Adopt learner accessibility preset patches

.agents/skills/speckit-autonomous/SKILL.md

@@ -19,6 +19,12 @@ $ARGUMENTS
 Use the request, repository constitution, agent guidance, current feature
 metadata, and accepted feature artifacts as binding input.
 
+Resolve the project's learner and accessibility policy before Specify. Carry
+its declared audience, language order, readability target, first-use
+terminology, assumed prior knowledge, and text-first dependency/status/decision
+rules through Spec, Plan, Tasks, implementation evidence, documentation, and
+retrospective. This preset does not invent a project-specific audience.
+
 Before creating a feature, inspect repository metadata and
 `specs/<feature>/autonomous-run-state.json`. A valid `PausedByUser` state MUST
 stop this command and direct the user to `speckit.autonomous-resume`. A valid

.agents/skills/speckit-intake-create/SKILL.md

@@ -45,6 +45,10 @@ series. This command never updates or deletes an active intake. It never starts
    requirements, quality and governance boundaries, dependencies, risks,
    expected artifacts, evidence, measurable acceptance, assumptions, and open
    questions. Follow repository language policy and applicable WCAG 2.2 AA.
+   For learner-facing material, preserve the profile's declared audience,
+   assumed prior knowledge, first-use terminology rule, and text-first
+   dependency/status/decision/next-action rule. Never silently assume Spec Kit
+   experience.
 8. Refuse an existing target or active receipt without writing anything.
    Report `$speckit-intake-update <target>` as the exact safe command. New
    targets use provenance mode `New`; Create never claims update authority,

