Reusable agent skills library for Codex, Opencode, and Hermes agents
Skill Codex
Run daily API drift checks for backend and external market-data dependencies, compare latest contracts against stored baseline, and report potential future crash risk before provider/API changes break runtime logic.
Skill Codex
Publish API drift results as admin-only feedback messages in database. Use when daily drift check finishes and you need immediate admin notification (including no-change heartbeat) without sending to all users.
Skill Codex
Use when the user wants to push the latest finance--tracker changelog into the production in-app release-note stream after a deploy. This skill verifies GitHub release state, compares the previous stable release with the new one, drafts a short user-facing summary, runs the publish script, and confirms the server now…
Skill Codex
Use when the user wants to SSH into the finance--tracker production server, inspect the live repo, run remote git pull or docker compose commands, or verify backend, worker, nginx, Postgres, and Redis on production.
Skill Codex
Use when the user wants to publish a finance--tracker version end to end in one run: verify the changelog version, create or verify the GitHub release, deploy main to the server, run health checks, and push a short in-app release note with user-facing bullets.
Skill Codex
Use when the user wants to update, redeploy, or verify the finance--tracker server. This skill standardizes preflight checks, risk classification, backup decisions, docker compose deployment, and post-deploy verification for the production nginx + backend + worker + Postgres + Redis stack.
Skill Claude CodeCodex
Process the watchlist ingest manifest — read raw/daily-digest/ingest-manifest.json, run the standard Ingest workflow for each high-score (≥8) raw source file, update domain registries, and commit. Use when Hermes processes the daily auto-ingest queue.
Skill Claude CodeCodex
Ultra-compressed communication mode. Cuts token usage 75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
Skill Codex
A release workflow for writing a changelog and publishing a software version, including matching the version and tag and creating a GitHub release.
Skill Codex
Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.
Skill Claude CodeCodex
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Skill Claude CodeCodex
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Skill Codex
Use when the task involves reading, creating, or editing .docx documents, especially when formatting or layout fidelity matters; prefer python-docx plus the bundled scripts/renderdocx.py for visual checks.
Skill Claude CodeCodex
Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
Skill Codex
One-by-one feedback triage and approval gate for admin feedback queues. Use when running daily review of unresolved feedback, requiring exactly one question at a time, draft implementation plan/patch/reply, and waiting for explicit command 批准并执行.
Skill Codex
A skill for applying approved feedback changes to code after an explicit approval command has been validated.
Skill Codex
A workflow for sending approved administrator replies to feedback and then closing those feedback items through existing API endpoints.
Skill Codex
Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.
Skill Codex
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use gh to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.
Skill Claude CodeCodex
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Skill Claude CodeCodex
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Skill Claude Code
Compact the current conversation into a handoff document for another agent to pick up.
Skill Claude CodeCodex
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: