Screenplay toolchain
Read preferred syntax when writing or reviewing .play.
This skill owns tool selection, verdicts and admission. Modeling method lives in
cratis-screenplay-modeling-lifecycle; syntax lives in the construct skills.
Locate the model
Decide opt-in per general.md "Model first"; where cratis-screenplay-modeling-lifecycle is installed, run its scripts/model-first-status.mjs to locate the model root. A folder of .play
files is one application: always check the folder, never one file of it.
MCP/CLI discovery reuses model/workspace roots, not code-only Source/ or src/;
otherwise use repository-root Screenplay/ (version gates and root boundaries).
Tool versions and the contract
Read the installed versions first: screenplay --version, cratis --version, and which -a cratis
(an older copy earlier on PATH shadows a newer install). The standalone tool and the compiler
bundled in the CLI are different releases, and the bundled one can be older; a construct the
standalone tool binds may be refused or unrendered through the CLI. Capabilities that need a
minimum release carry a one-line Requires ... note in the reference that teaches them.
Search screenplay-contract.json, not its
whole contents, for exact diagnostic code, tool name or cliCommands options.
Its version is screenplay-contract.version.
Read contract exceptions when a
superseded statement needs context; exceptions do not change the contract.
Ground rules
- Never invent syntax. Copy shapes from
references/cheat-sheet.md and the compiled
examples it names, or from a compiled documentation example. Construct keywords are
closed.
- Check the folder, warnings as errors.
screenplay <folder> --warnaserror or
cratis screenplay validate <folder> --warnings-as-errors. Warnings hide defects:
PLAY0029 (a misspelt keyword or a type inside a slice) drops a construct silently.
A committed screenplay.json at the model root declares the repository's gate (checks, warnings
as errors, scope, open questions): run without repeating those flags (confirm with
--print-gate before dropping --warnaserror), read it with
--print-gate, and treat a refused file as "could not run" (references/verdicts.md).
- Pick the compiler deliberately and name it. Standalone
screenplay for
language checks and reference specifications; cratis for rendering
and generation. Report both tool and version, rather than transferring a verdict across
releases.
- Know the mode (design, executable, renderable) and write from its subset.
- Capability is not correctness. The tool you ran decides what is accepted; the
domain and the documented semantics decide what is correct. On conflict keep the correct
model and record a tool gap; never reshape a model to silence a tool.
- Never remove
pii, secret, authorization, list queries, automations or rules
to reach V3 or a render. Report the verdict as blocked with the codes.
- A clean verdict proves only its own layer. "Not run" with the reason is a valid
result. Specifications written or bound are never specifications passing.
- Let the tool resolve what it can. Revisions, identities and renames come from the
tool, never from hand computation; discover tool, version and root once per session and
reuse them until the root, the tool or a call changes. Re-resolve only when a value actually
needs to change: a failed or stale call, a different model root, a changed tool, version or
configuration, or an explicit override.
The two compilers
|
Standalone screenplay |
cratis screenplay ... |
| Check root |
screenplay <root> --warnaserror --no-color |
cratis screenplay validate <root> --warnings-as-errors -o json-compact |
| Scope/checks |
--scope <address>, --check <names>; a scoped pass is not whole-application success |
validate --executable (bundled binder, no write), --check <names>, --scope; render --scope/--check; cratis screenplay conform, cratis screenplay conform-namespace |
| Declared gate |
screenplay <root> --print-gate, --format json, --no-gate-file |
validate <root> --print-gate, --no-gate-file; the same screenplay.json |
| Reference execution |
screenplay test <root> or MCP run-specifications |
Discover bundled MCP capability; target tests are not V4 |
| Version migration |
screenplay migrate <root> --from <major> [--to <major>] [--dry-run] [--report <file>] or MCP migrate (read-only); exit 2 means review |
Use the standalone tool; see cratis-screenplay-modeling-lifecycle |
| MCP |
screenplay mcp <root>; discover schemas |
cratis screenplay mcp [root]; registered by cratis ai install |
| Render boundary |
Binder admission is not Stage admission |
The CLI renders only ESM versions it knows; a newer bound model gets CLI-RENDER-004 |
Read references/verdicts.md for exact commands, exit codes, the MCP roots caveat and the model notes gate.