.agents/skills/speckit-intake-delete/SKILL.md

@@ -16,7 +16,7 @@ metadata:
 $ARGUMENTS
 ```
 
-Delete is logical and reversible from versioned evidence. v0.2.0 has no purge.
+Delete is logical and reversible from versioned evidence. v0.2.1 has no purge.
 
 1. Resolve exactly one active intake or one complete series. Require the exact
    identity, a deletion reason, and explicit current delete authority.

.agents/skills/speckit-intake-review/SKILL.md

@@ -26,6 +26,10 @@ exist. Use the installed policy and checklist.
    measurable acceptance, dependencies, order, security/privacy/A11Y/platform,
    evidence, delivery authority, risks, references, prompt alignment, and
    secret or unnecessary-personal-data exposure.
+   When project policy declares learner-facing material, also verify assumed
+   prior knowledge, first-use explanations for technical and Spec Kit terms,
+   the language/readability contract, and text-first dependencies, status,
+   decisions, and next actions.
 3. For a series, additionally review IDs, DAG, gaps, overlap, terminology,
    invariants, handoffs, future scope, and authority. Use schema 1.1, declare
    every root, order every target exactly once, and bind the request path and

.agents/skills/speckit-intake-series-create/SKILL.md

@@ -27,6 +27,10 @@ review or feature workflow.
    completion fact, or delivery authority.
 5. Prepare manifest, receipt, operation journal, and learner-readable order
    document under repository-owned paths.
+   Preserve the project's declared audience, language order, readability,
+   first-use terminology, and prior-knowledge boundary. The order document
+   must state dependencies, blockers, status, decisions, and next actions as
+   text even when it also contains a diagram.
 6. Validate paths, hashes, graph, lifecycle, and receipts in Bash and
    PowerShell before publishing any active file.
 7. Publish all prepared files atomically. A failure leaves an explicit

.agents/skills/speckit-parallel-autonomous/SKILL.md

@@ -19,6 +19,12 @@ Require an accepted campaign manifest, local runner-profile binding, explicit
 delivery authority, and `autonomous-run-governance >= 0.2.2` in every worker
 repository.
 
+Resolve the shared project learner and accessibility policy before scheduling.
+Every worker and the final consolidation must preserve the declared audience,
+language order, readability, first-use terminology, prior-knowledge boundary,
+and text-first dependency/status/decision/next-action contract. Provider or
+runner defaults cannot weaken that policy.
+
 Campaign schemas `1.0`, `1.1`, and `1.2` are supported. Schema `1.2` may
 declare `intakeReview.required`. When true, validate the result before any
 worktree or worker process is created. Require one semantic review per unique

.claude/skills/speckit-autonomous/SKILL.md

@@ -17,6 +17,12 @@ $ARGUMENTS
 Use the request, repository constitution, agent guidance, current feature
 metadata, and accepted feature artifacts as binding input.
 
+Resolve the project's learner and accessibility policy before Specify. Carry
+its declared audience, language order, readability target, first-use
+terminology, assumed prior knowledge, and text-first dependency/status/decision
+rules through Spec, Plan, Tasks, implementation evidence, documentation, and
+retrospective. This preset does not invent a project-specific audience.
+
 Before creating a feature, inspect repository metadata and
 `specs/<feature>/autonomous-run-state.json`. A valid `PausedByUser` state MUST
 stop this command and direct the user to `speckit.autonomous-resume`. A valid
@@ -145,4 +151,4 @@ Finish with task and artifact counts, validation, skipped conditions, review
 state, follow-ups, remote identifiers when authorized, and exact local/remote
 synchronization. Set `Completed` only when every applicable schema-1.1 closeout
 field is terminal and final validation is `Completed`. Do not start the next
-feature implicitly.
+feature implicitly.

.claude/skills/speckit-intake-create/SKILL.md

@@ -43,6 +43,10 @@ series. This command never updates or deletes an active intake. It never starts
    requirements, quality and governance boundaries, dependencies, risks,
    expected artifacts, evidence, measurable acceptance, assumptions, and open
    questions. Follow repository language policy and applicable WCAG 2.2 AA.
+   For learner-facing material, preserve the profile's declared audience,
+   assumed prior knowledge, first-use terminology rule, and text-first
+   dependency/status/decision/next-action rule. Never silently assume Spec Kit
+   experience.
 8. Refuse an existing target or active receipt without writing anything.
    Report `$speckit-intake-update <target>` as the exact safe command. New
    targets use provenance mode `New`; Create never claims update authority,
@@ -88,4 +92,4 @@ Finish with status, targets, receipts or series manifest, source count, question
 and decision counts, delivery authority, validation results, and exactly one
 next action. For one `ReadyForReview` target, use
 `$speckit-intake-review <target>`. For a series, use the generated schema-1.1
-Series request. Report the command without executing it.
+Series request. Report the command without executing it.

.claude/skills/speckit-intake-delete/SKILL.md

@@ -14,7 +14,7 @@ metadata:
 $ARGUMENTS
 ```
 
-Delete is logical and reversible from versioned evidence. v0.2.0 has no purge.
+Delete is logical and reversible from versioned evidence. v0.2.1 has no purge.
 
 1. Resolve exactly one active intake or one complete series. Require the exact
    identity, a deletion reason, and explicit current delete authority.
@@ -40,4 +40,4 @@ Delete is logical and reversible from versioned evidence. v0.2.0 has no purge.
 
 Finish with deleted identities, archive and tombstone paths, validation,
 invalidated references, and exact next action. Never recreate, review, specify,
-or start an autonomous command implicitly.
+or start an autonomous command implicitly.

.claude/skills/speckit-intake-review/SKILL.md

@@ -24,6 +24,10 @@ exist. Use the installed policy and checklist.
    measurable acceptance, dependencies, order, security/privacy/A11Y/platform,
    evidence, delivery authority, risks, references, prompt alignment, and
    secret or unnecessary-personal-data exposure.
+   When project policy declares learner-facing material, also verify assumed
+   prior knowledge, first-use explanations for technical and Spec Kit terms,
+   the language/readability contract, and text-first dependencies, status,
+   decisions, and next actions.
 3. For a series, additionally review IDs, DAG, gaps, overlap, terminology,
    invariants, handoffs, future scope, and authority. Use schema 1.1, declare
    every root, order every target exactly once, and bind the request path and
@@ -48,4 +52,4 @@ exist. Use the installed policy and checklist.
 
