the deterministic authoring path
website-brief
Agents do not invent structure — they instantiate it. Each skeleton below is a complete, valid workflow with # SLOT: markers at every decision point: route your intent, copy, fill the slots, nika check, done. Machines read the same pack at /templates/catalog.json; the originals live in the spec, conformance- gated on every push.
- 10skeletonsroute · copy · fill
- 94slot markersthe only blanks
- validevery fileconformance-gated
- sha256every copypinned, re-proven
take data, produce words, save them
- deterministic gather
- one model job
- explicit persist
watch X, act when Y
- jq extraction
- CEL skip-gate
- often zero model calls
do this for EVERY item
- runtime collection
- the full leash (max_parallel
- fail_fast
- retry)
only what changed since last run · survive bad input
- state read→diff→write
- `on_error: recover:` quarantine
research / review / open-ended
- plan-then-execute
- default-deny tools
- budgets
- typed final message
anything irreversible (deploy · send · publish)
- parallel gates
- assert
- `nika:prompt` GO
- `on_finally` record
understand a site (domain · theme · assets) from a URL
- fetch `traverse:` crawl
- one typed infer
- explicit persist
- zero exec
website-brief.nika.yaml# SPDX-License-Identifier: Apache-2.0# yaml-language-server: $schema=https://nika.sh/spec/v1/workflow.schema.json## TEMPLATE · website-brief · crawl a site → understand it → persist the brief.# The shape for « understand a site (domain · theme · assets) from a URL ».## Instantiate (agents · deterministic) ·# 1. Copy this file · rename per the job (kebab-case).# 2. Fill every `# SLOT:` line · delete slot comments when filled.# 3. Validate · `nika check <file>` (or conformance/runner.py validate).# 4. Repair using the error's fix line · re-check until valid.# Native-first · the crawl is `traverse:` (no curl · no helper script);# the brief is one typed infer; the persist is `nika:write`. Zero exec.nika: v1workflow: website-brief-template # SLOT: kebab-case workflow iddescription: "crawl → brief → persist" # SLOT: one honest sentencemodel: ollama/qwen3.5:4b # SLOT: provider/model · local · zero keyvars: site_url: "https://example.com" # SLOT: the site to understand out_path: "./out/brief.json" # SLOT: where the brief landstasks: - id: crawl_site invoke: tool: "nika:fetch" args: url: "${{ vars.site_url }}" traverse: { max_pages: 5 } # SLOT: crawl bound · 1..=25 (robots honored) - id: brief depends_on: [crawl_site] infer: max_tokens: 1200 prompt: | # SLOT: the one model job · what should the brief capture? From this site crawl, produce a creative brief: the domain of activity, the dominant visual theme, the audience, the usable colors and image assets. Crawl digest · ${{ tasks.crawl_site.output }} schema: # SLOT: the typed shape downstream tasks rely on type: object additionalProperties: false properties: domain: { type: string } theme: { type: string } audience: { type: string } colors: { type: array, items: { type: string } } assets: { type: array, items: { type: string } } required: [domain, theme, audience, colors, assets] - id: persist depends_on: [brief] invoke: tool: "nika:write" args: path: "${{ vars.out_path }}" create_dirs: true content: "${{ tasks.brief.output }}" # ALWAYS pass contentoutputs: brief: ${{ tasks.brief.output }} # SLOT: the callable contractsha256 c9ca853a728703f1… · conformance-gated upstream · source
generate image/audio assets from a brief
- `nika:image_generate`
- `nika:jq` manifest
- local/mock provider first
call a product API: upload a file, then create from it
- fetch `multipart:` upload
- masked secrets header
- mode/jq extraction
read a system's state (docker · kubectl · gh), explain it, keep the report
- argv-array exec (provable allowlist)
- parallel reads
- exec ledger
- one artifact
The protocol is mechanical: route with the phrases above, instantiate, fill the slots, then nika check teaches anything you missed before anything runs. Try one in the playground, or install and start from a real file. Read the spec →