jhste-skills 0.14.0 → 0.14.2

package/CHANGELOG.md

@@ -1,5 +1,19 @@
 # Changelog
 
+## 0.14.2 - 2026-09-05
+
+### Changed
+- Updated `jhste-to-tickets` to draft the issue graph with visible uncertainty and ask a user-owned question alongside the draft instead of before it.
+- Updated `jhste-prototype` to resolve an ambiguous question or evidence surface from the surrounding code and record that assumption when the user is unavailable.
+- Re-reviewed Matt Pocock's upstream at `3cca18b` with no adopted changes, recorded the OpenAI GPT-6 Astra prompting guidance reviewed for these behaviors, synchronized both READMEs, and released package version `0.14.2`.
+
+## 0.14.1 - 2026-09-03
+
+### Changed
+- Updated `jhste-subagent-orchestration` to keep safe head-owned work moving while workers are pending when the harness allows it, waiting only at real dependency barriers.
+- Updated `jhste-coding` to prefer targeted edits over rewriting otherwise unchanged files when behavior is equivalent.
+- Synchronized both READMEs, recorded the Anthropic Claude Fable 5.1 prompting guidance reviewed for these behaviors, and released package version `0.14.1`.
+
 ## 0.14.0 - 2026-08-17
 
 ### Added

package/README.en.md

@@ -15,14 +15,14 @@ Core `SKILL.md` files contain the task contract and important boundaries. Rare f
 
 ## Build and fix
 
-- **[`jhste-prototype`](skills/jhste-prototype/SKILL.md)** — tests one design question with the smallest runnable experiment and loads logic or UI detail only when relevant.
-- **[`jhste-coding`](skills/jhste-coding/SKILL.md)** — implements clear features, known fixes, refactors, exact resume steps, and in-progress merge or rebase conflict resolution while preserving repository contracts.
+- **[`jhste-prototype`](skills/jhste-prototype/SKILL.md)** — tests one design question with the smallest runnable experiment, loads logic or UI detail only when relevant, and resolves an ambiguous question from the surrounding code with a recorded assumption when the user is unavailable.
+- **[`jhste-coding`](skills/jhste-coding/SKILL.md)** — implements clear features, known fixes, refactors, exact resume steps, and in-progress merge or rebase conflict resolution while preserving repository contracts, and prefers targeted edits over rewriting otherwise unchanged files when behavior is equivalent.
 - **[`jhste-diagnosing-bugs`](skills/jhste-diagnosing-bugs/SKILL.md)** — diagnoses uncertain failures and performance regressions through symptom-specific signals, competing explanations, runtime evidence, and measurement while redacting secrets from surfaced diagnostic evidence.
 
 ## Divide and continue work
 
-- **[`jhste-subagent-orchestration`](skills/jhste-subagent-orchestration/SKILL.md)** — chooses the lightest useful structure among direct work, one owner, parallel owners, and dynamic verified waves.
-- **[`jhste-to-tickets`](skills/jhste-to-tickets/SKILL.md)** — turns defined work into one useful GitHub issue or an issue graph with real dependencies.
+- **[`jhste-subagent-orchestration`](skills/jhste-subagent-orchestration/SKILL.md)** — chooses the lightest useful structure among direct work, one owner, parallel owners, and dynamic verified waves, and keeps independent head-owned work moving while workers are pending when the harness permits it.
+- **[`jhste-to-tickets`](skills/jhste-to-tickets/SKILL.md)** — turns defined work into one useful GitHub issue or an issue graph with real dependencies, drafting first and asking user-owned questions alongside the draft.
 - **[`jhste-handoff`](skills/jhste-handoff/SKILL.md)** — creates a portable transfer for another executor or a durable record for shared evolving state.
 
