Back to authors
agenta-ai

agenta-ai

45 Skills published on GitHub.

write-docs

Use when writing or editing documentation pages (concept pages, how-to guides, API reference prose, tutorials) under docs/. Provides the writing style, voice, and structural rules for Agenta docs. Apply this skill before drafting any new docs page, and include it in the brief for any subagent tasked with writing docs.

UncategorizedView skill →

mobile-motion-patterns

Motion design rules for the Agenta mobile app (web/mobile) — the shared presets in src/lib/motion, when to animate, and reduced-motion requirements. Use when adding any animation or transition under web/mobile, animating navigation, sheets, skeletons, or list/chat surfaces.

UncategorizedView skill →

mobile-shadcn-conventions

How the Agenta mobile app (web/mobile) installs and extends shadcn/ui registry components, themes them via the palette token bridge, and builds chat UI on @agenta/chat. Use when adding UI components under web/mobile, changing theme colors, editing components.json or globals.css, or building chat UI.

UncategorizedView skill →

create-changelog-announcement

Use this skill to create and publish changelog announcements for new features, improvements, or bug fixes. This skill handles the complete workflow - creating detailed changelog documentation pages, regenerating the in-app What's New data, and ensuring everything follows project standards. Use when the user mentions adding changelog entries, documenting new features, creating release notes, or announcing product updates.

UncategorizedView skill →

add-announcement

Helps add announcement cards to the sidebar banner system. Use when adding changelog entries, feature announcements, updates, or promotional banners to the Agenta sidebar. Handles both simple changelog entries and complex custom banners.

UncategorizedView skill →

sync-findings

Sync the findings record against local review artifacts and optionally a GitHub PR. Accept optional `path` and GitHub PR `url`; when `url` is provided, sync against both remote PR state and local state, otherwise default to local-only sync. Default to `path=infer`. Confirm effective variables before starting.

UncategorizedView skill →

prospect-research

Research a prospective company and prepare a short, source-backed fit assessment.

UncategorizedView skill →

content-briefing

Create or revise an evidence-backed SEO brief for owner approval before scaffolding or drafting.

UncategorizedView skill →

content-planning

Prioritize content opportunities or a small cluster and decide create versus update from business fit, demand evidence, existing coverage and proof.

UncategorizedView skill →

content-production

Scaffold, draft, revise and prepare assets from an approved brief using existing owner playbooks. Preserve approved text and designer assets.

UncategorizedView skill →

content-refresh

Diagnose outdated or declining content and prepare or execute a scoped refresh through briefing, production and review, without implicit republishing permission.

UncategorizedView skill →

editorial-seo-review

Check facts, editorial quality, positioning, SEO, links, attribution, visuals and conversion before the owner's publish-readiness decision.

UncategorizedView skill →

learn-business-context

Learn the purpose, audience and context of a business or website through public research, useful private materials and conversation with its owner. Use for onboarding or updating that understanding.

UncategorizedView skill →

market-competitor-research

Research competitors' SEO and content strategies: blog topics, intent, ranking keywords and top pages where data is available. Identify search competitors and opportunities for useful content.

UncategorizedView skill →

technical-seo-audit

Inspect crawlability, indexability, rendering, canonicals, redirects, links, schema and mobile/performance problems. Report evidence, not automatic production changes.

UncategorizedView skill →

add-harness

Playbook for adding a new coding-agent harness to Agenta (Codex, Hermes, Gemini, OpenCode, ...). Use when starting, planning, or reviewing a new-harness project. Covers the readiness audit of prior art, the spike-first milestone plan, the full integration-surface checklist, the per-harness variance axes to probe, and the process/communication contract with Mahmoud. Living document: every harness project appends its lessons to resources/LESSONS.md.

UncategorizedView skill →

agent-release-gate

>-

UncategorizedView skill →

agenta-package-practices

Where to put frontend code (package vs the web/mobile app layer) and how to use the @agenta/* packages. Use when authoring or moving code in web/packages, choosing which @agenta/* package owns something (ui, entities, entity-ui, shared, chat, sessions, playground, the *-ui domain packages, ...), using molecules, the loadable bridge, the EntityPicker, or writing package unit tests.

