@xevy/skills 0.1.24 → 0.1.28

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.
@@ -1,26 +1,64 @@
1
1
  ---
2
2
  name: analyze
3
- description: Analyze a task in the cloud — run the Xevy server agent's 'analyze' action, then review and correct the resulting Analysis section. Use /xevy:analyze-here to analyze locally instead.
4
- argument-hint: "[task]"
3
+ description: Analyze a task locally in the current coding-agent session by default — inspect the codebase, write the Analysis section and story points, then self-review. Pass --cloud to delegate analysis to the Xevy server agent, then review and correct its result.
4
+ argument-hint: "[task] [--cloud]"
5
5
  disable-model-invocation: true
6
- allowed-tools: "Read Grep Bash mcp__xevy__find_task mcp__xevy__update_task mcp__xevy__list_specs mcp__xevy__list_subtasks mcp__xevy__start_ai_action mcp__xevy__get_ai_execution mcp__xevy__list_ai_executions"
6
+ allowed-tools: "Read Grep Bash mcp__xevy__find_task mcp__xevy__update_task mcp__xevy__list_specs mcp__xevy__list_subtasks mcp__xevy__list_task_notes mcp__xevy__create_task_note mcp__xevy__list_task_decisions mcp__xevy__create_decision mcp__xevy__answer_decision mcp__xevy__start_ai_action mcp__xevy__get_ai_execution mcp__xevy__list_ai_executions"
7
7
  ---
8
8
 
9
- # /xevy:analyze — analyze in the cloud (then review)
9
+ # /xevy:analyze — analyze locally or in the cloud
10
10
 
11
- Cloud is the default engine: the Xevy server agent does the analysis; **you then review and correct it**. To analyze locally instead, use `/xevy:analyze-here`.
11
+ Local analysis is the default. Pass the exact standalone `--cloud` flag to delegate the analysis to the Xevy server agent.
12
+
13
+ ## 0. Choose the engine
14
+
15
+ - Parse `$ARGUMENTS` for the exact standalone `--cloud` token and remove that token before resolving the task. Do not treat similar text such as `--cloudy` as the flag.
16
+ - Without `--cloud`, follow the **Local workflow** and do not call `start_ai_action`.
17
+ - With `--cloud`, follow the **Cloud workflow**.
12
18
 
13
19
  ## 1. Resolve the task
14
- Resolve from `$ARGUMENTS` (`mcp__xevy__find_task` by code) or the in-context task. If ambiguous, ask which task.
15
20
 
