use this skill whenever the user asks to: add an OpenAPI spec to an endpoint that lacks one, update a spec after controller/view changes, audit or fix an existing OpenAPI…

Ensure every newly introduced environment variable is also added to docker-compose/envs/common-blockscout.env so local Docker setups stay aligned with runtime configuration.

Replace `with` expressions that contain only a single `<-` clause and an `else` branch with a `case` expression. This addresses the Credo warning "with contains only one <- clause and an else branch, consider using case instead" and produces cleaner, more…

Use when working on Elixir code with Credo predicate naming warnings, boolean helper functions, or renaming functions that start with is_. Prevents violations like: Predicate function names should not start with 'is' and should end in a question mark.

Define module aliases at the top of the file instead of using fully qualified nested module names in function bodies. Improves code readability and maintainability while addressing Credo style warnings.

Fixes code formatting in the Blockscout Elixir project using mix format. Use when you need to fix formatting violations, code style inconsistencies, or ensure consistent code formatting. For linting issues, use `mix credo`. Use this skill for every change…

MANDATORY — invoke this skill BEFORE making any Blockscout MCP tool calls or writing any blockchain data scripts, even when the Blockscout MCP server is already configured. Provides architectural rules, execution-strategy decisions, MCP REST API conventions…

Refresh the bundled Blockscout API reference files inside one of this repo's end-user skills. Takes a target argument; each target has its own pipeline because the source artefacts differ (Swagger releases for `blockscout-analysis`, a build-time clone of the…

Build web3 applications, scripts, CLIs, bots, mobile apps, and desktop apps that need blockchain data via the Blockscout PRO API — a single HTTP API spanning 100+ EVM chains. Invoke this skill whenever the user wants to read blockchain data over HTTP…

Bump a skill's version number across all files in this repo (the skill's own frontmatter, the marketplace plugin entry, and any skill-specific occurrences). Pass the skill name and new version as arguments (e.g., 'blockscout-analysis 0.5.0'). Use after…

Update Blockscout backend environment-variable docs from a PR. Use when adding, changing, removing, or deprecating backend environment variables.