Requires Cratis CLI 3.57.0 or later (cratis --version) to render models that use equality filters or concept generation strategies (ESM v14 and v15); an older CLI answers CLI-RENDER-004. Requires Cratis CLI 3.74.0 for ESM v21–v26 and 3.75.0 for v27; see language admission for the v28–v30 CLI minimums. Above the CLI's ceiling, a bundled compiler that binds the construct answers CLI-RENDER-004, and one that predates it reports the binder's PLAY0268 (Uuid equality before Screenplay 4.205.0). Either way keep the rule and gap-fill.
MCP calls below use the screenplay server declared in .cratis/ai/mcp-servers.json, for example screenplay → read-workspace.
Verdicts
Independent results, not a ladder. Read references/verdicts.md for the commands and the report format when obtaining or reporting V1–V5 verdicts.
| Verdict |
Meaning |
How |
| V1 |
authorable (compiles, warnings as errors) |
the folder command above |
| V2 |
executable diagnostics read |
MCP open-workspace, then read-workspace view=executable-diagnostics |
| V3 |
binding-ready (binds, no blocking executable diagnostics) |
executableReady true and no error-severity diagnostic in V2; informational PLAY0269/0270 are reported separately |
| V4 |
reference specifications run |
screenplay test or MCP run-specifications; unsupported/unbound is not a pass; rendered Debug tests are V5.tests, never V4 |
| V5 |
rendered and target-verified |
cratis render, then Debug build and tests; report admission, publication, build and tests separately |
V2 needs MCP; V3 also supports cratis screenplay validate --executable <root>
(labeled as the bundled compiler). Read verdict commands
for MCP initialization, source identity and reporting. Without MCP, report
V2 not run: no MCP in this agent. Report each verdict separately with tool,
version, source identity and any blocking codes; MCP modelRevision is semantic,
not the source identity.
Read observation comparison when asking whether a running namespace holds what the model declares, or when reading a conform-namespace verdict. It differs from model comparison (model versus model) and conform (model versus code).
PLAY0516 ordering is presentation-only, not execution. For a wildcard-import
repair, read timeline diagnostics: replacing globs
with ordered imports means future files need explicit imports.
Subsets (write from the one your mode needs)
- Design: every construct family parses; use it to model first. Compiled shapes:
references/cheat-sheet.md. Read references/cheat-sheet-example.md when you need one complete design-mode document with every construct family.
- Executable (binds, V3):
references/executable-subset.md. Optional keyed lookups, unfiltered
lists and lists narrowed by one by key (observable too) bind; caller-supplied equality
filters on collections bind as ESM v14. Context from, single-result
filters, opaque scoped to and a by block on a list query remain PLAY0268; a performer query is an opaque read left out of the executable model (PLAY0270; version gate). Read
read-surface equality filters.
Pending handlers beside unconditional productions bind as described commands (v23),
but reached bodies are Unsupported; attached file/inline handlers bind the same way
beside unconditional produces with a resolved body and otherwise
refuse PLAY0800.
Requires Screenplay 4.210.0 (screenplay --version); older binders use PLAY0268 for this refusal. Read arguments.subject, not the message, for the command.
Eligible protected reads opt into v25; legacy reads and concurrency retain PLAY0271.
Concept compliance binds as v13 (precise refusals: command-surface references/compliance.md);
generated values and returns responses bind (ESM v7, references/generated-responses-example.md). Read references/executable-example.md when you need a small StateChange and StateView model that binds executable, references/pdl-example.md when writing projection forms that bind and run, and references/automation-translate-example.md when writing Automation and Translate slices (ESM v6).
- Renderable (V5):
references/renderable-subset.md has the admission table. The CLI admits through
its newest known ESM version to construct checks; supported UUID/String
generation/responses, enum numbers, compliance, equality filters and event reactions render.
Unsupported generated types still get STAGE-ESM-028; result combinations get -038.
Newer versions refuse CLI-RENDER-004. Run admission
before claiming a particular model renders (cratis render --scope for an admitted part, --check
for no-write planning).
- Event sources, streams and routes bind as ESM v8. Operations and exact numeric source mode remain
unadmitted. Details:
references/sources-and-streams.md.
- Public contracts and routes (v9/v10/v11): public contracts and direction select v9;
reaction identity, production overrides and observer filters select v10;
qualifying retained non-route Double literals select v11.
Flat composite read-model keys select v27 (Requires Screenplay 4.204.0; older binders
report PLAY0268); one explicit
key keeps its earlier version. Read
references/production-routes-and-filters.md, language admission
and read-surface references/named-keys.md.