 Finish with outcome, target and worker counts, findings by severity, accepted
 risks, open questions, result path, and exact next action. Do not start Specify
-or an autonomous run implicitly.
+or an autonomous run implicitly.

.claude/skills/speckit-intake-series-create/SKILL.md

@@ -25,9 +25,13 @@ review or feature workflow.
    completion fact, or delivery authority.
 5. Prepare manifest, receipt, operation journal, and learner-readable order
    document under repository-owned paths.
+   Preserve the project's declared audience, language order, readability,
+   first-use terminology, and prior-knowledge boundary. The order document
+   must state dependencies, blockers, status, decisions, and next actions as
+   text even when it also contains a diagram.
 6. Validate paths, hashes, graph, lifecycle, and receipts in Bash and
    PowerShell before publishing any active file.
 7. Publish all prepared files atomically. A failure leaves an explicit
    incomplete operation and no partially active series.
 8. Finish with series ID, cardinalities, validation results, eligible targets,
-   blockers, and exactly `$speckit-intake-series-status` as the next action.
+   blockers, and exactly `$speckit-intake-series-status` as the next action.

.claude/skills/speckit-parallel-autonomous/SKILL.md

@@ -17,6 +17,12 @@ Require an accepted campaign manifest, local runner-profile binding, explicit
 delivery authority, and `autonomous-run-governance >= 0.2.2` in every worker
 repository.
 
+Resolve the shared project learner and accessibility policy before scheduling.
+Every worker and the final consolidation must preserve the declared audience,
+language order, readability, first-use terminology, prior-knowledge boundary,
+and text-first dependency/status/decision/next-action contract. Provider or
+runner defaults cannot weaken that policy.
+
 Campaign schemas `1.0`, `1.1`, and `1.2` are supported. Schema `1.2` may
 declare `intakeReview.required`. When true, validate the result before any
 worktree or worker process is created. Require one semantic review per unique
@@ -46,4 +52,4 @@ or incomplete result schedules zero workers.
 
 *DE: Worker-spezifische Runner-Profile duerfen das Kampagnenprofil
 ueberschreiben. Modell und Reasoning nur bei ausdruecklicher Deklaration
-anzeigen; keine fremde Agentenkonfiguration erraten.*
+anzeigen; keine fremde Agentenkonfiguration erraten.*

.github/agents/speckit.autonomous.agent.md

@@ -14,6 +14,12 @@ $ARGUMENTS
 Use the request, repository constitution, agent guidance, current feature
 metadata, and accepted feature artifacts as binding input.
 
+Resolve the project's learner and accessibility policy before Specify. Carry
+its declared audience, language order, readability target, first-use
+terminology, assumed prior knowledge, and text-first dependency/status/decision
+rules through Spec, Plan, Tasks, implementation evidence, documentation, and
+retrospective. This preset does not invent a project-specific audience.
+
 Before creating a feature, inspect repository metadata and
 `specs/<feature>/autonomous-run-state.json`. A valid `PausedByUser` state MUST
 stop this command and direct the user to `speckit.autonomous-resume`. A valid
@@ -142,4 +148,4 @@ Finish with task and artifact counts, validation, skipped conditions, review
 state, follow-ups, remote identifiers when authorized, and exact local/remote
 synchronization. Set `Completed` only when every applicable schema-1.1 closeout
 field is terminal and final validation is `Completed`. Do not start the next
-feature implicitly.
+feature implicitly.

