vouchington-tooling 0.22.0 → 0.23.0

package/skills/retrospective-distill/SKILL.md

@@ -1,10 +1,14 @@
 ---
 name: retrospective-distill
-description: Distill completed session records into a small set of verified, actionable follow-up issues.
+description: Turn completed session records into verified follow-up candidates.
 ---
 
 # Retrospective distillation
 
+Read applicable `AGENTS.md` and their declared adapter alias, otherwise
+`.agents/skills/retrospective-distill/SKILL.md` from the repository root if present.
+Local policy overrides these defaults; do not reload an already-read adapter or canonical skill.
+
 Use when completed retrospectives or journals should become durable follow-up work. Read local
 `AGENTS.md`, issue policy, and journal retention rules before any mutation.
 

package/skills/review-ci-logs/SKILL.md

@@ -1,10 +1,14 @@
 ---
 name: review-ci-logs
-description: Audit CI failures or noisy logs, identify the root cause, and recommend diagnostics-preserving fixes.
+description: Diagnose CI failures and noise without weakening diagnostics.
 ---
 
 # Review CI logs
 
+Read applicable `AGENTS.md` and their declared adapter alias, otherwise
+`.agents/skills/review-ci-logs/SKILL.md` from the repository root if present.
+Local policy overrides these defaults; do not reload an already-read adapter or canonical skill.
+
 Use when investigating a CI failure, repeated workflow noise, or misleading diagnostics. Read local
 `AGENTS.md`, workflow guidance, and CI documentation before inspecting runs.
 
@@ -14,6 +18,11 @@ Use when investigating a CI failure, repeated workflow noise, or misleading diag
    failed steps and representative large entries, then remove the temporary artifacts.
 3. Classify each finding as a real error, misleading output, a downstream cascade, a necessary
    diagnostic, or a volume-only concern. Identify the first repository-owned root cause.
+   Compare the first failing run/job, its exact head revision, and scope with the pre-push verification record.
+   Establish whether the relevant local verification was omitted, passed under a different scope
+   or environment, genuinely CI-only, or unknown. A shared command name does not prove shared
+   project, target, fixtures, or configuration. Do not infer an omission from missing evidence or
+   label an external infrastructure failure a harness miss.
 4. For a persistent-workspace failure, name the producer of sparse state or unsafe ownership before
    proposing cleanup. Reject an unconditional pre-checkout workspace traversal. A compliant repair
    is the one in [github-actions-checklist](../github-actions-checklist/SKILL.md).
@@ -23,6 +32,11 @@ Use when investigating a CI failure, repeated workflow noise, or misleading diag
 6. Add focused regression evidence, run local workflow validation, and compare before and after
    output where that comparison is meaningful. Report deferred findings. Do not create issues unless
    authorized.
+7. Update [the PR description](../pr-description/SKILL.md) before handoff with confirmed omitted
+   verification or proven local/CI mismatch. Link the first failed run/job and its exact revision, the actual local
+   scope, the reason it missed the failure, and the durable harness correction or authorized
+   follow-up. Keep the distinction between omitted and locally passed checks explicit, and retain
+   confirmed gap records after CI turns green. Classify CI-only and unknown coverage separately.
 
 Consumer wrapper owns: workflow names, log retention, the CI provider command, retry policy, and
 scheduled automation.

package/skills/review-github-issue-taxonomy/SKILL.md

@@ -1,10 +1,14 @@
 ---
 name: review-github-issue-taxonomy
-description: Audit GitHub labels, milestones, projects, and path-label automation and return actionable taxonomy recommendations.
+description: Audit labels, milestones, projects, and path-label ownership.
 ---
 
 # Review GitHub issue taxonomy
 
+Read applicable `AGENTS.md` and their declared adapter alias, otherwise
+`.agents/skills/review-github-issue-taxonomy/SKILL.md` from the repository root if present.
+Local policy overrides these defaults; do not reload an already-read adapter or canonical skill.
+
 Use when the taxonomy itself needs review. Stay read-only unless the caller explicitly authorizes
 local configuration edits or a live taxonomy mutation. Read local `AGENTS.md` first.
 

package/skills/revisit-followups/SKILL.md

@@ -1,10 +1,14 @@
 ---
 name: revisit-followups
-description: Review recently completed work and repository instructions for genuinely deferred follow-ups, then propose verified issue candidates.
+description: Find verified deferred work in completed changes and instructions.
 ---
 
 # Revisit follow-ups
 
+Read applicable `AGENTS.md` and their declared adapter alias, otherwise
+`.agents/skills/revisit-followups/SKILL.md` from the repository root if present.
+Local policy overrides these defaults; do not reload an already-read adapter or canonical skill.
+
 Use to turn explicit deferred work into a curated backlog. Read local `AGENTS.md`,
 issue policy, and review-record conventions first.
 