- Enum numbers (v12): read command-surface
references/enum-numbers.md for
pins, stored numbers and Stage output; references/diagnostics.md owns PLAY0667–0671.
- Concept strategies (v15): read
generation strategies for Guarded
freshness and strict fixtures, and command-surface
references/generated-values-and-responses.md for strategy/refusal depth.
- v17–v21: recovery/no-events (v17), query Validation errors (v18), refusal
branches (v19), generated-concept proofs (v20), pattern/random/rule/checksum (v21).
Read
references/executable-subset.md for version prerequisites and
references/diagnostics.md for proof/support failures. Binding is not rendering.
Tool/renderer authors: read references/generation-checks.md
when discovering strategy options, checking one concept or value, or consuming rule proofs.
- v32: a
source events capture with a typed scalar key carries the key's type onto
the appended event's identity.
Requires Screenplay 4.241.0 (screenplay --version);
older compilers keep the key as Text. Read
language admission for the Stage boundary.
- v28:
==/!= between Uuid values in require and produces when select v28
(Requires Screenplay 4.205.0; screenplay --version; older binders refuse PLAY0268).
Read language admission and command-surface
references/uuid-equality.md.
- v22–v27: read language admission for atomic
batches, described handlers, text rules, protected reads, chronological command
Date/DateTime comparisons (Requires Screenplay 4.199.0;
screenplay --version;
older binders refuse PLAY0268) and Stage refusals.
Read diagnostic arguments for MCP/JSON subjects:
code and typed arguments, never message parsing.
- Caller/compliance metadata:
$identity aliases caller built-ins;
additional identity details are metadata and executable reads still refuse.
Bare pii/secret replace legacy spellings; pii personal repeats one marker
(PLAY0653). Purposes/checks/processing records and event subject are report-only,
not legal compliance, retention or runtime subject realization. See
command-surface references/context.md and references/compliance.md.
Edit strategy
Read the MCP authoring loop
when editing: the identity owner uses typed proposals for catalog-changing edits;
text edits never bypass a refusal. Without MCP, return identity-affecting work
to its owner. Proposals are connection-local; apply is not crash-atomic, and an
unknown apply outcome requires recovery, not retry.
Top traps
All 44 traps, with fixes: references/traps.md. Read references/traps.md when diagnosing an unexpected compile, binding, rendering or MCP result.
Read references/diagnostics.md when a PLAY, STAGE or CLI-RENDER diagnostic needs its meaning and fix. Sink lines (PLAY0931–PLAY0939) are realization metadata (PLAY0270): a sink change leaves the ESM revision unchanged. When the Screenplay documentation and the compiler disagree, follow the compiler for what is accepted, keep the intended semantics in the model, and record the gap.
- Clean V1 is not executable: only MCP (V2) or
render binds.
- Prefer inline
produces event for a command-owned event; plain command productions need explicit for <identifier>.
- PLAY0029 is a warning: validate with warnings as errors.
- Validate the folder; name the compiler.
- V1 warns on undeclared projection targets (
PLAY0514) and removal/capture
event references (PLAY0166). Unmapped declared fields can be reported by
opt-in --check field-origins (PLAY0534); unknown coverage is skipped, so
still walk lineage. See diagnostics for editor versus C#-only checks.
- Without reaction
runs as an invoke is caller-less. Declare its trusted role
(ESM v10), keep the gate, and reference-test; CLI/Stage support is separate.
- Mark read-model identity with trailing
key, not identifier. Otherwise single-instance
queries must agree on by; only with none and an admitted list query can *Id
inference run. Queryless views need key (read-surface references/named-keys.md).
Align projection keys; several parts need an untyped key block (v27).
- Projection
key routes only on from; joins never create; all is per source.
null only for optional read-model properties in specifications.
then events are exhaustive and ordered; after when append they list only what followed.
- Declare an event once, in its producing slice.
- Quoted
import "glob" is your own files; unquoted import Ctx.Event is a foreign
contract and does not bind.
- Pending described handlers bind but do not execute their bodies; attached handlers and
numbers exact do not bind. Descriptions render as XML doc comments, not behavior.
Gate
Before a verdict leaves this skill: tool and version named; the folder (not a file) was
checked; warnings were treated as errors; each verdict is a result or "not run" with the
reason; blocked verdicts list codes and keep the protection they blocked on.