 ## Review and finish

package/README.md

@@ -15,14 +15,14 @@
 
 ## 직접 만들고 고치기
 
-- **[`jhste-prototype`](skills/jhste-prototype/SKILL.md)** — production 구현 전에 하나의 설계 질문을 가장 작은 실행 가능한 실험으로 검증하고, 필요한 logic 또는 UI 지침만 추가로 읽습니다.
-- **[`jhste-coding`](skills/jhste-coding/SKILL.md)** — 충분히 이해된 기능, 알려진 수정, 리팩터링, 정확한 재개 지점, 진행 중인 merge/rebase conflict를 저장소 계약에 맞게 처리합니다.
+- **[`jhste-prototype`](skills/jhste-prototype/SKILL.md)** — production 구현 전에 하나의 설계 질문을 가장 작은 실행 가능한 실험으로 검증하고, 필요한 logic 또는 UI 지침만 추가로 읽으며, 질문이 모호하고 사용자가 없으면 주변 코드에 맞는 해석을 택하고 그 가정을 기록합니다.
+- **[`jhste-coding`](skills/jhste-coding/SKILL.md)** — 충분히 이해된 기능, 알려진 수정, 리팩터링, 정확한 재개 지점, 진행 중인 merge/rebase conflict를 저장소 계약에 맞게 처리하며, 동작이 같다면 변경되지 않은 파일 전체를 다시 쓰기보다 필요한 부분만 편집합니다.
 - **[`jhste-diagnosing-bugs`](skills/jhste-diagnosing-bugs/SKILL.md)** — 원인이 불명확한 장애와 성능 저하를 증상별 신호, 경쟁 설명, runtime 증거, 측정으로 진단하며 노출되는 진단 자료의 secret을 가립니다.
 
 ## 일을 나누고 이어가기
 
-- **[`jhste-subagent-orchestration`](skills/jhste-subagent-orchestration/SKILL.md)** — 직접 수행, 단일 소유, 병렬 소유, 동적 wave 가운데 작업에 맞는 가장 가벼운 구조로 워커를 조정합니다.
-- **[`jhste-to-tickets`](skills/jhste-to-tickets/SKILL.md)** — 정의된 작업을 하나의 유용한 GitHub issue 또는 실제 dependency가 있는 issue graph로 나눕니다.
+- **[`jhste-subagent-orchestration`](skills/jhste-subagent-orchestration/SKILL.md)** — 직접 수행, 단일 소유, 병렬 소유, 동적 wave 가운데 작업에 맞는 가장 가벼운 구조로 워커를 조정하고, 하네스가 허용하면 워커 결과와 독립적인 head 작업은 기다리지 않고 계속합니다.
+- **[`jhste-to-tickets`](skills/jhste-to-tickets/SKILL.md)** — 정의된 작업을 하나의 유용한 GitHub issue 또는 실제 dependency가 있는 issue graph로 나누고, 사용자 결정이 필요한 부분은 초안을 먼저 만든 뒤 초안과 함께 묻습니다.
 - **[`jhste-handoff`](skills/jhste-handoff/SKILL.md)** — 다른 실행자로 넘기는 portable handoff 또는 여러 소유자가 유지하는 durable handoff를 만듭니다.
 
 ## 검토하고 마무리하기

package/THIRD_PARTY_NOTICES.md

@@ -14,16 +14,18 @@ The JHSTE workflow set is independently maintained, but parts of the workflow st
 - `jhste-coding`: module/interface/seam reasoning, caller-visible contracts, avoiding shallow pass-through abstractions, and conflict resolution guided by repository history and the intent of both sides rather than conflict text alone;
 - `jhste-prototype`: disposable runnable evidence for one design question, separate logic and UI exploration modes, visible state, in-memory or stubbed side effects by default, structurally distinct UI variants, non-developer-facing shareable logic experiments, and preserving the question and verdict separately from production implementation.
 