package/skills/stacked-prs/SKILL.md

@@ -1,10 +1,14 @@
 ---
 name: stacked-prs
-description: Recognize a native GitHub stacked pull request and drain it from the bottom-most ready layer up, rather than waiting for the whole stack to be ready first.
+description: Drain native GitHub stacks from the bottom ready layer.
 ---
 
 # Stacked pull requests
 
+Read applicable `AGENTS.md` and their declared adapter alias, otherwise
+`.agents/skills/stacked-prs/SKILL.md` from the repository root if present.
+Local policy overrides these defaults; do not reload an already-read adapter or canonical skill.
+
 Use when a change is a chain of native GitHub stacked pull requests. Read local `AGENTS.md` and
 `AGENTS.md` first. They own whether this repository stacks, which tool creates, rebases, and merges
 a stack, and who may authorize a merge.

package/skills/static-analysis-checklist/SKILL.md

@@ -1,10 +1,14 @@
 ---
 name: static-analysis-checklist
-description: Use when adding, changing, replacing, or removing static-analysis rules, configurations, fixtures, suppressions, allowlists, or repository guards.
+description: Place, author, and validate static-analysis invariants.
 ---
 
 # Static analysis checklist
 
+Read applicable `AGENTS.md` and their declared adapter alias, otherwise
+`.agents/skills/static-analysis-checklist/SKILL.md` from the repository root if present.
+Local policy overrides these defaults; do not reload an already-read adapter or canonical skill.
+
 Use when changing a static-analysis invariant. Read local `AGENTS.md`, analyzer
 documentation, rule inventory, and fixture conventions before selecting an implementation.
 

package/skills/storybook-authoring/SKILL.md

@@ -1,10 +1,14 @@
 ---
 name: storybook-authoring
-description: Add maintainable Storybook stories and browser-mode component coverage.
+description: Author component stories and browser coverage for real states.
 ---
 
 # Storybook authoring
 
+Read applicable `AGENTS.md` and their declared adapter alias, otherwise
+`.agents/skills/storybook-authoring/SKILL.md` from the repository root if present.
+Local policy overrides these defaults; do not reload an already-read adapter or canonical skill.
+
 Apply [test-authoring](../test-authoring/SKILL.md).
 
 - Show a meaningful supported state with realistic args and fixtures.

package/skills/swift-test-authoring/SKILL.md

@@ -1,10 +1,14 @@
 ---
 name: swift-test-authoring
-description: Add Swift and SwiftUI tests with deterministic state, networking, and view inspection.
+description: Test Swift and SwiftUI state, networking, and view behavior.
 ---
 
 # Swift test authoring
 
+Read applicable `AGENTS.md` and their declared adapter alias, otherwise
+`.agents/skills/swift-test-authoring/SKILL.md` from the repository root if present.
+Local policy overrides these defaults; do not reload an already-read adapter or canonical skill.
+
 Apply [test-authoring](../test-authoring/SKILL.md).
 
 - Test public behavior with deterministic inputs and injected dependencies.

package/skills/test-authoring/SKILL.md

@@ -1,10 +1,14 @@
 ---
 name: test-authoring
-description: Write focused, maintainable tests and test fixtures for application or library behavior.
+description: Choose meaningful tests, fixtures, and observable boundaries.
 ---
 
 # Test authoring
 
+Read applicable `AGENTS.md` and their declared adapter alias, otherwise
+`.agents/skills/test-authoring/SKILL.md` from the repository root if present.
+Local policy overrides these defaults; do not reload an already-read adapter or canonical skill.
+
 Use the repository's test conventions and the matching runner skill.
 
 - Test observable behavior, boundary failures, and regressions. Do not test implementation details.

package/skills/test-authoring/references/core-practice.md

@@ -12,3 +12,5 @@
 - For every acceptance criterion, keep evidence from a focused test, a review, or an explicitly
   justified manual check. Evidence counts only when it is falsifiable. Confirm the assertion is not
   [tautological](tautological-tests.md) before treating it as coverage.
+- For instruction and documentation contracts, test real paths, links, rendered markers, or
+  executable behavior. Do not freeze prose wording unless a real consumer parses that exact text.

package/skills/vitest-test-authoring/SKILL.md

@@ -1,10 +1,14 @@
 ---
 name: vitest-test-authoring
-description: Apply Vitest-specific patterns when adding or changing Vitest tests, mocks, or fixtures.
+description: Author deterministic Vitest assertions, mocks, and factories.
 ---
 
 # Vitest test authoring
 
+Read applicable `AGENTS.md` and their declared adapter alias, otherwise
+`.agents/skills/vitest-test-authoring/SKILL.md` from the repository root if present.
+Local policy overrides these defaults; do not reload an already-read adapter or canonical skill.
+
 Apply [test-authoring](../test-authoring/SKILL.md) first.
 
 - Isolate tests with Vitest lifecycle hooks. Restore spies and globals after each test.