Verify
Read model notes gate when checking
unresolved questions: the standalone tool has --open-questions fail; cratis screenplay validate
does through --open-questions report|fail. It is separate from compilation and --warnaserror.
Requires Cratis CLI 3.60.0 or later (cratis --version) for that option; older CLIs lack it.
Read fast path for the ordered requirements-to-running-app checklist (validate, render --check, render, build, run, check in a browser, run the specs).
Route near misses
Read references/neighbouring-skills.md when the work is modeling phases, MCP editing, construct depth, rendering or running systems.
1---2name: cratis-screenplay-toolchain3description: Use when selecting a Screenplay compiler, running verdict checks or interpreting PLAY, STAGE and CLI diagnostics. Not for modeling phase decisions, AST editing proposals or the end-to-end rendering workflow.4license: MIT5metadata:6 source: https://skillmd.com/skills/cratis/cratis-screenplay-toolchain7---89# Screenplay toolchain1011Read [preferred syntax](references/preferred-syntax.md) when writing or reviewing `.play`.1213This skill owns tool selection, verdicts and admission. Modeling method lives in14`cratis-screenplay-modeling-lifecycle`; syntax lives in the construct skills.1516## Locate the model1718Decide opt-in per `general.md` "Model first"; where `cratis-screenplay-modeling-lifecycle` is installed, run its `scripts/model-first-status.mjs` to locate the model root. A folder of `.play`19files is one application: always check the folder, never one file of it.20MCP/CLI discovery reuses model/workspace roots, not code-only `Source/` or `src/`;21otherwise use repository-root `Screenplay/` ([version gates and root boundaries](../cratis-screenplay-event-modeling/references/file-layout.md#locate-the-model)).2223## Tool versions and the contract2425Read the installed versions first: `screenplay --version`, `cratis --version`, and `which -a cratis`26(an older copy earlier on `PATH` shadows a newer install). The standalone tool and the compiler27bundled in the CLI are different releases, and the bundled one can be older; a construct the28standalone tool binds may be refused or unrendered through the CLI. Capabilities that need a29minimum release carry a one-line `Requires ...` note in the reference that teaches them.3031Search [screenplay-contract.json](references/screenplay-contract.json), not its32whole contents, for exact diagnostic `code`, tool `name` or `cliCommands` options.33Its version is [screenplay-contract.version](references/screenplay-contract.version).34Read [contract exceptions](references/screenplay-contract-exceptions.json) when a35superseded statement needs context; exceptions do not change the contract.3637## Ground rules38391. **Never invent syntax.** Copy shapes from `references/cheat-sheet.md` and the compiled40 examples it names, or from a compiled documentation example. Construct keywords are41 closed.422. **Check the folder, warnings as errors.** `screenplay <folder> --warnaserror` or43 `cratis screenplay validate <folder> --warnings-as-errors`. Warnings hide defects:44 PLAY0029 (a misspelt keyword or a `type` inside a slice) drops a construct silently.45 A committed `screenplay.json` at the model root declares the repository's gate (checks, warnings46 as errors, scope, open questions): run without repeating those flags (confirm with47 `--print-gate` before dropping `--warnaserror`), read it with48 `--print-gate`, and treat a refused file as "could not run" (`references/verdicts.md`).493. **Pick the compiler deliberately and name it.** Standalone `screenplay` for50 language checks and reference specifications; `cratis` for rendering51 and generation. Report both tool and version, rather than transferring a verdict across52 releases.534. **Know the mode** (design, executable, renderable) and write from its subset.545. **Capability is not correctness.** The tool you ran decides what is accepted; the55 domain and the documented semantics decide what is correct. On conflict keep the correct56 model and record a tool gap; never reshape a model to silence a tool.576. **Never remove `pii`, `secret`, authorization, list queries, automations or rules58 to reach V3 or a render.** Report the verdict as blocked with the codes.597. **A clean verdict proves only its own layer.** "Not run" with the reason is a valid60 result. Specifications written or bound are never specifications passing.618. **Let the tool resolve what it can.** Revisions, identities and renames come from the62 tool, never from hand computation; discover tool, version and root once per session and63 reuse them until the root, the tool or a call changes. Re-resolve only when a value actually64 needs to change: a failed or stale call, a different model root, a changed tool, version or65 configuration, or an explicit override.6667## The two compilers6869| | Standalone `screenplay` | `cratis screenplay ...