Skip to content
Agentmart
Submit a tool

expectations-checklist

Operator wishlist checklist seeded at /dr-prd or /dr-plan; verified at /dr-qa and /dr-compliance with BLOCKED routing on missed/partial without override.

Skill by Arcanada-one

IndexedMIT★ 16
Write a review

Chalk Labs

Need help deploying expectations-checklist?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/arcanada-one-expectations-checklist

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Operator wishlist checklist seeded at /dr-prd or /dr-plan; verified at /dr-qa and /dr-compliance with BLOCKED routing on missed/partial without override.

Use cases: testing, security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/expectations-checklist

What's inside

Skill name
expectations-checklist
Description
Operator wishlist checklist seeded at /dr-prd or /dr-plan; verified at /dr-qa and /dr-compliance with BLOCKED routing on missed/partial without override.
License
MIT
Instructions
552 lines in SKILL.md · view on GitHub

Before installing

  • Instructions call the network

Agent Skills spec issues

  • body: 552 lines (spec recommends under 500)

Files (2)

  • SKILL.md
  • deferral-phrases.txt

SKILL.md (first lines)

# Expectations Checklist

> **Why this exists.** The init-task file (see `init-task-persistence.md`)
> preserves the operator's *prompt*. The expectations file preserves the
> operator's *acceptance test* — what the operator wants to verify when the
> work comes back. Each item is one human-readable wish: "did this aspect of
> the task come out the way I asked?" Without it, agents run their own
> `/dr-qa` checks against PRD acceptance criteria, which are an agent's
> paraphrase of operator intent and can drift silently.
>
> Expectations are written in the resolved artifact language, one bullet per wish, with a verifiable success
> criterion and an advisory cross-link to a PRD acceptance criterion when
> one exists. `/dr-qa` and `/dr-compliance` assign each item a status
> (`met` / `partial` / `missed` / `n-a` / `deleted`); `partial` or `missed`
> without an operator-supplied override blocks the pipeline and routes work
> back to `/dr-do` with the offending wish-ids in focus.

## File location and naming

```
datarim/tasks/{TASK-ID}-expectations.md
```

One file per task. Same `{TASK-ID}` as the corresponding
`{TASK-ID}-task-description.md` and `{TASK-ID}-init-task.md`. The three
artefacts form a sibling triad:

| File | Author | Purpose |
|------|--------|---------|
| `{ID}-init-task.md` | operator (verbatim) | the original prompt |
| `{ID}-task-description.md` | planner | the agent's interpretation + implementation notes |
| `{ID}-expectations.md` | architect (L3+) / planner (L2 no PRD) | the operator's acceptance test |

## When the file is created

| Complexity | Stage | Agent | Trigger |
|-----------:|-------|-------|---------|
| L3, L4 | `/dr-prd` | architect | after PRD acceptance criteria are finalised |
| L2 (no PRD) | `/dr-plan` | planner | after plan acceptance is finalised |
| L1 | — | — | not required (optional; soft window applies) |

Expectations are **canonical first**, **append-merge after**. The first write
creates the file from PRD/plan AC plus the operator's init-task brief. Later
edits (operator amendments, new AC, scope changes) append new items at the
bottom; existing items are not rewritten — instead a History entry records
the transition.

## Artifact schema

Required YAML frontmatter (closed schema):

```yaml
---
task_id: <TASK-ID>          # ^[A-Z][A-Z0-9]{1,9}-[0-9]{4}$ — required
artifact: expectations      # literal — required
schema_version: 4           # integer — required (current: 4; legacy: 1-3)
captured_at: <YYYY-MM-DD>   # date of first write — required
captured_by: /dr-init       # /dr-init | /dr-prd | /dr-plan — required
status: canonical           # canonical | amended — required (flips on first append)
agent: planner              # architect | planner — recommended
parent_init_task: <path>    # relative path to init-task file — recommended
parent_prd: <path>          # relative path to PRD file when one exists
---
```

**Schema v4 (current default):** requires exactly one
`customer_derived: true | false` field on every wish. The obsolete
`customer_binding_from` marker is rejected because a movable prefix can exempt
previously governed wishes. See § Customer-requirement binding.

**Schema v3 (legacy, accepted):** adds optional per-wish `verification_mode` and
`evidence_artifact` fields distinguishing a one-off manual check from a
reproducible/wired check. See § `verification_mode` axis. Only active when the
file declares `schema_version: 3` or `4`; all sub-v3 files are unchanged.

**Schema v2 (legacy, accepted):** adds required `evidence_type` field per wish item
(enum: `empirical | static | measurement`). Validator
(`"${DATARIM_RUNTIME:?}/dev-tools/check-expectations-checklist.sh"`) rejects items without
`evidence_type` in v2 mode.

**Schema v1 (legacy):** accepted by validator until **2027-05-23** (12 months
from the v1→v2 migration archive). Deprecation warning emitted on every validator
invocation. Migration recipe: add `evidence_type: empirical` (or
`static`/`measurement`) to each wish; bump `schema_version: 2`.

**Migration note — author new files at v4.** `/dr-prd` (and `/dr-plan` for the
L2-no-PRD path) MUST create new expectations files at `schema_version: 4`.
v1-v3 remain accepted for read and verification without customer-binding
fields, but MUST NOT receive new wishes. Before the first append, perform an
explicit metadata-only migration: preserve every existing body, title, history,
order, and `wish_id`; add `evidence_type` where v1 lacks it; add
`customer_derived` to every wish and the conditional binding quartet to each
`true` wish; then bump to schema v4, set `status: amended`, and record the
migration in the append-log. Only then append the new wish. v1 keeps its
**2027-05-23** sunset and deprecation warning.

## Body shape

English presentation is the template default. Localize prose/title/section labels
in the resolved artifact language. Keep field keys and status enums below stable.
Use `<!-- datarim:expectations -->` on a translated Expectations H2. Legacy
Russian field/heading aliases remain readable without rewriting history.
Historical English labels are also accepted: `Operator expectations`,
`Status history`, `Current status`, `How to verify (success criterion)` and
`Related AC from PRD`. Both validators normalize only these known labels to
the canonical keys. New files keep the canonical ASCII keys; arbitrary heading
translations use the Expectations marker below. A wish may link to several
acceptance criteria, and every link must resolve in the spec graph. Wishes in
the exact `Append-log (operator amendments)` and `PRD append-merge` sections
receive the same structural and status validation as the initial checklist.


```markdown
# {TASK-ID} — Operator expectations

## Expectations <!-- datarim:expectations -->

- **<N>. <Plain-language title ending with a period>**
  - wish_id: <stable ASCII kebab-slug; preserve existing legacy IDs>

From Arcanada-one/datarim, MIT.

More from Arcanada-one/datarim

Signals

Stars
16
Forks
1
Open issues
0
Last commit (this folder)
Oct 19, 2026 (11 days ago)
Last release
Oct 22, 2026 (9 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Arcanada-one

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get expectations-checklist running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying expectations-checklist?

CallGet help
Cite this page

expectations-checklist skill. Agent Mart. https://agentmart.dev/skills/arcanada-one-expectations-checklist (last updated 2026-10-24)