.github/agents/speckit.intake-create.agent.md

@@ -40,6 +40,10 @@ series. This command never updates or deletes an active intake. It never starts
    requirements, quality and governance boundaries, dependencies, risks,
    expected artifacts, evidence, measurable acceptance, assumptions, and open
    questions. Follow repository language policy and applicable WCAG 2.2 AA.
+   For learner-facing material, preserve the profile's declared audience,
+   assumed prior knowledge, first-use terminology rule, and text-first
+   dependency/status/decision/next-action rule. Never silently assume Spec Kit
+   experience.
 8. Refuse an existing target or active receipt without writing anything.
    Report `$speckit-intake-update <target>` as the exact safe command. New
    targets use provenance mode `New`; Create never claims update authority,
@@ -85,4 +89,4 @@ Finish with status, targets, receipts or series manifest, source count, question
 and decision counts, delivery authority, validation results, and exactly one
 next action. For one `ReadyForReview` target, use
 `$speckit-intake-review <target>`. For a series, use the generated schema-1.1
-Series request. Report the command without executing it.
+Series request. Report the command without executing it.

.github/agents/speckit.intake-delete.agent.md

@@ -11,7 +11,7 @@ description: Logically delete active intake artifacts through archive and tombst
 $ARGUMENTS
 ```
 
-Delete is logical and reversible from versioned evidence. v0.2.0 has no purge.
+Delete is logical and reversible from versioned evidence. v0.2.1 has no purge.
 
 1. Resolve exactly one active intake or one complete series. Require the exact
    identity, a deletion reason, and explicit current delete authority.
@@ -37,4 +37,4 @@ Delete is logical and reversible from versioned evidence. v0.2.0 has no purge.
 
 Finish with deleted identities, archive and tombstone paths, validation,
 invalidated references, and exact next action. Never recreate, review, specify,
-or start an autonomous command implicitly.
+or start an autonomous command implicitly.

.github/agents/speckit.intake-review.agent.md

@@ -21,6 +21,10 @@ exist. Use the installed policy and checklist.
    measurable acceptance, dependencies, order, security/privacy/A11Y/platform,
    evidence, delivery authority, risks, references, prompt alignment, and
    secret or unnecessary-personal-data exposure.
+   When project policy declares learner-facing material, also verify assumed
+   prior knowledge, first-use explanations for technical and Spec Kit terms,
+   the language/readability contract, and text-first dependencies, status,
+   decisions, and next actions.
 3. For a series, additionally review IDs, DAG, gaps, overlap, terminology,
    invariants, handoffs, future scope, and authority. Use schema 1.1, declare
    every root, order every target exactly once, and bind the request path and
@@ -45,4 +49,4 @@ exist. Use the installed policy and checklist.
 
 Finish with outcome, target and worker counts, findings by severity, accepted
 risks, open questions, result path, and exact next action. Do not start Specify
-or an autonomous run implicitly.
+or an autonomous run implicitly.

.github/agents/speckit.intake-series-create.agent.md

@@ -22,9 +22,13 @@ review or feature workflow.
    completion fact, or delivery authority.
 5. Prepare manifest, receipt, operation journal, and learner-readable order
    document under repository-owned paths.
+   Preserve the project's declared audience, language order, readability,
+   first-use terminology, and prior-knowledge boundary. The order document
+   must state dependencies, blockers, status, decisions, and next actions as
+   text even when it also contains a diagram.
 6. Validate paths, hashes, graph, lifecycle, and receipts in Bash and
    PowerShell before publishing any active file.
 7. Publish all prepared files atomically. A failure leaves an explicit
    incomplete operation and no partially active series.
 8. Finish with series ID, cardinalities, validation results, eligible targets,
-   blockers, and exactly `$speckit-intake-series-status` as the next action.
+   blockers, and exactly `$speckit-intake-series-status` as the next action.

.github/agents/speckit.parallel-autonomous.agent.md