` |70| --- | --- | --- |71| Check root | `screenplay <root> --warnaserror --no-color` | `cratis screenplay validate <root> --warnings-as-errors -o json-compact` |72| Scope/checks | `--scope <address>`, `--check <names>`; a scoped pass is not whole-application success | `validate --executable` (bundled binder, no write), `--check <names>`, `--scope`; `render --scope`/`--check`; `cratis screenplay conform`, `cratis screenplay conform-namespace` |73| Declared gate | `screenplay <root> --print-gate`, `--format json`, `--no-gate-file` | `validate <root> --print-gate`, `--no-gate-file`; the same `screenplay.json` |74| Reference execution | `screenplay test <root>` or MCP `run-specifications` | Discover bundled MCP capability; target tests are not V4 |75| Version migration | `screenplay migrate <root> --from <major> [--to <major>] [--dry-run] [--report <file>]` or MCP `migrate` (read-only); exit 2 means review | Use the standalone tool; see `cratis-screenplay-modeling-lifecycle` |76| MCP | `screenplay mcp <root>`; discover schemas | `cratis screenplay mcp [root]`; registered by `cratis ai install` |77| Render boundary | Binder admission is not Stage admission | The CLI renders only ESM versions it knows; a newer bound model gets `CLI-RENDER-004` |7879Read `references/verdicts.md` for exact commands, exit codes, the MCP roots caveat and the model notes gate.8081Requires Cratis CLI 3.57.0 or later (`cratis --version`) to render models that use equality filters or concept generation strategies (ESM v14 and v15); an older CLI answers `CLI-RENDER-004`. Requires Cratis CLI 3.74.0 for ESM v21–v26 and 3.75.0 for v27; see [language admission](references/language-admission.md#compiler-and-target-minimums) for the v28–v30 CLI minimums. Above the CLI's ceiling, a bundled compiler that binds the construct answers `CLI-RENDER-004`, and one that predates it reports the binder's PLAY0268 (Uuid equality before Screenplay 4.205.0). Either way keep the rule and gap-fill.8283MCP calls below use the `screenplay` server declared in `.cratis/ai/mcp-servers.json`, for example `screenplay` → `read-workspace`.8485## Verdicts8687Independent results, not a ladder. Read `references/verdicts.md` for the commands and the report format when obtaining or reporting V1–V5 verdicts.8889| Verdict | Meaning | How |90| --- | --- | --- |91| V1 | authorable (compiles, warnings as errors) | the folder command above |92| V2 | executable diagnostics read | MCP `open-workspace`, then `read-workspace view=executable-diagnostics` |93| V3 | binding-ready (binds, no blocking executable diagnostics) | `executableReady` true and no error-severity diagnostic in V2; informational PLAY0269/0270 are reported separately |94| V4 | reference specifications run | `screenplay test` or MCP `run-specifications`; unsupported/unbound is not a pass; rendered Debug tests are V5.tests, never V4 |95| V5 | rendered and target-verified | `cratis render`, then Debug build and tests; report admission, publication, build and tests separately |9697V2 needs MCP; V3 also supports `cratis screenplay validate --executable <root>`98(labeled as the bundled compiler). Read [verdict commands](references/verdicts.md)99for MCP initialization, source identity and reporting. Without MCP, report100`V2 not run: no MCP in this agent`. Report each verdict separately with tool,101version, source identity and any blocking codes; MCP `modelRevision` is semantic,102not the source identity.103104Read [observation comparison](references/observation-comparison.md) when asking whether a running namespace holds what the model declares, or when reading a `conform-namespace` verdict. It differs from model comparison (model versus model) and `conform` (model versus code).105106PLAY0516 ordering is presentation-only, not execution. For a wildcard-import107repair, read [timeline diagnostics](references/diagnostics.md): replacing globs108with ordered imports means future files need explicit imports.109110## Subsets (write from the one your mode needs)111112- **Design**: every construct family parses; use it to model first. Compiled shapes:113 `references/cheat-sheet.md`. Read [references/cheat-sheet-example.md](references/cheat-sheet-example.md) when you need one complete design-mode document with every construct family.114- **Executable** (binds, V3): `references/executable-subset.md`. Optional keyed lookups, unfiltered115 lists and lists narrowed by one `by` key (observable too) bind; caller-supplied equality116 filters on collections bind as ESM v14. Context `from`, single-result117 filters, opaque `scoped to` and