-Upstream was re-reviewed at commit `068b6e0c62393147daf03530149cdce209c93da8` on 2026-08-17:
+Upstream was re-reviewed at commit `3cca18b368ae95cdbdebbff572ccafa662551015` on 2026-09-05 (previous review: `068b6e0c62393147daf03530149cdce209c93da8` on 2026-08-17):
 
 - https://github.com/mattpocock/skills
-- https://github.com/mattpocock/skills/tree/068b6e0c62393147daf03530149cdce209c93da8/skills/engineering/diagnosing-bugs
-- https://github.com/mattpocock/skills/tree/068b6e0c62393147daf03530149cdce209c93da8/skills/engineering/resolving-merge-conflicts
-- https://github.com/mattpocock/skills/tree/068b6e0c62393147daf03530149cdce209c93da8/skills/engineering/domain-modeling
-- https://github.com/mattpocock/skills/tree/068b6e0c62393147daf03530149cdce209c93da8/skills/productivity/to-questionnaire
-- https://github.com/mattpocock/skills/tree/068b6e0c62393147daf03530149cdce209c93da8/skills/engineering/prototype
-- https://github.com/mattpocock/skills/tree/068b6e0c62393147daf03530149cdce209c93da8/skills/productivity/grilling
-- https://github.com/mattpocock/skills/tree/068b6e0c62393147daf03530149cdce209c93da8/skills/productivity/handoff
+- https://github.com/mattpocock/skills/tree/3cca18b368ae95cdbdebbff572ccafa662551015/skills/engineering/diagnosing-bugs
+- https://github.com/mattpocock/skills/tree/3cca18b368ae95cdbdebbff572ccafa662551015/skills/engineering/resolving-merge-conflicts
+- https://github.com/mattpocock/skills/tree/3cca18b368ae95cdbdebbff572ccafa662551015/skills/engineering/domain-modeling
+- https://github.com/mattpocock/skills/tree/3cca18b368ae95cdbdebbff572ccafa662551015/skills/productivity/to-questionnaire
+- https://github.com/mattpocock/skills/tree/3cca18b368ae95cdbdebbff572ccafa662551015/skills/engineering/prototype
+- https://github.com/mattpocock/skills/tree/3cca18b368ae95cdbdebbff572ccafa662551015/skills/productivity/grilling
+- https://github.com/mattpocock/skills/tree/3cca18b368ae95cdbdebbff572ccafa662551015/skills/productivity/handoff
+
+The 2026-09-05 review found only punctuation cleanup, YAML description quoting, a grilling round display format, and two in-progress skills (`implement-spec`, `retro`) since the previous review. None was adopted: the display format is a presentation choice this set leaves open, and the in-progress skills cover flows already handled by `jhste-subagent-orchestration`, `jhste-to-tickets`, and `MAINTENANCE.md`.
 
 The current review considered upstream secret-redaction guidance for debugging evidence, intent-based merge/rebase conflict resolution, literal domain-artifact triggers, and the questionnaire boundary between the current user and another knowledge owner. JHSTE adapts these ideas into its existing authority and deletion-first model: it does not force merge completion when aborting or restarting is safer, does not turn every ADR into domain modeling, does not force questionnaires into repository files, and does not add a separate research, TDD, Wayfinder, wizard, or architecture-audit workflow.
 
