Software Development Skills

Use to create or polish repo agent context files: README.md, AGENTS.md/CLAUDE.md symlinks, and existing project .agents/skills/SKILL.md files. Updates existing skills only; do not create skills.

Use to retrospect on a task against historical Codex and Claude Code chat transcripts in the current project, identify recurring agent mistakes, and recommend or apply durable fixes such as AGENTS.md updates or new skills.

Use when the user asks to "update dependencies", "update npm packages", "bump dependencies", "upgrade node packages", "check for outdated packages", "update package.json", or mentions dependency updates, npm/pnpm/yarn/bun package upgrades, or taze CLI usage.

Execute automated release workflow for Rust projects using Conventional Emoji Commits. Analyze commits since last release, determine semantic version bump (MAJOR/MINOR/PATCH), update Cargo.toml, generate changelog with git-cliff, create git tags, and publish GitHub releases. Use when the user requests to cut a release, bump version, create a release, or publish a new version. Also use when the user asks about the release process or wants to preview what the next release would be.

Use when the user asks to "send a transaction", "call a contract", "sign a message", "use cast", "cast send", "cast call", "cast wallet", "decode calldata", "encode ABI", "check balance", or mentions Foundry cast CLI, RPC endpoints, or on-chain interactions.

Use when the user mentions "gh CLI", "gh command", asks to "view repository info", "trigger workflows", "search GitHub", "manage codespaces", "check PR status", "list issues", "browse repo", or asks about GitHub CLI usage and automation from the command line.

Use when the user asks to "create a justfile", "write just recipes", "configure just settings", "add just modules", "use just attributes", "set up task automation", mentions justfile, just command runner, or task automation with just.

Use when the user asks to "polish code", "simplify and review", "clean up and review code", "full code polish", "simplify then review", "refactor and review", "simplify and fix", "clean up and fix", or wants a combined simplification and review workflow on recently changed code.

Simplify code by consolidating duplicates, removing dead code, and flattening unnecessary abstractions. Use when the user asks to simplify, refactor, dedupe, or clean up code. Keywords: simplify, refactor, dedupe, dead code, flatten abstractions, cleanup.

Use when the user asks for crypto prices, market data, market cap, trending coins, historical or OHLC data, token lookup by contract address, coin search, token logos, global crypto stats, or mentions CoinGecko API.

Use for CoinGecko/cg CLI crypto market data: prices, market cap, trending coins, top gainers/losers, coin search, historical data, or OHLC.

Use to open CoinGecko historical-data pages in the default browser for a coin/date or to show historical price on date X.

Communication retrospective — honest analysis of where user and Claude failed each other this…

Use when the user asks to create a monochrome technical diagram, schematic, or systems/architecture diagram in black-and-white line-art style. Trigger phrases include "create a diagram", "monochrome diagram", "systems diagram", "draw a schematic".

Use when the user asks about Effect-TS patterns, services, layers, error handling, service composition, or writing/refactoring code that imports from 'effect'. Also covers Effect + Next.js integration with @prb/effect-next.

Use when the user asks to "check ETH balance", "query ERC-20 balance", "get wallet balance", "check token holdings", "find first funding transaction", "trace fund origin", "who funded this address", "query Etherscan", or mentions Etherscan API, blockchain balance queries, multi-chain balance lookups, or wallet provenance tracing.

Use for targeted EVM chain, account, transaction, RPC, explorer, and bridge data: chain name/ID, native symbol, RouteMesh, balances, token/NFT holdings/transfers, tx history, funding origin via Etherscan/Blockscout/Chainscout; Bungee, LayerZero, LI.FI, Socket enrichment.

Use when the user asks to resolve an EVM chain name or chain ID, find chain metadata such as a default public RPC or native currency symbol, determine whether a chain is supported by RouteMesh, or needs chain resolution before fetching data from or interacting with an EVM chain.

Use when the user asks to squash a feature branch's commits into one and rebase onto the base branch. Trigger phrases include "squash commits", "squash branch", "flatten branch history", "prepare a clean PR commit".

Explicit-only meta skill for running another agent skill repeatedly, defaulting to 3 iterations, with one final net report.

Manages project documentation: CLAUDE.md, AGENTS.md, README.md, CONTRIBUTING.md. Use when asked to update, create, or init these context files.

Use when the user asks to consult Codex/GPT for planning or code review, or wants a second opinion on code. Trigger phrases include "ask Codex", "consult Codex", "second opinion on code", "consult the oracle". NOT for implementation tasks.

Use only when explicitly invoked to rename a GitHub upstream repo and matching local project folder, update the local origin remote, and preserve Codex CLI and Claude Code thread continuity references.

Use to audit Agent Skills catalogs or installed skill roots: validate SKILL.md frontmatter, Codex openai.yaml metadata, README catalog coverage, cli- version pins, and relative resource links; optionally apply conservative --fix-safe metadata repairs.