a `by` block on a list query remain PLAY0268; a `performer` query is an opaque read left out of the executable model (PLAY0270; [version gate](references/executable-subset.md#code-attachments-what-binds-what-never-does)). Read118 read-surface [equality filters](../cratis-screenplay-read-surface/references/equality-filters.md).119 Pending handlers beside unconditional productions bind as described commands (v23),120 but reached bodies are Unsupported; attached file/inline handlers bind the same way121 beside unconditional `produces` with a resolved body and otherwise122 refuse PLAY0800.123 Requires Screenplay 4.210.0 (`screenplay --version`); older binders use PLAY0268 for this refusal. Read `arguments.subject`, not the message, for the command.124 Eligible protected reads opt into v25; legacy reads and `concurrency` retain PLAY0271.125 Concept compliance binds as v13 (precise refusals: command-surface `references/compliance.md`);126 generated values and `returns` responses bind (ESM v7, `references/generated-responses-example.md`). Read [references/executable-example.md](references/executable-example.md) when you need a small StateChange and StateView model that binds executable, [references/pdl-example.md](references/pdl-example.md) when writing projection forms that bind and run, and [references/automation-translate-example.md](references/automation-translate-example.md) when writing Automation and Translate slices (ESM v6).127- **Renderable** (V5): `references/renderable-subset.md` has the admission table. The CLI admits through128 its newest known ESM version to construct checks; supported UUID/String129 generation/responses, enum numbers, compliance, equality filters and event reactions render.130 Unsupported generated types still get `STAGE-ESM-028`; result combinations get `-038`.131 Newer versions refuse `CLI-RENDER-004`. Run admission132 before claiming a particular model renders (`cratis render --scope` for an admitted part, `--check`133 for no-write planning).134- **Event sources, streams and routes** bind as ESM v8. Operations and exact numeric source mode remain135 unadmitted. Details: `references/sources-and-streams.md`.136- **Public contracts and routes (v9/v10/v11):** public contracts and direction select v9;137 reaction identity, production overrides and observer filters select v10;138 qualifying retained non-route Double literals select v11.139 Flat composite read-model keys select v27 (Requires Screenplay 4.204.0; older binders140 report PLAY0268); one explicit `key` keeps its earlier version. Read141 `references/production-routes-and-filters.md`, [language admission](references/language-admission.md)142 and read-surface `references/named-keys.md`.143- **Enum numbers (v12):** read command-surface `references/enum-numbers.md` for144 pins, stored numbers and Stage output; `references/diagnostics.md` owns PLAY0667–0671.145- **Concept strategies (v15):** read146 [generation strategies](references/generation-strategies-example.md) for Guarded147 freshness and strict fixtures, and command-surface148 `references/generated-values-and-responses.md` for strategy/refusal depth.149- **v17–v21:** recovery/no-events (v17), query Validation errors (v18), refusal150 branches (v19), generated-concept proofs (v20), pattern/random/rule/checksum (v21).151 Read `references/executable-subset.md` for version prerequisites and152 `references/diagnostics.md` for proof/support failures. Binding is not rendering.153 Tool/renderer authors: read [references/generation-checks.md](references/generation-checks.md)154 when discovering strategy options, checking one concept or value, or consuming rule proofs.155- **v32:** a `source events` capture with a typed scalar key carries the key's type onto156 the appended event's identity.157 Requires Screenplay 4.241.0 (`screenplay --version`);158 older compilers keep the key as Text. Read159 [language admission](references/language-admission.md) for the Stage boundary.160- **v28:** `==`/`!=` between Uuid values in `require` and `produces when` select v28161 (Requires Screenplay 4.205.0; `screenplay --version`; older binders refuse PLAY0268).162 Read [language admission](references/language-admission.md) and command-surface163 `references/uuid-equality.md`.164- **v22–v27:** read [language admission](references/language-admission.md) for atomic165 batches, described handlers, text rules, protected reads, chronological command166 Date/DateTime comparisons (Requires Screenplay 4.199.0; `screenplay --version`;167 older binders refuse PLAY0268) and Stage refusals.168 Read [diagnostic arguments](references/diagnostic-arguments.md) for MCP/JSON subjects:169 code and typed arguments, never message parsing.170- **Caller/compliance metadata:** `$identity` aliases