16
- ## 2. Run the cloud action
17
- - `mcp__xevy__start_ai_action({ taskId, action: "analyze", stream: true })` — **always pass `stream: true`**. The call blocks and streams live per-step progress; report it as it arrives. Do **NOT** use fire-and-forget or `sleep`/manual poll loops — streaming is the default and is reliable.
18
- - Only if this streamed call returns *before* a terminal status (genuine client disconnect — the run keeps going server-side) resume with `mcp__xevy__get_ai_execution` until `succeeded | failed | cancelled` (newest run via `list_ai_executions` if needed).
19
- - If it fails, read the captured output, report the error, and offer to retry or fall back to `/xevy:analyze-here`.
21
+ Resolve the remaining task argument or the in-context task (`mcp__xevy__find_task` / `find_task`). If ambiguous, ask which task. Read existing specs, subtasks, and notes.
22
+
23
+ ## 2A. Local workflow (default)
24
+
25
+ ### Decisions gate
26
+
27
+ Call `mcp__xevy__list_task_decisions`. If any decision is **open**, resolve it before doing the work: present each open question through the host's user-question mechanism using its preset choices and explanations, record the answer with `mcp__xevy__answer_decision`, and fold the answers into the analysis. Never guess or bypass an open decision.
28
+
29
+ ### Inspect the codebase
30
+
31
+ Read the relevant files, including callers, callees, and similar patterns. Identify whether the task involves UI changes; if so, study existing UI patterns and record a `UI/UX Flow` note with `mcp__xevy__create_task_note`. Base decisions on established patterns and ask only about genuine ambiguity.
32
+
33
+ ### Write the Analysis
34
+
35
+ Use `mcp__xevy__update_task` to append a `## Analysis` section without replacing the user's original request:
36
+
37
+ - **Overview:** plain-language summary, before/after behaviour, user impact, and key decisions.
38
+ - **Technical Implementation:** affected files/modules, API/data/UI changes, assumptions, risks, and verification approach.
39
+ - Estimate `storyPoints` (1 trivial · 2 small · 3 medium · 5 large · 8 XL · 13 epic) and set it.
40
+ - For a genuine ambiguity that a human must resolve, record it with `mcp__xevy__create_decision` using preset choices and explanations. If the user is present, use the host's user-question mechanism and persist the result with `create_decision` + `answer_decision`.
41
+
42
+ ### Review and correct
43
+
44
+ Re-read the Analysis against the actual code. Confirm every claim is accurate, affected files exist, and risks and acceptance criteria are concrete. Fix every gap or inaccuracy before finishing. Call `mcp__xevy__list_task_decisions` again and surface any decision that remains open.
45
+
46
+ Report a PASS/PARTIAL verdict, what you corrected, any open decisions, and the task URL. Do not push the user to the next phase.
47
+
48
+ ## 2B. Cloud workflow (`--cloud`)
49
+
50
+ ### Run the server action
51
+
52
+ - Call `mcp__xevy__start_ai_action({ taskId, action: "analyze", stream: true })`; always pass `stream: true`. The call blocks and streams live per-step progress, so report progress as it arrives. Do not use fire-and-forget or sleep/manual polling loops.
53
+ - Only if the streamed call returns before a terminal status because of a genuine client disconnect, resume with `mcp__xevy__get_ai_execution` until `succeeded | failed | cancelled` (use `list_ai_executions` to find the newest run if needed).
54
+ - If it fails, read the captured output, report the error, and offer to retry or rerun `/xevy:analyze` without `--cloud`.
55
+
56
+ ### Review and correct
20
57
 
21
- ## 3. Review & correct (MANDATORY — do not finish until clean)
22
58
  Act as the reviewer of the cloud result:
23
- - Re-read the task (`find_task`) and any specs/subtasks. Re-read the Analysis section the agent wrote.
24
- - Check it actually covers: Overview (plain-language, before/after, user impact), Technical Implementation (affected files, API/data/UI changes, assumptions, risks, verification), and a `storyPoints` estimate. Inspect the referenced code with Read/Grep to confirm the analysis is accurate, not hand-wavy.
25
- - If anything is missing, wrong, or contradicts the code, **fix it** via `mcp__xevy__update_task` (append/repair the Analysis section — never delete the user's original request) and set `storyPoints` if absent.
26
- - Report a PASS/PARTIAL verdict, what you corrected, and the task URL. Don't push the user to the next phase.
59
+
60
+ - Re-read the task, specs, subtasks, and the Analysis section the agent wrote.
61
+ - Confirm it covers the plain-language overview, before/after behaviour, user impact, affected files, API/data/UI changes, assumptions, risks, verification, and a `storyPoints` estimate. Inspect referenced code with Read/Grep rather than trusting the write-up.
62
+ - Repair missing, inaccurate, or contradictory material with `mcp__xevy__update_task`; append or repair the Analysis and never delete the user's original request. Set `storyPoints` if absent.
63
+
64
+ Report a PASS/PARTIAL verdict, what you corrected, and the task URL. Do not push the user to the next phase.
@@ -1,29 +1,69 @@
1
1
  ---
2
2
  name: execute
3
- description: Execute a task in the cloud — run the Xevy server agent's 'execute' action (implements, pushes a branch, opens a PR), then review the diff/PR, run tests, correct issues, and deploy a preview. Use /xevy:execute-here to implement locally.
4
- argument-hint: "[task]"
3
+ description: Execute a task locally in the current coding-agent session by default — use the task worktree, implement the plan, verify, push, and open a PR. Pass --cloud to delegate implementation to the Xevy server agent, then review and correct its result.
4
+ argument-hint: "[task] [--cloud]"
5
5
  disable-model-invocation: true
6
- allowed-tools: "Read Grep Edit Bash Agent mcp__xevy__find_task mcp__xevy__update_task mcp__xevy__list_subtasks mcp__xevy__list_sprints mcp__xevy__assign_task_to_sprint mcp__xevy__start_ai_action mcp__xevy__get_ai_execution mcp__xevy__list_ai_executions mcp__xevy__deploy_preview mcp__xevy__get_deploy_status"
6
+ allowed-tools: "Read Grep Edit Write Bash Agent mcp__xevy__find_task mcp__xevy__update_task mcp__xevy__update_task_status mcp__xevy__list_specs mcp__xevy__list_subtasks mcp__xevy__update_subtask mcp__xevy__list_sprints mcp__xevy__assign_task_to_sprint mcp__xevy__list_task_decisions mcp__xevy__create_decision mcp__xevy__answer_decision mcp__xevy__start_ai_action mcp__xevy__get_ai_execution mcp__xevy__list_ai_executions set_session_task_lock"
7
7
  ---
8
8
 