@@ -94,3 +96,29 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
+
+## Anthropic Claude Fable 5.1 prompting guidance
+
+The 0.14.1 maintenance pass reviewed Anthropic's public prompting guidance for Claude Fable 5.1 and adapted two model-agnostic behaviors into the existing JHSTE contracts:
+
+- when the harness allows the head to keep working while delegated workers are pending, continue safe head-owned work that does not depend on those results and wait only at a real dependency barrier;
+- when behavior is equivalent, prefer a targeted edit over rewriting otherwise unchanged files.
+
+Guidance reviewed on 2026-09-03:
+
+- https://platform.claude.com/docs/ko/build-with-claude/prompt-engineering/prompting-claude-fable-5-1
+
+No guide text is copied. Model-specific effort, search-trigger, conversation-history, thinking-display, and API-message guidance remains outside these harness-neutral skills.
+
+## OpenAI GPT-6 Astra prompting guidance
+
+The 0.14.2 maintenance pass reviewed OpenAI's public prompting guidance for GPT-6 Astra, which notes stronger sensitivity to skill-file instructions, more frequent clarifying questions, and broader testing than a change needs. Two model-agnostic behaviors were adapted into existing contracts:
+
+- `jhste-to-tickets` drafts the issue graph with visible uncertainty and asks a user-owned question alongside the draft, matching the synthesis-first behavior already in `jhste-to-spec`;
+- `jhste-prototype` resolves an ambiguous question or evidence surface from the surrounding code and records that assumption instead of stopping when the user is unavailable.
+
+Guidance reviewed on 2026-09-05:
+
+- https://developers.openai.com/api/docs/guides/latest-model
+
+No guide text is copied. User-versus-skill precedence, delegation encouragement, writing style, and model-specific API guidance remain harness- and user-owned and are not written into these skills.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jhste-skills",
-  "version": "0.14.0",
+  "version": "0.14.2",
   "description": "A lean, harness-neutral engineering skill set for autonomous coding, diagnosis, prototyping, subagent coordination, specifications, tickets, handoffs, implementation finalization, pull request review, decision interviews, external questionnaires, and domain modeling.",
   "type": "module",
   "license": "MIT",

package/skills/jhste-coding/SKILL.md

@@ -19,6 +19,8 @@ Discover repository and environment facts directly. Make reversible, repository-
 
 Inspect the affected code, local guidance, and nearby patterns. Keep behavior that changes for the same reason together. Preserve public return shapes, nullability, errors, side effects, ordering, compatibility, authorization, and sensitive-data boundaries unless the request changes them.
 
+When behavior is equivalent, prefer targeted edits over rewriting otherwise unchanged files.
+
 Add an abstraction only when the current change demonstrates real variation, repeated change, or a clearer side-effect boundary. Avoid speculative extension points, pass-through wrappers, broad cleanup, and prototype scaffolding in production code.
 
 For an in-progress merge or rebase conflict, read [references/merge-conflicts.md](references/merge-conflicts.md) before resolving the conflicted state.

package/skills/jhste-prototype/SKILL.md

@@ -17,6 +17,8 @@ State the question, why it matters, what observation would support or falsify th
 
 Do not use a prototype to manufacture certainty around an open-ended, trivial, reversible, or user-owned choice.
 
+When the question or its evidence surface is ambiguous and the user is unavailable, choose the interpretation that matches the surrounding code and state that assumption in the recorded answer.
+
 ## Choose the evidence surface
 
 Use the smallest surface that exposes the answer clearly:

package/skills/jhste-subagent-orchestration/SKILL.md

@@ -22,6 +22,8 @@ An explicit delegation request still selects this skill. If no real worker mecha
 
 Delegate only when the outcome is decision-complete enough to assign, independently verifiable, and separable without hidden coordination. Complexity alone is not a reason to fan out. Repeated reading, duplicated setup, and integration cost count against delegation.
 
+When the harness permits the head to continue while workers are pending, continue safe head-owned work that does not depend on those results. Wait only at a real dependency barrier.
+
 ## Respect the harness boundary
 
 Treat model selection, provider selection, reasoning or effort, worker count, concurrency, concrete agent configuration, isolation, and scheduling as user- and harness-owned. Do not choose, recommend, or override them.

package/skills/jhste-to-tickets/SKILL.md

@@ -13,7 +13,7 @@ Create issue boundaries that represent coherent outcomes, ownership, and verific
 
 Identify the repository and read referenced issues, specifications, guidance, domain context, and enough relevant code and tests to understand current contracts and validation paths. Discover repository facts directly.
 
-Ask only for a user-owned decision that would materially change scope, issue boundaries, or real dependencies. Do not encode unsettled behavior or an unknown root cause as implementation tickets.
+Ask only for a user-owned decision that would materially change scope, issue boundaries, or real dependencies. Draft the rest of the graph with that uncertainty visible and ask alongside the draft. Do not encode unsettled behavior or an unknown root cause as implementation tickets.
 
 ## Choose the smallest useful graph