caller built-ins;171 additional identity details are metadata and executable reads still refuse.172 Bare `pii`/`secret` replace legacy spellings; `pii personal` repeats one marker173 (PLAY0653). Purposes/checks/processing records and event `subject` are report-only,174 not legal compliance, retention or runtime subject realization. See175 command-surface `references/context.md` and `references/compliance.md`.176177## Edit strategy178179Read [the MCP authoring loop](../cratis-screenplay-model-authoring/references/mcp-loop.md)180when editing: the identity owner uses typed proposals for catalog-changing edits;181text edits never bypass a refusal. Without MCP, return identity-affecting work182to its owner. Proposals are connection-local; apply is not crash-atomic, and an183unknown apply outcome requires recovery, not retry.184185## Top traps186187All 44 traps, with fixes: `references/traps.md`. Read `references/traps.md` when diagnosing an unexpected compile, binding, rendering or MCP result.188189Read [references/diagnostics.md](references/diagnostics.md) when a PLAY, STAGE or CLI-RENDER diagnostic needs its meaning and fix. Sink lines (`PLAY0931`–`PLAY0939`) are realization metadata (PLAY0270): a sink change leaves the ESM revision unchanged. When the Screenplay documentation and the compiler disagree, follow the compiler for what is accepted, keep the intended semantics in the model, and record the gap.1901911. Clean V1 is not executable: only MCP (V2) or `render` binds.1922. Prefer inline `produces event` for a command-owned event; plain command productions need explicit `for <identifier>`.1933. PLAY0029 is a warning: validate with warnings as errors.1944. Validate the folder; name the compiler.1955. V1 warns on undeclared projection targets (`PLAY0514`) and removal/capture196 event references (`PLAY0166`). Unmapped declared fields can be reported by197 opt-in `--check field-origins` (`PLAY0534`); unknown coverage is skipped, so198 still walk lineage. See diagnostics for editor versus C#-only checks.1996. Without reaction `runs as` an invoke is caller-less. Declare its trusted role200 (ESM v10), keep the gate, and reference-test; CLI/Stage support is separate.2017. Mark read-model identity with trailing `key`, not `identifier`. Otherwise single-instance202 queries must agree on `by`; only with none and an admitted list query can `*Id`203 inference run. Queryless views need `key` (read-surface `references/named-keys.md`).204 Align projection keys; several parts need an untyped `key` block (v27).2058. Projection `key` routes only on `from`; joins never create; `all` is per source.2069. `null` only for optional read-model properties in specifications.20710. `then` events are exhaustive and ordered; after `when append` they list only what followed.20811. Declare an event once, in its producing slice.20912. Quoted `import "glob"` is your own files; unquoted `import Ctx.Event` is a foreign210 contract and does not bind.21113. Pending described handlers bind but do not execute their bodies; attached handlers and `numbers exact` do not bind. Descriptions render as XML doc comments, not behavior.212213## Gate214215Before a verdict leaves this skill: tool and version named; the folder (not a file) was216checked; warnings were treated as errors; each verdict is a result or "not run" with the217reason; blocked verdicts list codes and keep the protection they blocked on.218219## Verify220221- [ ] The command ran on the folder and its exit status was read, not inferred from output.222- [ ] `screenplay --version` and `cratis --version` were read; `which -a cratis` shows no223 stale copy ahead on `PATH`.224- [ ] Every PLAY0029 and unresolved-name warning is fixed, not silenced.225- [ ] A V3 or render claim names the compiler that bound it.226- [ ] Nothing was removed to pass a verdict.227- [ ] Any new example fence compiles with the standalone tool; unmarked fences also pass228 `cratis screenplay validate --warnings-as-errors`.229230Read [model notes gate](references/verdicts.md#model-notes-gate) when checking231unresolved questions: the standalone tool has `--open-questions fail`; `cratis screenplay validate`232does through `--open-questions report|fail`. It is separate from compilation and `--warnaserror`.233Requires Cratis CLI 3.60.0 or later (`cratis --version`) for that option; older CLIs lack it.234235Read [fast path](references/fast-path.md) for the ordered requirements-to-running-app checklist (validate, `render --check`, render, build, run, check in a browser, run the specs).236237## Route near misses238239Read [references/neighbouring-skills.md](references/neighbouring-skills.md) when the work is modeling phases, MCP editing, construct depth, rendering or running systems.