@xevy/skills 0.1.63 → 0.1.65

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -2,7 +2,7 @@
2
2
  "name": "xevy",
3
3
  "displayName": "Xevy",
4
4
  "description": "Native /xevy:* SDLC workflow commands driven through the Xevy MCP server. Analyze, plan, execute, fix, and move-to-qa run locally by default and accept --cloud for the server Web Agent. Merge stays local; merge-pull-request evaluates and lands the remote PR.",
5
- "version": "0.1.63",
5
+ "version": "0.1.65",
6
6
  "author": {
7
7
  "name": "Xevy"
8
8
  },
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@xevy/skills",
3
- "version": "0.1.63",
3
+ "version": "0.1.65",
4
4
  "description": "Install Xevy agent skills and secure per-agent MCP transports for Cursor, Claude Code, Codex, and other coding agents.",
5
5
  "type": "module",
6
6
  "keywords": [
@@ -14,12 +14,13 @@ Trigger a Coolify deploy through the Xevy MCP. `$ARGUMENTS` may start with `prev
14
14
  - First word `preview` → per-task preview. `main` → project main. If unspecified (smart default): if a task is in context (`.xevy` session, an open task, or a task hint) → **preview**; otherwise → **main**. If genuinely ambiguous, ask the user.
15
15
 
16
16
  ## Preview
17
- - Resolve the task (`mcp__xevy__find_task` by code). A pushed feature branch must exist for it (recorded as the task's pull request) — if not, tell the user to run `/xevy:execute` first; `deploy_preview` returns `NO_BRANCH` otherwise.
18
- - Call `mcp__xevy__deploy_preview({ taskId, branch })` with the task's pushed branch. Report the returned status + URL.
17
+ - Resolve the task (`mcp__xevy__find_task` by code). A pushed feature branch must exist. Call `mcp__xevy__deploy_preview({ taskId })` using recorded evidence, or optionally supply its exact pushed `branch` when not yet recorded. Conflicting branch input is rejected; never rewrite repository identity to force deployment.
18
+ - Association is automatic: branch-only legacy tasks check linked deployment-enabled repositories; existing scoped records and exclusions remain authoritative. No repository selector is required. Every selected branch must be verified exactly; absent branches, inaccessible repositories, missing credentials or unavailable verification are skipped. Never substitute a default branch.
19
+ - Report actual `queued`, `partial` or `skipped` status, URLs and each repository's reason. Partial results mean only independently verified repositories queued. If nothing queued, do not claim a build started; explain the recorded reasons.
19
20
 
20
21
  ## Main
21
22
  - Call `mcp__xevy__deploy_main` for the current project. It deploys the project's REMOTE default branch and never pushes git branches; warn that unmerged local work won't appear until landed via PR. Report the main URL.
22
23
 
23
24
  ## Report progress
24
- - Deploys are async (queued → building → live). Use `mcp__xevy__get_deploy_status` to report current state. Tell the user the URL may take a few minutes to become reachable.
25
+ - Queued deploys are async (queued → building → live). Use `mcp__xevy__get_deploy_status` to report current state. Tell the user the URL may take a few minutes to become reachable.
25
26
  - If the server reports previews are disabled, say so and stop. Never push protected branches (master/main/develop/staging) to make a deploy reflect local changes.
@@ -21,7 +21,7 @@ Local implementation is the default. Pass the exact standalone `--cloud` flag to
21
21
  ## 1. Resolve and apply common gates
22
22
 