UncategorizedView skill →

design-interfaces

Design and review interface parameters by semantic role: classify each field by what it IS (data, config, policy, credentials, routing, metadata, protocol context), who owns it, when it changes, and whether a standard name exists, not by the feature it vaguely relates to. Use when designing or reviewing ANY interface shape - API request/response params, wire/protocol fields, config schemas, tool definitions, event payloads, function signatures with option bags. Triggers - designing a new endpoint/wire field/config block, reviewing a PR that adds or changes interface fields, "review the interfaces", any plan-feature/implement-feature step that defines or changes a contract.

UncategorizedView skill →

gitbutler-stacks

Hard-won GitButler mechanics for multi-lane work in this repo — committing to a specific lane in a stack, spreading a pile of edits back across an existing stack, ordering a stack and setting PR bases, and recovering from a scrambled workspace. Use when working with stacked branches, when `but rub`/`but absorb`/`but commit --only` mis-routes a change, when a stack collapses or a commit lands on the wrong lane, or when a hunk gets dropped. Not needed for ordinary single-lane work.

UncategorizedView skill →

implement-feature

Drive a researched and planned feature to a landed, tested change. Use after plan-feature has produced a docs/design/<project>/ workspace and the user says "implement it", "build the plan", "run the plan", or "let's ship this". Orchestrates refresh-plan, implement, review, a debug-local-deployment loop, and a test loop across the daytona / local-pi / claude x SDK / UI matrix, then documentation and a GitButler stacked branch. The orchestrator stays in the loop and spins narrow subagents for each phase.

UncategorizedView skill →

keep-docs-in-sync

Keep documentation in sync with a code or contract change in the SAME PR. Use whenever you change an interface, wire field, endpoint, config field, default, harness/backend value, or runtime behavior, and after any implement-feature slice that lands such a change. Triggers - "keep docs in sync", "update the docs too", "the docs drifted", "document this change", "did we update the inventory". Maps a change to every doc that describes it (design docs, the agent-workflows documentation/ pages, the interface inventory + its index, AGENTS.md, skills) and enforces one source of truth.

UncategorizedView skill →

mobile-app-structure

Feature-folder layout, states/ convention, and data-flow rules for the Agenta mobile app (web/mobile). Use when creating or moving files under web/mobile, deciding where a component lives, adding a new feature or screen, or wiring data into mobile components.

UncategorizedView skill →

naming-and-resources

Pick and record the names of a new concept in every layer (database table and column, ORM model, DTO, route, JSON field, UI label), and give every stored item kind the same resource shape and the same actions. Holds the glossary format with an Avoid list, the per-layer name table, the resource template, standard and custom actions, field, enum, state and owner rules, the Agenta convention table, the folder naming rule, and the spec naming checklist. Use when writing or changing a spec, design or plan that adds or renames a table, column, index, route, DTO field, enum value, config field or UI label, when asked "what should this be called", "is this name consistent", "fill the naming section", or when another skill asks for the per-layer names. It applies even when the word "naming" never appears. Do not use it for field grouping by role (use design-interfaces), for migration errors, or for a rated review (use review-naming).

UncategorizedView skill →

plain-writing

>-

UncategorizedView skill →

planner-feature

Create a plan for a feature, and the files required to continue working on it. Use when the user asks for research for a feature or a plan to run it.

UncategorizedView skill →

prepare-pr-review

Prepare a plain-language PR review briefing from a GitHub pull request URL or number. Use when the user says "help me review this PR", "summarize this PR for review", "what does this PR do", or wants the reason, systems involved, changes, risks, CI state, and questions needed before reviewing a pull request.

UncategorizedView skill →

resolve-findings

Resolve findings by implementing the chosen fix path in code, tests, or docs. Accept optional `path` and a `priority` selector; by default resolve only the next highest remaining priority bucket, in order `P0`, `P1`, `P2`, `P3`. Also accept explicit levels or `all`. Default to `path=infer`. Confirm effective variables before starting.

UncategorizedView skill →

review-correctness

Review one code change for correctness and rate it Low, Medium, or High. Looks for bugs, regressions in existing behavior, broken flows, concurrency and retry problems, and migrations that can fail or lose data. Use when asked to "review this PR for bugs", "check this diff for regressions", "is this change correct", or when a review loop runs the correctness lens. Read-only; it reports findings and does not fix them.