9
- # /xevy:execute — execute in the cloud (then review + deploy)
9
+ # /xevy:execute — execute locally or in the cloud
10
10
 
11
- Cloud is the default engine: the Xevy server agent implements the task, pushes a feature branch, and opens a PR. **You then review the result, correct issues, and deploy a preview.** To implement locally, use `/xevy:execute-here`.
11
+ Local implementation is the default. Pass the exact standalone `--cloud` flag to delegate implementation to the Xevy server agent.
12
12
 
13
- ## 1. Resolve + gates
14
- - Resolve the task (`$ARGUMENTS` / context). Confirm planning artifacts exist (`list_subtasks`); if none and the task is non-trivial, suggest `/xevy:plan` first.
15
- - Sprint gate: if an active sprint exists (`list_sprints` status=active) and the task isn't on it, ensure it has `## Analysis` + `storyPoints` > 0, then `assign_task_to_sprint` — else stop and ask the user to analyze/estimate first.
13
+ ## 0. Choose the engine
16
14
 
17
- ## 2. Run the cloud action
18
- - `mcp__xevy__start_ai_action({ taskId, action: "execute", stream: true })` — **always pass `stream: true`**. The call blocks and streams live per-step progress; report it as it arrives. Do **NOT** use fire-and-forget or `sleep`/manual poll loops — streaming is the default and is reliable. Only if this streamed call returns *before* a terminal status (genuine disconnect — the run keeps going server-side) resume with `get_ai_execution`. On failure, surface the output; offer retry or `/xevy:execute-here`.
19
- - On success the server has pushed the feature branch and opened a PR (recorded on the task).
15
+ - Parse `$ARGUMENTS` for the exact standalone `--cloud` token and remove that token before resolving the task. Do not treat similar text such as `--cloudy` as the flag.
16
+ - Without `--cloud`, follow the **Local workflow** and do not call `start_ai_action`.
17
+ - With `--cloud`, follow the **Cloud workflow**.
20
18
 
