Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 35 additions & 0 deletions .agents/skills/speckit-intake-series-create/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
---
name: speckit-intake-series-create
description: Create one traceable intake series from explicitly named existing intakes.
compatibility: Requires spec-kit project structure with .specify/ directory
metadata:
author: github-spec-kit
source: preset:intake-sequencing-governance
---

# Speckit Intake Series Create Skill

## User Input

```text
$ARGUMENTS
```

Create exactly one new series. Do not change intake content and do not start a
review or feature workflow.

1. Read repository guidance, sequencing policy, and every explicitly named
target as strict UTF-8.
2. Refuse an existing active series. Never infer an update authority.
3. Present the exact target order, roles, normalized hashes, roots, typed edges,
binding flags, lifecycle states, and evidence paths before writing.
4. Ask material questions one at a time. Do not guess a dependency, root,
completion fact, or delivery authority.
5. Prepare manifest, receipt, operation journal, and learner-readable order
document under repository-owned paths.
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.
28 changes: 28 additions & 0 deletions .agents/skills/speckit-intake-series-delete/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
---
name: speckit-intake-series-delete
description: Logically delete one intake series through archive and tombstone evidence.
compatibility: Requires spec-kit project structure with .specify/ directory
metadata:
author: github-spec-kit
source: preset:intake-sequencing-governance
---

# Speckit Intake Series Delete Skill

## User Input

```text
$ARGUMENTS
```

Logically delete exactly one named series with explicit current authority.

1. Validate current manifest and receipt.
2. State that intake documents remain unchanged.
3. Archive manifest and receipt byte-identically.
4. Create a tombstone with identity, authority, reason, UTC time, archive paths,
hashes, and `intakeDocumentsDeleted: false`.
5. Publish deletion receipt and tombstone only after both validators pass.
6. Do not physically purge evidence or start another command.

Finish with archive and tombstone proof plus one exact safe next action.
32 changes: 32 additions & 0 deletions .agents/skills/speckit-intake-series-next/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
---
name: speckit-intake-series-next
description: List every currently eligible intake target or exact blockers without
starting work.
compatibility: Requires spec-kit project structure with .specify/ directory
metadata:
author: github-spec-kit
source: preset:intake-sequencing-governance
---

# Speckit Intake Series Next Skill

## User Input

```text
$ARGUMENTS
```

Select candidates only from a valid, current named series.

1. Run the read-only status contract first.
2. A target is eligible only when its lifecycle permits selection and every
binding predecessor is `Completed`.
3. Report all eligible targets in visible order. If none are eligible, report
each exact blocker and evidence path.
4. Distinguish preferred order and shared-writer serialization from binding
functional dependencies.
5. Revalidate downstream review freshness and user authority only when a later
command is separately invoked.
6. Never start Intake Review, Specify, Autonomous, or Parallel Autonomous.

Finish with a copy-ready suggested command only; do not execute it.
29 changes: 29 additions & 0 deletions .agents/skills/speckit-intake-series-read/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
---
name: speckit-intake-series-read
description: Summarize one intake series without changing files.
compatibility: Requires spec-kit project structure with .specify/ directory
metadata:
author: github-spec-kit
source: preset:intake-sequencing-governance
---

# Speckit Intake Series Read Skill

## User Input

```text
$ARGUMENTS
```

Read one named series in Summary, Detailed, or JSON form.

1. Resolve only the named manifest and receipt.
2. Validate them before summarizing.
3. Report visible order, roots, typed dependencies, binding versus
serialization-only edges, lifecycle states, eligible targets, blockers,
evidence freshness, and residual risk.
4. Keep the explanation text-first, German-first/English-second where project
policy requires it, and understandable without graph-theory knowledge.
5. Do not modify files, stage changes, or start another Spec Kit command.

Finish with the read-only hash proof and one exact safe next action.
28 changes: 28 additions & 0 deletions .agents/skills/speckit-intake-series-status/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
---
name: speckit-intake-series-status
description: Validate current intake-series state without changing files.
compatibility: Requires spec-kit project structure with .specify/ directory
metadata:
author: github-spec-kit
source: preset:intake-sequencing-governance
---

# Speckit Intake Series Status Skill

## User Input

```text
$ARGUMENTS
```

Inspect one named series read-only.

1. Hash run state and tracked evidence before inspection.
2. Run Bash and PowerShell validators.
3. Report identity, status, targets, roots, dependencies, eligible targets,
blockers, receipt lineage, archive/tombstone state, and drift.
4. Classify ambiguity or drift fail-closed. Do not repair it.
5. Prove before/after hashes and Git status are unchanged.
6. Do not stage, commit, push, review, or execute a target.

Finish with one exact next action.
31 changes: 31 additions & 0 deletions .agents/skills/speckit-intake-series-update/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
---
name: speckit-intake-series-update
description: Update one intake series with explicit authority and preserved lineage.
compatibility: Requires spec-kit project structure with .specify/ directory
metadata:
author: github-spec-kit
source: preset:intake-sequencing-governance
---

# Speckit Intake Series Update Skill

## User Input

```text
$ARGUMENTS
```

Update exactly one active series. Current explicit update authority is required.

1. Validate the accepted manifest and receipt before proposing changes.
2. Present exact target, order, root, edge, lifecycle, and evidence differences.
3. Refuse ambiguous facts and unrelated intake-content changes.
4. Archive the prior manifest and receipt byte-identically.
5. Prepare successor manifest, receipt, operation journal, and order document.
6. Bind the successor through `supersedes`, prior hashes, archive paths, and
current authority evidence.
7. Run both validators before atomic publication.
8. Do not perform Intake Review or start downstream work.