UncategorizedView skill →

review-naming

Review one code change, or one design (an OpenSpec change, a spec draft or an architecture doc), for naming, consistency and layering, and rate it Low, Medium, or High. Looks for one concept with several names across layers (table, column, DTO, route, JSON field, UI label), one word with two meanings, enum values from mixed schemes, names that mislead, item kinds or owner levels that break the shared resource pattern, singular and plural folder pairs, and layering faults such as pass-through layers, one decision in several places, rules that only one entry point checks, and doubtful public surface. Each finding cites the rule it breaks. Use when asked to "review the naming", "check this spec for consistent names", "is this PR consistent with our conventions", "review this PR that changes a contract", or when a review loop runs the naming lens. Read-only; it reports findings and does not fix them.

UncategorizedView skill →

review-simplify

Review one code change, or one design (an OpenSpec change or an architecture doc), for needless complexity and rate it Low, Medium, or High. Looks for scope that could be narrower, edge cases that do not deserve machinery, state kept in several places, boundaries that only forward, and code or design parts whose reason to exist is gone. Use when asked to "simplify this diff", "is this overbuilt", "review this PR for simplicity", "review this spec or design for simplicity", or when a review loop runs the simplify lens. Read-only; it reports findings and does not fix them.

UncategorizedView skill →

review-slop

Review one code change for agent slop and rate it Low, Medium, or High. Slop is avoidable, low-trust work that comes from not understanding the repo, such as wrong assumptions, broken flows, duplicate systems, weak tests, comment noise, and leftover dead code. Use when asked to "review this diff for slop", "check this PR for slop", "is this change sloppy", or when a review loop runs the slop lens. Read-only; it reports findings and does not fix them.

UncategorizedView skill →

discover-and-wire-tools

Use find_capabilities to discover the right Agenta tools for an agent you are building, report what each integration needs to connect, and wire the tools into the new agent's config. Use when a setup/builder agent must turn a plain-language task ("post to Slack and open GitHub issues") into attached, connected, ready-to-run tools.

UncategorizedView skill →

scan-codebase

Perform a fresh-context scan of code and docs that turns verification observations and missing-test gaps into findings. Accept optional `path` and `depth` parameters and default to `path=infer`, `depth=deep`. Confirm effective variables before starting.

UncategorizedView skill →

style-editing

Apply Joseph Williams' clarity principles when writing or editing prose. Use when drafting technical or business writing, diagnosing unclear sentences, rewriting passive or abstract prose, or any time the user references Williams, "Style: Lessons in Clarity and Grace," or "Style: The Basics of Clarity and Grace."

UncategorizedView skill →

sync-model-catalog

Refresh Agenta's harness catalogs, provider model lists, recommended defaults, and provider-supplied display names. Use for new OpenAI, Anthropic, Codex, Pi, or OpenRouter models and before releases that need current model choices.

UncategorizedView skill →

test-codebase

Run or inspect the relevant validation paths and turn failures, regressions, or missing coverage into findings. Accept optional `path` and `depth` parameters and default to `path=infer`, `depth=deep`. Confirm effective variables before starting.

UncategorizedView skill →

triage-findings

Coordinate findings work with the user, decide whether scan, test, or sync should run, and turn the current findings set into a ready plan. Accept optional `path` and GitHub PR `url`; default to `path=infer`. Confirm effective variables before starting.

UncategorizedView skill →

update-api-docs

Update the API reference documentation by downloading the latest OpenAPI spec from production and regenerating the Docusaurus API docs

UncategorizedView skill →

update-llm-model-list

Audit and update the supported LLM model list in assets.py against litellm's registry (models.litellm.ai). Use when adding new models, pruning outdated ones, or verifying the list is correct.

UncategorizedView skill →

write-issue

Write and file Linear issues (bugs and feature requests) the Agenta way. Use when the user asks to create, file, or draft a Linear or GitHub issue, write a bug report or feature request, or turn a problem into a tracked issue. Covers the title format, reproduction-first structure, when to use a todo list, and the team/project/label/priority/state conventions, plus filing it through the Linear MCP so the linked GitHub issue is auto-created and the PR links back.

UncategorizedView skill →

write-pr-description

Write PR titles and descriptions the way a staff engineer would. Use when drafting or editing a pull request title and body, before running `gh pr create`, or any time the user asks for a PR description, summary, or release-notes-style writeup of a change. Apply this skill from the start, not as a cleanup pass after a generic first draft.

UncategorizedView skill →

write-template-playbooks

>-

UncategorizedView skill →

agenta-apps

>-

UncategorizedView skill →

tavily-job-search

Use when searching the web for job openings, comparing job-board search strategies, validating listings, and extracting job details with Tavily.

UncategorizedView skill →