agenticos

In the author's own words, from each skill's SKILL.md — showing the first 30 of 94 files.

• agent-capability

  Add or change what an agent can do — a new tool the model can call, a new capability (knowledge, web search, charts, a guardrail, a compaction strategy), a tool rename, or a per-tool approval gate. Use whenever the ask is "give the agent a new tool/function/action", "add a capability", "let the agent do X". There is no @agent.tool and no assistant module in this project; every tool arrives throug…

  .claude/skills/agent-capability/SKILL.md on GitHub (opens in a new tab)

• agent-spec

  Change the agent spec — add or remove a field, rename one, tighten a rule, bump SPEC_VERSION, change publish-time validation, or touch YAML export/import. Use whenever editing app/agents/spec.py or anything that reads a stored spec. Every published agent and every client git repository holds a copy of this format, so a change that only works forwards breaks agents nobody touched.

  .claude/skills/agent-spec/SKILL.md on GitHub (opens in a new tab)

• alembic-migration

  Change the PostgreSQL schema with Alembic — add or alter a table, column, index or constraint, backfill data, or tighten a rule on a column that already holds rows. Use whenever a SQLAlchemy model changes, and whenever a validation rule narrows on a field stored as JSON. A model change without a migration passes the unit suite (sessions are mocked) and breaks on real Postgres.

  .claude/skills/alembic-migration/SKILL.md on GitHub (opens in a new tab)

• backend-tests

  Write or extend the backend Python test suite — a unit test for a service, an integration test against a real Postgres, an API test through the FastAPI app, or the test a bug fix needs. Also for "coverage is failing", "make test is red", and deciding which of the four layers a test belongs in. Uses anyio (not pytest-asyncio) and a 100% coverage gate on the platform layer.

  .claude/skills/backend-tests/SKILL.md on GitHub (opens in a new tab)

• background-task

  Add or change work that runs outside the request/response cycle — document ingestion, MCP refresh, reports, cleanups, scheduled jobs — or debug a task that vanished with nothing in the logs. Use when something is slow or fire-and-forget, when adding a periodic job, and before reaching for asyncio.create_task (which drops work silently in this codebase's exact failure mode).

  .claude/skills/background-task/SKILL.md on GitHub (opens in a new tab)

• channel-bot

  Work with messaging-channel bots — Telegram, Slack or Mattermost. Register a bot, route inbound messages through an agent, choose webhook vs polling, handle an @slug mention, or add a new channel adapter. Use when wiring chat into a messaging platform or debugging bot delivery, identity linking or "the bot answered as itself".

  .claude/skills/channel-bot/SKILL.md on GitHub (opens in a new tab)

• dev-agent

  AI development agent. Opens a development branch and a stacked design branch up front, drives design and a general implementation plan to a reviewed, merged PR before any code exists, then — once merged — writes tests and the implementation on the development branch with review considered, without pushing. Portable across repos — detects the project's own test runner, source/test layout, branch n…

  .claude/skills/dev-agent/SKILL.md on GitHub (opens in a new tab)

• e2e-tests

  Write or fix a Playwright end-to-end test in frontend/e2e — a new journey spec, a seeded fixture, or debugging "the e2e suite passes but the feature is broken" / "make test-e2e fails". Use for any spec that crosses the whole stack (sign in, build an agent, publish, run, approve). Every page in this product renders its empty state when a query fails, so a spec that asserts on chrome is a spec that…

  .claude/skills/e2e-tests/SKILL.md on GitHub (opens in a new tab)

• frontend-feature

  Build or change a page, view or data-driven feature in the Next.js frontend — a route under the dashboard, wiring UI to a backend endpoint, a Zustand store, a permission that must hide a control, or localized copy. Use for any work in frontend/src, including "the page renders but shows an empty state" and "this button should not be visible to a Viewer".

  .claude/skills/frontend-feature/SKILL.md on GitHub (opens in a new tab)

• mcp-connections

  Work with MCP servers — connect one, add an entry to the server catalog, debug "the agent cannot see my MCP tools" or a failing OAuth flow, or change how connections are probed, prefixed or filtered. Use when the ask involves an external SaaS tool (GitHub, Linear, Notion, Slack, Stripe, Postgres…) and before writing a capability that would just be an API client for one.

  .claude/skills/mcp-connections/SKILL.md on GitHub (opens in a new tab)

• permissions-rbac

  Gate a route or a service on who may do it — add a permission, wire a role, decide between require() and resolve_access, share a resource with a grant, or debug "this user can see something they should not" and "a Viewer with an edit grant is being refused". Use for any authorization work, any new org-scoped route, and any review of one. There is no UserRole, RoleChecker or CurrentAdmin in this p…

  .claude/skills/permissions-rbac/SKILL.md on GitHub (opens in a new tab)

• pr-comments

  Use this skill when user asks to address PR review comments. It will fetch all comments, present them in a structured format.

  .claude/skills/pr-comments/SKILL.md on GitHub (opens in a new tab)

• pr-description

  Create or update PR. Use this skill every time user asks to create or update a PR to ensure clear, consistent descriptions between PRs.

  .claude/skills/pr-description/SKILL.md on GitHub (opens in a new tab)

• project-docs

  Write or fix the documentation site — add a page, update one after a behaviour change, fix a dead link or a failing docs build, add a diagram or an icon, or wire a new page into the nav. Use whenever docs/ or mkdocs.yml is touched, and whenever a code change alters behaviour a page describes. make docs-build runs --strict, so a dead link fails CI.