21
- ## 3. Review & correct (MANDATORY — you are the reviewer)
22
- Do NOT finish until the change is verified and correct:
23
- - `git fetch origin` and check out / diff the task's feature branch (read the branch from `find_task` → pull request metadata). Inspect the full diff against the task requirements and plan (trace each requirement to code).
24
- - Run the project's checks (type-check, lint, tests). Read failures; if anything is broken, incomplete, or violates a "must NOT" constraint, **fix it**: edit the files, then commit + push to the **feature branch** (never a protected branch). You may dispatch the **reviewer** subagent for an independent pass.
25
- - **Frontend/UI changes:** before editing any UI (pages, components, app shell, forms, styling), follow the `/xevy:xevy-design` skill so the change matches the project design system (`./.xevy/design.md`).
26
- - Re-run checks until green. Refresh the PR. Summarise PASS/PARTIAL/FAIL with file:line evidence and what you corrected.
19
+ ## 1. Resolve and apply common gates
27
20
 
28
- ## 4. Deploy a preview
29
- - After review passes, `mcp__xevy__deploy_preview({ taskId, branch })` with the feature branch; report the URL (poll `get_deploy_status`). Preview failure is non-blocking — note it and continue.
21
+ - Resolve the remaining task argument or the in-context task. Read its `## Analysis`, plan spec, and subtasks. If planning artifacts are absent and the task is non-trivial, suggest `/xevy:plan` or ask whether to plan-and-execute or execute directly.
22
+ - Sprint gate: if an active sprint exists and the task is not on it, require `## Analysis` and `storyPoints` greater than zero, then call `assign_task_to_sprint`; otherwise stop and ask the user to analyze and estimate first.
23
+
24
+ ## 2A. Local workflow (default)
25
+
26
+ ### Decisions gate
27
+
28
+ Call `mcp__xevy__list_task_decisions` before implementing. If any decision is **open**, present it through the host's user-question mechanism, record the answer with `mcp__xevy__answer_decision`, and fold it into the work. If a relevant subtask is already done, the answer may require a new subtask. Never guess or bypass an open decision.
29
+
30
+ ### Worktree protocol
31
+
32
+ - Record the current branch and directory. Derive a canonical branch `xevy/<TASK-ID>-<slug>` using the task code or the first eight characters of its UUID. Reuse an existing task branch; never create a second branch for the same task.
33
+ - Create or attach a git worktree in a sibling directory and change into it. When resuming, first merge the latest source branch (for example `git merge origin/main`). Do all work in the task worktree.
34
+ - In Pi, call `set_session_task_lock(taskCode, taskId, taskTitle, worktreePath, branch)` immediately after attaching the worktree, using the absolute `git rev-parse --show-toplevel` path. If the tool is unavailable, continue while keeping the worktree rules.
35
+ - Never commit or push on a protected branch (`master`, `main`, `develop`, `staging`); use only the `xevy/*` task branch.
36
+
37
+ ### Implement
38
+
39
+ - Move the task to `in_progress` with `update_task_status` when implementation begins. This mirrors cloud execution, which moves to `in_progress` at start and `for_review` on success.
40
+ - Work through subtasks in order. When useful and supported, dispatch builder/frontend subagents with the worktree as their working directory. Keep changes surgical, match existing style, and update subtask status through MCP.
41
+ - Before editing UI pages, components, app shell, forms, or styling, follow `/xevy:xevy-design` and the project's `./.xevy/design.md`.
42