Finish with changed cardinalities, archive evidence, validation results, and
exactly `$speckit-intake-series-status` as the next action.
33 changes: 33 additions & 0 deletions .claude/skills/speckit-intake-series-create/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,33 @@
---
name: speckit-intake-series-create
description: Create one traceable intake series from explicitly named existing intakes.
compatibility: Requires spec-kit project structure with .specify/ directory
metadata:
author: github-spec-kit
source: intake-sequencing-governance:commands/speckit.intake-series-create.md
---

## User Input

```text
$ARGUMENTS
```

Create exactly one new series. Do not change intake content and do not start a
review or feature workflow.

1. Read repository guidance, sequencing policy, and every explicitly named
target as strict UTF-8.
2. Refuse an existing active series. Never infer an update authority.
3. Present the exact target order, roles, normalized hashes, roots, typed edges,
binding flags, lifecycle states, and evidence paths before writing.
4. Ask material questions one at a time. Do not guess a dependency, root,
completion fact, or delivery authority.
5. Prepare manifest, receipt, operation journal, and learner-readable order
document under repository-owned paths.
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.
26 changes: 26 additions & 0 deletions .claude/skills/speckit-intake-series-delete/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
---
name: speckit-intake-series-delete
description: Logically delete one intake series through archive and tombstone evidence.
compatibility: Requires spec-kit project structure with .specify/ directory
metadata:
author: github-spec-kit
source: intake-sequencing-governance:commands/speckit.intake-series-delete.md
---

## User Input

```text
$ARGUMENTS
```

Logically delete exactly one named series with explicit current authority.

1. Validate current manifest and receipt.
2. State that intake documents remain unchanged.
3. Archive manifest and receipt byte-identically.
4. Create a tombstone with identity, authority, reason, UTC time, archive paths,
hashes, and `intakeDocumentsDeleted: false`.
5. Publish deletion receipt and tombstone only after both validators pass.
6. Do not physically purge evidence or start another command.

Finish with archive and tombstone proof plus one exact safe next action.
30 changes: 30 additions & 0 deletions .claude/skills/speckit-intake-series-next/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
---
name: speckit-intake-series-next
description: List every currently eligible intake target or exact blockers without
starting work.
compatibility: Requires spec-kit project structure with .specify/ directory
metadata:
author: github-spec-kit
source: intake-sequencing-governance:commands/speckit.intake-series-next.md
---

## User Input

```text
$ARGUMENTS
```

Select candidates only from a valid, current named series.

1. Run the read-only status contract first.
2. A target is eligible only when its lifecycle permits selection and every
binding predecessor is `Completed`.
3. Report all eligible targets in visible order. If none are eligible, report
each exact blocker and evidence path.
4. Distinguish preferred order and shared-writer serialization from binding
functional dependencies.
5. Revalidate downstream review freshness and user authority only when a later
command is separately invoked.
6. Never start Intake Review, Specify, Autonomous, or Parallel Autonomous.

Finish with a copy-ready suggested command only; do not execute it.
27 changes: 27 additions & 0 deletions .claude/skills/speckit-intake-series-read/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
---
name: speckit-intake-series-read
description: Summarize one intake series without changing files.
compatibility: Requires spec-kit project structure with .specify/ directory
metadata:
author: github-spec-kit
source: intake-sequencing-governance:commands/speckit.intake-series-read.md
---

## User Input

```text
$ARGUMENTS
```

Read one named series in Summary, Detailed, or JSON form.

1. Resolve only the named manifest and receipt.
2. Validate them before summarizing.
3. Report visible order, roots, typed dependencies, binding versus
serialization-only edges, lifecycle states, eligible targets, blockers,
evidence freshness, and residual risk.
4. Keep the explanation text-first, German-first/English-second where project
policy requires it, and understandable without graph-theory knowledge.
5. Do not modify files, stage changes, or start another Spec Kit command.

Finish with the read-only hash proof and one exact safe next action.
26 changes: 26 additions & 0 deletions .claude/skills/speckit-intake-series-status/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
---
name: speckit-intake-series-status
description: Validate current intake-series state without changing files.
compatibility: Requires spec-kit project structure with .specify/ directory
metadata:
author: github-spec-kit
source: intake-sequencing-governance:commands/speckit.intake-series-status.md
---

## User Input

```text
$ARGUMENTS
```

Inspect one named series read-only.

1. Hash run state and tracked evidence before inspection.
2. Run Bash and PowerShell validators.
3. Report identity, status, targets, roots, dependencies, eligible targets,
blockers, receipt lineage, archive/tombstone state, and drift.
4. Classify ambiguity or drift fail-closed. Do not repair it.
5. Prove before/after hashes and Git status are unchanged.
6. Do not stage, commit, push, review, or execute a target.

Finish with one exact next action.
29 changes: 29 additions & 0 deletions .claude/skills/speckit-intake-series-update/SKILL.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
---
name: speckit-intake-series-update
description: Update one intake series with explicit authority and preserved lineage.
compatibility: Requires spec-kit project structure with .specify/ directory
metadata:
author: github-spec-kit
source: intake-sequencing-governance:commands/speckit.intake-series-update.md
---

## User Input

```text
$ARGUMENTS
```

Update exactly one active series. Current explicit update authority is required.

1. Validate the accepted manifest and receipt before proposing changes.
2. Present exact target, order, root, edge, lifecycle, and evidence differences.
3. Refuse ambiguous facts and unrelated intake-content changes.
4. Archive the prior manifest and receipt byte-identically.
5. Prepare successor manifest, receipt, operation journal, and order document.
6. Bind the successor through `supersedes`, prior hashes, archive paths, and
current authority evidence.
7. Run both validators before atomic publication.
8. Do not perform Intake Review or start downstream work.

Finish with changed cardinalities, archive evidence, validation results, and
exactly `$speckit-intake-series-status` as the next action.
Loading
Loading