23
23
  - Resolve the task and read its current numbered Plan and linked visualization. Read the current Plan with `get_task_plan` and the saved `storyPoints` with `find_task`. Before implementation or dispatching the cloud Execute action, ensure planning is complete and the Xevy task has `storyPoints > 0`, including when no active sprint exists.
24
- - If the Plan is missing or no longer covers the requested scope, follow [plan](../plan/SKILL.md) first in the selected engine, including investigation, the canonical numbered Plan, linked visualization, and a saved story-point estimate. If only the estimate is missing or zero, size the existing Plan using `1, 2, 3, 5, 8, 13`, save `storyPoints` with `update_task`, and record a brief rationale. Re-read the task and Plan to confirm both prerequisites. If planning or saving the estimate is blocked, stop before implementation and report the gap.
24
+ - If the Plan is missing or no longer covers the requested scope, follow [plan](../plan/SKILL.md) first in the selected engine, including investigation, the canonical numbered Plan, linked visualization, and a saved story-point estimate. If only the estimate is missing or zero, size the existing Plan using `1, 2, 3, 5, 8, 13` and save `storyPoints` with `update_task`. Keep the estimate only in the dedicated field; do not duplicate it or a sizing rationale in task/Plan prose or the Artifact. Re-read the task and Plan to confirm both prerequisites. If planning or saving the estimate is blocked, stop before implementation and report the gap.
25
25
  - Show a short plan before substantial changes and wait for the user’s go-ahead. Continue approved work without asking again. Preserve original requirements and legacy history. An Analysis section and generated subtasks are never prerequisites.
26
26
  - Sprint gate: if an active sprint exists and the task is not on it, require the Plan and `storyPoints` greater than zero, then call `assign_task_to_sprint`. Record missing sprint prerequisites as blocked and preserve authorization gates.
27
27
 
@@ -28,7 +28,7 @@ Resolve routine technical choices from the code. Collect meaningful human questi
28
28
 
29
29
  ### Write the concrete Plan
30
30
 
31
- Write the canonical `## Plan` section in the task description. Synchronize an existing spec with kind `plan` when present; separate contract specs are optional when the changes need them. Use approximately five or six numbered steps; each Xevy step follows **Title — concise technical details**. Name the relevant files, functions or components, the change, and resulting behavior in one or two short sentences. Keep the plan proportionate to the task; use fewer steps for small changes.
31
+ Write the canonical `## Plan` section in the task description. Synchronize an existing spec with kind `plan` when present; separate contract specs are optional when the changes need them. Use the fewest numbered steps that still communicate every material change, condition, dependency, risk, decision, and verification needed for implementation and informed approval; there is no fixed minimum, maximum, or target count. Group related work when clear, but never omit important details merely to shorten the plan. Each step follows **Bold action phrase** — normal-weight technical details naming relevant files, functions/components, behavior, and important conditions. Keep writing concise and scannable without hiding consequential choices.
32
32
 
33
33
  Example stored in Xevy:
34
34
 
@@ -37,7 +37,7 @@ Example stored in Xevy:
37
37
 
38
38
  Plan creates zero subtasks. Preserve existing subtasks and treat them as legacy guidance. Do not convert numbered steps into subtasks, a trace-matrix document, or a required checklist. Keep verification details in separate **QA Notes** or **Technical Review Instructions** when needed.
39
39
 
40
- Estimate the planned scope using the story-point scale `1, 2, 3, 5, 8, 13` and persist the estimate in the Xevy task's `storyPoints` field with `update_task`. Include a brief sizing rationale in the Plan. This applies to every task, including tasks outside a sprint. Re-read the task with `find_task` and confirm `storyPoints > 0` before presenting Plan as complete; a number written only in prose does not complete estimation.
40
+ Estimate the planned scope using the story-point scale `1, 2, 3, 5, 8, 13` and persist the estimate only in the Xevy task's dedicated `storyPoints` field with `update_task`. Do not duplicate the estimate or a sizing rationale in the task description, Plan prose, or Artifact; the field is the source of truth. This applies to every task, including tasks outside a sprint. Re-read the task with `find_task` and confirm `storyPoints > 0` before presenting Plan as complete; a number written only in prose does not complete estimation.
41
41
 
42
42
  ### Link the visualization
43
43
 
@@ -47,7 +47,7 @@ Follow [create-artifact](../create-artifact/SKILL.md) to save a private project
47
47
 
48
48
  Check every requirement against the inspected code, numbered steps, and visualization; correct gaps before presenting it. Do not create review/sign-off subtasks. Do not start Execute or change task status as a side effect of planning.
49
49
 
50
- Read the current Plan with `get_task_plan`. In chat show only the short numbered titles, the task link, and visualization link. Keep the technical details in Xevy. For the example above, chat shows:
50
+ Read the current Plan with `get_task_plan`. In chat show the goal/interpretation and a compact decision-ready plan, with **bold action phrases** and normal-weight details; include material risks, open decisions, and verification needed for informed approval. Keep exhaustive implementation context in Xevy rather than hiding consequential information behind a link. Include the task and visualization links. Do not duplicate story-point estimates from the dedicated field. For example, chat may show:
51
51
 