+ - If a genuine human decision appears mid-implementation, record it with `mcp__xevy__create_decision` using preset choices rather than guessing. If the user is present, persist their answer with `create_decision` + `answer_decision`.
43
+ - Validate after each step: type-check, lint, then targeted tests.
44
+
45
+ ### Review, push, and hand off
46
+
47
+ - Run the full project checks. Trace every requirement to code and verify every “must NOT” constraint. When supported, dispatch a **reviewer** for an independent PASS/PARTIAL/FAIL with file:line evidence; otherwise do a separate review pass. Fix all findings and re-run checks until green.
48
+ - Commit and push the task branch. Open or refresh the PR and always give the user its PR or compare link. Do not merge automatically.
49
+ - Record the branch on the task in `aiPullRequest.branch`, then move the task to `for_review` with `update_task_status`.
50
+ - Do not deploy Preview automatically. Preview is an explicit user action via `/xevy:deploy preview`.
51
+
52
+ ## 2B. Cloud workflow (`--cloud`)
53
+
54
+ ### Run the server action
55
+
56
+ - Call `mcp__xevy__start_ai_action({ taskId, action: "execute", stream: true })`; always pass `stream: true`. Report live per-step progress as it arrives. Do not use fire-and-forget or sleep/manual polling loops.
57
+ - Only if the streamed call returns before a terminal status because of a genuine disconnect, resume with `mcp__xevy__get_ai_execution` (use `list_ai_executions` if needed).
58
+ - On failure, surface the captured output and offer to retry or rerun `/xevy:execute` without `--cloud`.
59
+ - On success, the server has pushed the feature branch and opened a PR recorded on the task.
60
+
61
+ ### Review and correct
62
+
63
+ - Fetch origin and inspect the task's feature branch using the pull-request metadata from `find_task`. Trace every requirement in the task and plan to the full diff.
64
+ - Run the project's type-check, lint, and tests. Fix anything broken, incomplete, or contrary to a “must NOT” constraint; commit and push corrections to the feature branch, never a protected branch. When useful, dispatch a **reviewer** for an independent pass.
65
+ - Before correcting UI code, follow `/xevy:xevy-design` and the project's `./.xevy/design.md`.
66
+ - Re-run checks until green and refresh the PR. Report PASS/PARTIAL/FAIL with file:line evidence and corrections made.
67
+ - Do not deploy Preview automatically. Preview is an explicit user action via `/xevy:deploy preview`.
68
+
69
+ Report the PR and verification result.
@@ -1,26 +1,58 @@
1
1
  ---
2
2
  name: fix
3
- description: Apply a fix/rework to a task in the cloud — run the Xevy server agent's 'fix' action (reworks, pushes, refreshes the PR), then review the diff, run tests, correct issues, and redeploy the preview. Use /xevy:fix-here to fix locally.
4
- argument-hint: "[task]"
3
+ description: Apply a task fix locally in the current coding-agent session by default — reuse its worktree, rework, verify, push, and refresh the PR. Pass --cloud to delegate the fix to the Xevy server agent, then review and correct its result.
4
+ argument-hint: "[task] [--cloud]"
5
5
  disable-model-invocation: true
6
- allowed-tools: "Read Grep Edit Bash Agent mcp__xevy__find_task mcp__xevy__start_ai_action mcp__xevy__get_ai_execution mcp__xevy__list_ai_executions mcp__xevy__deploy_preview mcp__xevy__get_deploy_status"
6
+ allowed-tools: "Read Grep Edit Write Bash Agent mcp__xevy__find_task mcp__xevy__update_task mcp__xevy__list_subtasks mcp__xevy__update_subtask mcp__xevy__start_ai_action mcp__xevy__get_ai_execution mcp__xevy__list_ai_executions"
7
7
  ---
8
8
 
