agentleFS
hushh-labshushh-labs/hushh-research/.agents/skills/backend/SKILL.md

backend

Skill40 starsChanged 4 days agoApache-2.0View on GitHub

Use when the request is broadly about backend runtime, API routes, services, agents, or protocol package behavior and the correct backend specialist skill is not yet clear.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use devops, security and 5 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • mrgoonieSkill

    devops

    Deploy to Cloudflare (Workers, R2, D1), Docker, GCP (Cloud Run, GKE), Kubernetes (kubectl, Helm). Use for serverless, containers, CI/CD, GitOps, security audit.

    Also in 4 projects that use this

  • 0xSeroSkill

    security

    Also in 7 projects that use this

  • MicrosoftSkill

    help

    Entry point for the MedImageInsight plugin, covering the getting-started walkthrough, how the skills work, what MI2 is, and troubleshooting.

    Also in 3 projects that use this

  • OpenAISkill

    supabase

    Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector).

    Also in 3 projects that use this

  • VercelSkill

    deploy

    Deploy applications to Vercel. Use when the user says "deploy", "deploy to Vercel", "push to production", "deploy my app", or "go live".

    Also in 3 projects that use this

  • NVIDIASkill

    testing

    Run Python and Rust tests for physicsnemo-curator using uv + pytest with coverage reporting via pytest-cov, and cargo-nextest for Rust tests. Includes benchmark workflows with pytest-benchmark and criterion.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Avoid overlap with security-audit, repo-operations, and repo-context.

    line 12
  2. Distinctive:

    Keep backend docs, tests, and boundary contracts aligned when the underlying rule changes.

    line 57
  3. Very specific:

    If the user explicitly wants a visible OS terminal window, prefer ./bin/hushh terminal backend --mode local --reload as the primary backend …

    line 59
  4. Very specific:

    If the task begins as a cross-domain scan, start with repo-context.

    line 68

“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Hussh Backend Skill

Purpose and Trigger

  • Primary scope: backend-intake
  • Trigger on broad backend requests across runtime routes, services, agents, protocol docs, tests, and package surfaces.
  • Avoid overlap with security-audit, repo-operations, and repo-context.

Coverage and Ownership

  • Role: owner
  • Owner family: backend

Owned repo surfaces:

  1. consent-protocol/api
  2. consent-protocol/hushh_mcp
  3. consent-protocol/tests
  4. consent-protocol/docs
  5. consent-protocol/scripts
  6. packages/hushh-mcp

Non-owned surfaces:

  1. docs-governance
  2. security-audit
  3. repo-operations

Do Use

  1. Broad backend intake before the correct backend spoke is clear.
  2. Requests spanning API routes, service boundaries, backend tests, agents, and backend package surfaces.
  3. Choosing whether the work belongs to runtime governance, API contracts, agents/operons, or the MCP developer surface.

Do Not Use

  1. Trust, IAM, vault, or audit work where security is the primary domain.
  2. CI/deploy/env parity work that belongs to repo-operations.
  3. Broad repo mapping before the domain itself is known.

Read First

  1. consent-protocol/README.md
  2. consent-protocol/docs/README.md
  3. docs/architecture/system.md
  4. docs/development/repository-map.md
  5. docs/architecture/pod-data-door.md

Workflow

  1. Decide whether the task belongs to runtime governance, API contracts, agents/operons, or the MCP developer surface.
  2. Keep backend docs, tests, and boundary contracts aligned when the underlying rule changes.
  3. Route IAM, consent, vault, PKM, and audit-heavy issues into security-audit when those are the real ownership surface.
  4. If the user explicitly wants a visible OS terminal window, prefer ./bin/hushh terminal backend --mode local --reload as the primary backend path.
  5. Local runtime uses three separate terminals (no combined stack command): ./bin/hushh proxy --mode local, ./bin/hushh backend --mode local --reload, and ./bin/hushh web --mode local. Use the ./bin/hushh terminal proxy|backend|web wrappers only when a visible OS terminal window is explicitly preferred.

Handoff Rules

  1. Route route and service-boundary work to backend-runtime-governance.
  2. Route proxy/backend contract work to backend-api-contracts.
  3. Route agents, operons, and ADK surfaces to backend-agents-operons.
  4. Route @hushh/mcp and developer API/package work to mcp-developer-surface.
  5. If the task begins as a cross-domain scan, start with repo-context.

Required Checks

./bin/hushh protocol --help
cd consent-protocol && python3 -m pytest tests -q

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.