Agent skills for software development, debugging, code review, and implementation. Browse reusable SKILL.md agent workflows and prompt templates in this category. Each card links to when-to-use notes and setup steps.
Pick up any workstream mid-flight, in any harness, when the session that was carrying it stops — usage exhausted, a crash, a handoff to another person or another assistant. Identifies the workstream's plan, derives present state from the record and the repo rather than asserting it, carries the operator's standing instructions and the hard constraints that hold regardless of workstream, and hands back a report in the operator's format. Asserts nothing it has not just checked; anything it cannot verify it reports as unverified. Written to work as a skill in Claude Code or Cursor and as a plain document pasted into a harness that has no skill mechanism at all.
Advance, test, refute, or independently review machine-checked work in elizaOS/proximityprize's Delta Star proximity-gap programme. Use when an agent is asked to solve formal mathematics, implement Lean proofs, validate a research lane, improve executable checks, or prepare evidence for contribution-share review toward the external Proximity Prize.
Implement, test, diagnose, or independently review mission-critical work in elizaOS/eliza, with optional public payout registration. Use when an agent is asked to improve the shipped Eliza app, Eliza Cloud, the core agent runtime, or a primary capability on an existing product path; prove one authorized outcome; publish a device-signed project token receipt; or register a public Solana payout address.
Open a high-quality pull request with a standardized description (Problems / Solutions / UX improvements / Documentation / Test plan / Breaking changes), the changeguardrailsrules.md pre-PR checklist enforced, and thorough functional-change documentation under docs/ surfaced via the docs server and docs site. Use this whenever a PR is about to be opened — directly via /createpr or as a sub-step of /processissues, /processprs, /release, /fixfeaturebug.
Builds and evolves enterprise-quality CSS Design Systems based on Chameleon web components. Use when the user wants to create, scaffold, or evolve a DS, add components/tokens/themes. Triggers on: 'design system', 'DS', 'design tokens', 'theme system', 'build a DS', 'scaffold DS', 'create design system'.
CI/CD pipelines, Docker, Kubernetes, and infrastructure as code. Use when configuring deployment pipelines, containerization, or cloud infrastructure. Do NOT use for fixing application code - delegate code issues to appropriate specialists.
Verify and proofread C code with ACSL using this repository's Frama-C MCP workflow, Frama-C WP static proof, EVA alarms, and optional E-ACSL runtime checks. Use when asked to run Frama-C, check ACSL contracts, explain WP goals, inspect EVA alarms, validate C annotations, or state what a C proof does and does not establish.
Use scripts/connectors/gsc.py as the only executable surface for Google Search Console work. Keep this skill as an instruction layer: do not copy the connector into the skill, reimplement its API calls, or broaden its OAuth scope.
Run the toolkit's security commands in order to surface secrets, MCP supply-chain issues, install drift, release provenance gaps, and untrusted-code risks before shipping. Use before opening a PR, after adding a dependency, or whenever the security posture needs a fresh check.
Show places, directions and day plans on a map in the thread. Use when the user asks what is near a place (restaurants, cafés, a pharmacy, shops of a kind), how to get from A to B (walk, metro, car, bike), where something is, or to lay out a day or a trip on a map.
Generate an explore-prompt.md file that gives Momentic's explore agent (momentic ai explore diff / momentic ai explore latest) repo-specific context — which applications to test, the URLs tests must target, how to authenticate, where to save generated tests, and repo quirks. Use when setting up or improving the prompt file passed via --prompt-file.
Momentic is an end-to-end testing framework where each test is composed of browser interaction steps. Each step combines Momentic-specific behavior (AI checks, natural-language locators, ai actions, etc.) with Playwright capabilities wrapped in our YAML step schema. When these tests are run, they produce results data that can be used to analyze the outcome of the test. The results data contains metadata about the run as well as any assets generated by the run (e.g. screenshots, logs, network requests, video recordings, etc.). Your job is to use these test results to classify failures that occurred in Momentic test runs.
Discovery for an autonomous loop — find this turn's work instead of being handed it. Reads what changed since the last run (failed CI, new issues, merged commits), judges what's actually worth acting on, writes findings to a durable state file, and hands each off to the SDLC loop with a stop-condition. Use as the first move of a scheduled loop, or by hand to plan a session. Read-only on code; never edits, opens PRs, or merges.
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style transition', 'animated slide sequence', 'shape continuity across slides'. Output is a single .pptx. This skill is a scene layer on top of officecli-pptx — inherits every pptx v2 rule (visual floor, grid, palettes, connector canon, Delivery Gate 1–5a). DO NOT invoke for a generic deck, pitch deck, or board review without cross-slide motion — route those to officecli-pptx base or officecli-pitch-deck.
Use when working in, operating, extending, integrating, documenting, or debugging OpenGeni: the session-based agent service with an API, durable event log, Temporal worker, sandboxed OpenAI Agents SDK runtime, file/object storage, MCP tools, scheduled tasks, and self-hosted local stack. Trigger this skill for questions about OpenGeni architecture, client-side API integration, sessions/events, worker orchestration, sandbox backends, file uploads, tools/MCP, scheduling, storage, GitHub integration, configuration, deployment, or how to keep agents using OpenGeni correctly as the repo evolves.