52
52
  1. Remove Analyze.
53
53
  2. Simplify Plan.
@@ -45,8 +45,8 @@ Review the exact PR and report evidence-based findings. This skill is **read-onl
45
45
  ## 4. Deliver a verdict
46
46
 
47
47
  - Use plain-text headings and numbered or bulleted lists only; **never use Markdown tables**. Keep the developer-facing response short, actionable, and easy to copy and paste. Do the full review and maintain internal ledgers, but do not print exhaustive inventories or checklists unless requested. Avoid repeating evidence across sections.
48
- - At response time, obtain the actual current datetime from the system clock and convert it to **GMT+8** (UTC+08:00), for example with `TZ=Etc/GMT-8 date --iso-8601=seconds`; do not guess it. Immediately after the opening merge indicator, include **Reviewed at:** with an ISO 8601 datetime ending in `+08:00`. If the clock cannot be read, explicitly state that the timestamp is unavailable.
49
- - Start with exactly one explicit merge indicator, then the linked task code immediately before the PR URL, followed by a brief reason and the reviewed head/base SHAs. Format: `**<MERGE INDICATOR>** — <TASK-CODE> — <PR-URL>`. If multiple distinct tasks are linked, list their codes comma-separated before the PR URL. If no task is resolved, use `NO LINKED TASK` before the PR URL:
48
+ - At response time, obtain the actual current datetime from the system clock and convert it to **GMT+8** (UTC+08:00), for example with `TZ=Etc/GMT-8 date --iso-8601=seconds`; do not guess it. Immediately after the opening merge indicator, include **Task Status:** `<status>` for the linked task (or each task when multiple are linked); if no task is linked, write **Task Status:** Not linked. Follow this with **Reviewed at:** and an ISO 8601 datetime ending in `+08:00`. If a linked task's status cannot be freshly verified, state **Task Status:** Unverified and treat its merge gate as unsatisfied. If the clock cannot be read, explicitly state that the timestamp is unavailable.
49
+ - Start with exactly one explicit merge indicator, then the linked task code immediately before the PR URL, followed by a brief reason and the reviewed head/base SHAs. Format: `**<MERGE INDICATOR>** — <TASK-CODE> — <PR-URL>`. If multiple distinct tasks are linked, list their codes comma-separated before the PR URL. If no task is resolved, use `NO LINKED TASK` before the PR URL. Immediately after this opening line, print `**Task Status:** <fresh current status>` (one per linked task, or `Not linked`), then `**Reviewed at:** <ISO 8601 datetime ending in +08:00>`, in that order. This opening status line does not replace the detailed linked-task status and gate results required below. If status cannot be freshly verified, print `Unverified` and treat the task gate as unsatisfied:
50
50
  - **NOT SAFE TO MERGE** — a confirmed release blocker, conflict, failed required check, draft status, unmet review/branch-protection gate, or linked task below QA remains. For every linked task, show its identifier and freshly checked current status in the response. Only `for_qa`, `verified`, and `done` satisfy this task-status gate; `draft`, `ready`, `planned`, `in_progress`, and `qa_failed` are procedural **NOT SAFE TO MERGE** blockers even when code and checks pass. Unknown, inaccessible, or stale status is unverified and cannot satisfy the gate; refresh all linked task statuses immediately before the verdict. Continue the complete PR review and report code findings regardless of task status. Never change task records or statuses. Distinguish code-safety blockers from procedural merge gates in the reason. This takes precedence over unverified checks; still report verification gaps.
51
51
  - **SAFE TO MERGE WITH NON-BLOCKING ISSUES** — full changed scope reviewed, no confirmed blockers or unresolved material safety questions, no conflicts, required checks passed and merge gates satisfied; only non-blocking findings remain.
52
52
  - **SAFE TO MERGE** — the same verification and gate conditions are satisfied, with no outstanding findings in the reviewed scope. This is a scoped recommendation, not a guarantee of defect-free code.