@@ -14,6 +14,12 @@ Require an accepted campaign manifest, local runner-profile binding, explicit
 delivery authority, and `autonomous-run-governance >= 0.2.2` in every worker
 repository.
 
+Resolve the shared project learner and accessibility policy before scheduling.
+Every worker and the final consolidation must preserve the declared audience,
+language order, readability, first-use terminology, prior-knowledge boundary,
+and text-first dependency/status/decision/next-action contract. Provider or
+runner defaults cannot weaken that policy.
+
 Campaign schemas `1.0`, `1.1`, and `1.2` are supported. Schema `1.2` may
 declare `intakeReview.required`. When true, validate the result before any
 worktree or worker process is created. Require one semantic review per unique
@@ -43,4 +49,4 @@ or incomplete result schedules zero workers.
 
 *DE: Worker-spezifische Runner-Profile duerfen das Kampagnenprofil
 ueberschreiben. Modell und Reasoning nur bei ausdruecklicher Deklaration
-anzeigen; keine fremde Agentenkonfiguration erraten.*
+anzeigen; keine fremde Agentenkonfiguration erraten.*

.opencode/command/speckit.autonomous.md

@@ -14,6 +14,12 @@ $ARGUMENTS
 Use the request, repository constitution, agent guidance, current feature
 metadata, and accepted feature artifacts as binding input.
 
+Resolve the project's learner and accessibility policy before Specify. Carry
+its declared audience, language order, readability target, first-use
+terminology, assumed prior knowledge, and text-first dependency/status/decision
+rules through Spec, Plan, Tasks, implementation evidence, documentation, and
+retrospective. This preset does not invent a project-specific audience.
+
 Before creating a feature, inspect repository metadata and
 `specs/<feature>/autonomous-run-state.json`. A valid `PausedByUser` state MUST
 stop this command and direct the user to `speckit.autonomous-resume`. A valid
@@ -142,4 +148,4 @@ Finish with task and artifact counts, validation, skipped conditions, review
 state, follow-ups, remote identifiers when authorized, and exact local/remote
 synchronization. Set `Completed` only when every applicable schema-1.1 closeout
 field is terminal and final validation is `Completed`. Do not start the next
-feature implicitly.
+feature implicitly.

.opencode/command/speckit.intake-create.md

@@ -40,6 +40,10 @@ series. This command never updates or deletes an active intake. It never starts
    requirements, quality and governance boundaries, dependencies, risks,
    expected artifacts, evidence, measurable acceptance, assumptions, and open
    questions. Follow repository language policy and applicable WCAG 2.2 AA.
+   For learner-facing material, preserve the profile's declared audience,
+   assumed prior knowledge, first-use terminology rule, and text-first
+   dependency/status/decision/next-action rule. Never silently assume Spec Kit
+   experience.
 8. Refuse an existing target or active receipt without writing anything.
    Report `$speckit-intake-update <target>` as the exact safe command. New
    targets use provenance mode `New`; Create never claims update authority,
@@ -85,4 +89,4 @@ Finish with status, targets, receipts or series manifest, source count, question
 and decision counts, delivery authority, validation results, and exactly one
 next action. For one `ReadyForReview` target, use
 `$speckit-intake-review <target>`. For a series, use the generated schema-1.1
-Series request. Report the command without executing it.
+Series request. Report the command without executing it.

.opencode/command/speckit.intake-delete.md

@@ -11,7 +11,7 @@ description: Logically delete active intake artifacts through archive and tombst
 $ARGUMENTS
 ```
 
-Delete is logical and reversible from versioned evidence. v0.2.0 has no purge.
+Delete is logical and reversible from versioned evidence. v0.2.1 has no purge.
 
 1. Resolve exactly one active intake or one complete series. Require the exact
    identity, a deletion reason, and explicit current delete authority.
@@ -37,4 +37,4 @@ Delete is logical and reversible from versioned evidence. v0.2.0 has no purge.
 
 Finish with deleted identities, archive and tombstone paths, validation,
 invalidated references, and exact next action. Never recreate, review, specify,
-or start an autonomous command implicitly.
+or start an autonomous command implicitly.