  .claude/skills/project-docs/SKILL.md on GitHub (opens in a new tab)

• rag-knowledge

  Work with the knowledge base — ingest documents, run semantic search, manage collections, add a sync connector (Google Drive, S3), change a parser or an ingestion setting. Use when populating or debugging retrieval, when a document upload fails or dies silently in a worker, or when "the agent cannot find something that is definitely in the collection". pgvector + per-organization embedding keys.

  .claude/skills/rag-knowledge/SKILL.md on GitHub (opens in a new tab)

• resolve-changelog-conflict

  Resolve a merge conflict in CHANGELOG.md by detecting the file's own convention (Keep a Changelog per-version sections, monthly sections, a single [Unreleased] bucket, or another format) and folding the other side's entries into it. Use whenever git reports a conflict in CHANGELOG.md, or when entries in an older format need folding into the current one.

  .claude/skills/resolve-changelog-conflict/SKILL.md on GitHub (opens in a new tab)

• review-map

  On-demand visual walkthrough of a pull request for a reviewer — projects the diff onto the system architecture map (changed components highlighted, before/after flows, suggested reading order) and publishes it as a private HTML artifact. Use when a diff is too large or system-touching to hold in your head while reviewing.

  .claude/skills/review-map/SKILL.md on GitHub (opens in a new tab)

• ste-writing

  Rewrite prose (docs, READMEs, PR descriptions, error messages, release notes, comments — never code) into ASD-STE100 Simplified Technical English. Use when asked to make writing not sound like AI, make docs clear or plain, enforce a controlled writing style, or write technical documentation that reads human. Two modes — strict (procedures/safety) and STE-flavored (general prose).

  .claude/skills/ste-writing/SKILL.md on GitHub (opens in a new tab)

• vault-secrets

  Store, read or rotate a credential — a provider API key, a channel bot token, an MCP token, a third-party service key — or add a new secret kind. Use whenever a change touches a credential at rest, whenever something needs to be encrypted, and whenever reviewing code that could leak a plaintext key into a response, a log line or an audit entry. Everything seals through app/core/vault.py; there is…

  .claude/skills/vault-secrets/SKILL.md on GitHub (opens in a new tab)

• vstorm-code-review

  High-signal, convergent code review for any repository. Runs a staged pipeline of subagents (Scope → Correctness → Security → Quality → Verification → Judge), one dedicated subagent per angle, all grading against one shared finding taxonomy, so every candidate is raised, filed, or refuted with proof — never silently re-surfaced after a fix. Accepts an optional `model` argument (default Claude Opu…

  .claude/skills/vstorm-code-review/SKILL.md on GitHub (opens in a new tab)

• artifact-pages

  How to build a page to publish with publish_artifact - the served library set, the house style and its components, icons instead of emoji, two templates, and how to change a page later.

  backend/app/core/catalog/skills/artifact-pages/SKILL.md on GitHub (opens in a new tab)

• code-review

  How this organization reviews a change, and what a review must not let through.

  backend/app/core/catalog/skills/code-review/SKILL.md on GitHub (opens in a new tab)

• incident-report

  How to write up an incident so the next person can act on it, not just read it.

  backend/app/core/catalog/skills/incident-report/SKILL.md on GitHub (opens in a new tab)

• refund-policy

  When a refund is given without asking, when it needs approval, and how to say no.

  backend/app/core/catalog/skills/refund-policy/SKILL.md on GitHub (opens in a new tab)

• abandoned-cart-follow-up

  Write a follow-up that answers the objection rather than repeating the offer.

  backend/app/core/catalog/skill_gallery/ecommerce/abandoned-cart-follow-up/SKILL.md on GitHub (opens in a new tab)

• inventory-alerting

  Turn stock levels into a small number of decisions with a lead time attached.

  backend/app/core/catalog/skill_gallery/ecommerce/inventory-alerting/SKILL.md on GitHub (opens in a new tab)

• order-status-answers

  Answer where-is-my-order from the order and carrier record, and say what happens next.

  backend/app/core/catalog/skill_gallery/ecommerce/order-status-answers/SKILL.md on GitHub (opens in a new tab)

• print-file-validation

  Check an artwork file against the press requirements and say exactly what to fix.

  backend/app/core/catalog/skill_gallery/ecommerce/print-file-validation/SKILL.md on GitHub (opens in a new tab)

• product-description-writer

  Write listing copy from the spec sheet, without inventing an attribute.

  backend/app/core/catalog/skill_gallery/ecommerce/product-description-writer/SKILL.md on GitHub (opens in a new tab)

• returns-and-exchanges

  Decide a return without asking, know what needs a person, and refuse with a next step.

  backend/app/core/catalog/skill_gallery/ecommerce/returns-and-exchanges/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• rufloby ruvnet 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems.… 75.1k stars · 30 skills
• paperclipby paperclipai The open-source app everyone uses to manage agents at work 103k stars · 30 skills
• claude-code-best-practiceby shanraisshan from vibe coding to agentic engineering - practice makes claude perfect 67.6k stars · 9 skills
• agentsby wshobson Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi 40.9k stars · 30 skills
• invisible_dotsby feder-cr Open-source, self-hosted alternative to OpenAI Dots, Grok Bot. Built to be undetectable by anti-bot systems. 32.1k stars · 1 skill
• distillyby titanwings Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）. 25.7k stars · 1 skill