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
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.
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.
About
Use cases: testing, security
Reviews
Write a reviewNo 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
- 0.642score
human-outcome-reporting
Arcanada-one
Explain human-facing task outcomes with requirements, evidence, honest acceptance status and read-only re-explanation, inside or outside Datarim.
SkillAFreshness: A★ 16Claude Code +9 - 0.640score
finishing-a-development-branch
Arcanada-one
Use when implementation is complete and all tests pass.
SkillAFreshness: A★ 16Claude Code +9 - 0.639score
hypothesis-validation
Arcanada-one
Use when a product decision depends on an uncertain claim and needs a bounded, falsifiable check.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
customer-delivery
Arcanada-one
Enforce delivery from a verbatim requirement through pre-work knowledge selection, production evidence, and disposition; excludes enabling-only closure.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
artifact-context
Arcanada-one
Canonical conventions for native agents generating or editing Datarim artifacts, including stage headers, frontmatter, and exact contract quotations.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
cta-format
Arcanada-one
Canonical CTA "Next Step" block format for every /dr-* command and pipeline agent.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
ai-quality
Arcanada-one
Five pillars of AI-assisted development — decomposition, TDD, architecture-first, focused work, context.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
brainstorming
Arcanada-one
MUST use this before any creative work — features, components, functionality, behavior changes.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
compliance
Arcanada-one
Post-QA hardening — detects task type (code, docs, research, legal, content, infra) and applies the matching verification checklist before archiving.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
consilium
Arcanada-one
Assemble a panel of Datarim agents for multi-perspective analysis of decisions.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
context-window-self-clearing
Arcanada-one
Preserve Datarim task continuity while orchestrated Claude Code or Codex sessions compact or clear context at deterministic pressure thresholds.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
adversarial-review
Arcanada-one
Forces an adversarial mindset on a plan, PRD, design, or code change — break it rather than bless it.
SkillAFreshness: A★ 16Claude Code +9
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
- Repository
- github.com/Arcanada-one/datarim
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Arcanada-one
- 0.642score
human-outcome-reporting
Arcanada-one
Explain human-facing task outcomes with requirements, evidence, honest acceptance status and read-only re-explanation, inside or outside Datarim.
SkillAFreshness: A★ 16Claude Code +9 - 0.640score
finishing-a-development-branch
Arcanada-one
Use when implementation is complete and all tests pass.
SkillAFreshness: A★ 16Claude Code +9 - 0.639score
hypothesis-validation
Arcanada-one
Use when a product decision depends on an uncertain claim and needs a bounded, falsifiable check.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
brainstorming
Arcanada-one
MUST use this before any creative work — features, components, functionality, behavior changes.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
artifact-context
Arcanada-one
Canonical conventions for native agents generating or editing Datarim artifacts, including stage headers, frontmatter, and exact contract quotations.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
ai-quality
Arcanada-one
Five pillars of AI-assisted development — decomposition, TDD, architecture-first, focused work, context.
SkillAFreshness: A★ 16Claude Code +9
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.
Cite this page
expectations-checklist skill. Agent Mart. https://agentmart.dev/skills/arcanada-one-expectations-checklist (last updated 2026-10-24)