agentsclimarketplace

Spec agent

Skill itential/builder-skills/.claude/skills/spec-agent

Use this skill to start any new automation delivery — when someone wants to automate something, build a new use case, figure out requirements, write up an HLD, or kick off a project on the Itential Platform. Trigger it for phrases like "I want to automate X", "help me build a workflow for Y", "we're starting a new automation project", "I need to define requirements for Z", "kick off a delivery", or "let's start with requirements". This is the entry point for the spec-driven delivery lifecycle. It picks from 22 built-in use case specs or starts from scratch, refines requirements with the engineer, and produces an approved customer-spec.md. Use it whenever someone is at the beginning of building something new and hasn't yet defined what they're building. For ad-hoc platform exploration, use /explore instead. Hands off to /solution-arch-agent after approval.From its SKILL.md

Install
npx -y skills add itential/builder-skills --skill spec-agent

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 13 stars13 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

6.6 KB, as published. Nobody here has run it

Spec Agent

Stage: Requirements Owns: Defining what needs to be built. Producing the approved HLD. Hands off to: /solution-arch-agent


Stage Expectations

Engineer providesUse case description, business context, scope constraints
Agent doesRefines requirements, clarifies scope, defines acceptance criteria, structures the HLD
Engineer actionReviews and approves the requirements spec
Deliverablecustomer-spec.md (HLD, approved)
Customer receivesApproved statement of what will be built — scope, constraints, acceptance criteria. Nothing is assessed or built until this is signed off.

Requirements defines what is needed. Nothing is built or assessed until this is approved.

No auth. No API calls. Pure conversation.


How to Begin

/spec-agent
    │
    ├── Deliver from Spec → Pick spec → Fork → Refine → Approve → /solution-arch-agent
    │
    └── Already set up? → Reuse existing working directory

If the engineer wants to explore the platform freely (browse adapters, try tasks, build freestyle), direct them to /explore instead.


Step 1: Pick a Spec

Present available specs from ${CLAUDE_PLUGIN_ROOT}/spec-files/, grouped by category:

CategorySpecs
NetworkingPort Turn-Up, VLAN Provisioning, Circuit Provisioning, BGP Peer, VPN Tunnel, WAN Bandwidth
OperationsSoftware Upgrade, Config Backup, Health Check, Device Onboarding, Device Decommissioning, Change Management, Incident Remediation
SecurityFirewall Rules, Cloud Security Groups, SSL Certificates
InfrastructureDNS Records, IPAM Lifecycle, Load Balancer VIP, Config Drift Remediation, Compliance Audit

Or the engineer describes what they need and you recommend a spec.


Step 2: Fork the Spec

mkdir -p {use-case-name}
# Only fork if it doesn't already exist — engineer may have customized from a previous session
[ ! -f {use-case}/customer-spec.md ] && cp ${CLAUDE_PLUGIN_ROOT}/spec-files/spec-port-turn-up.md {use-case}/customer-spec.md

If {use-case}/customer-spec.md already exists, reuse it — do not overwrite.

If the engineer provided credentials or a .env file exists, save it to {use-case}/.env for later use during Feasibility. Do NOT authenticate yet.


Step 3: Understand and Refine

Read {use-case}/customer-spec.md and extract:

  • Phases from Section 3 (workflow stages)
  • Design decisions from Section 4 (constraints)
  • Capabilities and Integrations tables from Section 7
  • Discovery questions from Section 7
  • Acceptance criteria from Section 9

Ask: "Do you have existing documentation I should follow? Naming conventions, change policies, runbooks, config standards?"

Write to {use-case}/customer-context.md if provided.

Then go through the spec's discovery questions — skip anything the spec already answers, ask only what the engineer must decide.

Incorporate all input into {use-case}/customer-spec.md:

  • Added requirements → Section 7
  • Changed scope → Section 5
  • Business rules → relevant sections
  • Changed decisions → Section 4

Step 4: Present for Approval

Show the engineer the updated spec:

  • Summary of changes from the generic spec
  • What's in scope vs out of scope
  • Discovery question answers captured

Ask: "Here's your spec. Review it — add, remove, or change anything. When you approve it, I'll hand off to the Solution Architecture Agent."

When the engineer approves: the spec is locked. Save the file.


Step 5: Set Expectations and Hand Off

Tell the engineer what happens next:

"Requirements are locked. Here's the rest of the delivery:

  1. Feasibility — The Solution Architecture Agent connects to your platform and assesses what's possible against your approved spec.
  2. Design — A solution design is produced with exactly what to build, reuse, and skip. You approve it before anything is built.
  3. Build — The Builder Agent implements the approved design and tests each component individually.
  4. Test — The QA Agent drafts a test plan from your acceptance criteria, which you approve before anything runs live, then verifies the delivered solution against it with real evidence.
  5. As-Built — What was actually delivered is recorded, backed by that test evidence, including any deviations and learnings.

You own approval at Feasibility, Design, and the Test Plan. Nothing gets built or tested live without your sign-off."

Artifact-based handoff. The workspace the Solution Architecture Agent receives:

{use-case}/
  customer-spec.md     ← approved HLD (Requirements complete)
  .env                 ← credentials (if provided)
  customer-context.md  ← business rules, naming (if provided)
  use-case-memory.md   ← create from helpers/use-case-memory.md, set Stage: feasibility, Status: active

Create use-case-memory.md at handoff — populate the use-case name, one-sentence description, and Stage: feasibility / Status: active. The solution-arch-agent will add platform refs and adapter details during feasibility, and update Stage again at its own handoff; the builder will add asset IDs and decisions during build.

No auth. No platform data. /solution-arch-agent owns everything from Feasibility onward.


Files Created

FilePurpose
customer-spec.mdApproved HLD — the source of truth for this delivery
.envCredentials saved for later auth during Feasibility
customer-context.mdBusiness rules and naming conventions (if provided)
use-case-memory.mdLiving context file — initialized here, updated throughout all stages

Keep looking

Skills are one crate of 628,853. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.