9
- # /xevy:fix — fix in the cloud (then review + redeploy)
9
+ # /xevy:fix — fix locally or in the cloud
10
10
 
11
- Cloud is the default engine: the server agent reworks the task and refreshes the PR; **you then review and correct.** To fix locally, use `/xevy:fix-here`.
11
+ Local rework is the default. Pass the exact standalone `--cloud` flag to delegate the fix to the Xevy server agent.
12
+
13
+ ## 0. Choose the engine
14
+
15
+ - Parse `$ARGUMENTS` for the exact standalone `--cloud` token and remove that token before resolving the task. Do not treat similar text such as `--cloudy` as the flag.
16
+ - Without `--cloud`, follow the **Local workflow** and do not call `start_ai_action`.
17
+ - With `--cloud`, follow the **Cloud workflow**.
12
18
 
13
19
  ## 1. Resolve
14
- Resolve the task (`$ARGUMENTS` / context). It should already have a feature branch from a prior execute.
15
20
 
16
- ## 2. Run the cloud action
17
- - `mcp__xevy__start_ai_action({ taskId, action: "fix", stream: true })` — **always pass `stream: true`**. The call blocks and streams live per-step progress; report it as it arrives. Do **NOT** use fire-and-forget or `sleep`/manual poll loops — streaming is the default and is reliable. Only if this streamed call returns *before* a terminal status (genuine disconnect — the run keeps going server-side) resume with `get_ai_execution`. On failure surface output and offer retry or `/xevy:fix-here`.
21
+ Resolve the remaining task argument or the in-context task. It should already have a feature branch from a previous execute.
22
+
23
+ ## 2A. Local workflow (default)
24
+
25
+ ### Locate the worktree
26
+
27
+ Find the existing task worktree and branch with `git worktree list`, matching by task code. The worktree must already exist; do not create a new branch. If none exists, stop and ask. Merge the latest source branch into the feature branch first to avoid divergence.
28
+
29
+ ### Rework
30
+
31
+ Make the requested fix in the worktree with the host's read/search/edit tools, or use a builder subagent with that worktree as its working directory. Keep the change surgical and correct the root cause rather than symptoms. Update subtasks through MCP.
32
+
33
+ Before editing UI pages, components, app shell, forms, or styling, follow `/xevy:xevy-design` and the project's `./.xevy/design.md`.
34
+
35
+ ### Review, push, and hand off
36
+
37
+ - Run the full project checks. Verify the issue is fixed without regressions and check every “must NOT” constraint. When supported, dispatch a **reviewer** for an independent PASS/PARTIAL/FAIL with file:line evidence; otherwise perform a separate review pass. Fix every finding and re-run until green.
38
+ - Commit and push the feature branch, refresh the PR, and give the user its link. Do not merge automatically.
39
+ - Do not redeploy Preview automatically. Preview is an explicit user action via `/xevy:deploy preview`.
40
+ - Ask whether to merge with `/xevy:merge`; do not merge on your own.
41
+
42
+ ## 2B. Cloud workflow (`--cloud`)
43
+
44
+ ### Run the server action
45
+
46
+ - Call `mcp__xevy__start_ai_action({ taskId, action: "fix", stream: true })`; always pass `stream: true`. Report live progress as it arrives. Do not use fire-and-forget or sleep/manual polling loops.
47
+ - Only if the streamed call returns before a terminal status because of a genuine disconnect, resume with `mcp__xevy__get_ai_execution` (use `list_ai_executions` if needed).
48
+ - On failure, surface the output and offer to retry or rerun `/xevy:fix` without `--cloud`.
49
+
50
+ ### Review and correct
18
51
 
19
- ## 3. Review & correct (MANDATORY)
20
- - `git fetch origin` and diff the task's feature branch. Verify the fix actually resolves the reported issue and introduces no regressions; trace to the failing requirement / QA finding.
21
- - Run type-check/lint/tests. If still broken or incomplete, **fix it** — edit, commit, push to the feature branch (never protected). Dispatch the **reviewer** subagent for an independent pass. Re-run until green.
22
- - **Frontend/UI changes:** before editing any UI (pages, components, app shell, forms, styling), follow the `/xevy:xevy-design` skill so the change matches the project design system (`./.xevy/design.md`).
23
- - Report PASS/PARTIAL/FAIL with evidence and what you corrected.
52
+ - Fetch origin and diff the task's feature branch. Verify the fix resolves the reported issue and introduces no regression; trace it to the failing requirement or QA finding.
53
+ - Run type-check, lint, and tests. If the result remains broken or incomplete, fix it and commit/push to the feature branch, never a protected branch. When useful, dispatch a **reviewer** for an independent pass.
54
+ - Before correcting UI code, follow `/xevy:xevy-design` and the project's `./.xevy/design.md`.
55
+ - Re-run until green and report PASS/PARTIAL/FAIL with evidence and corrections made.
56
+ - Do not redeploy Preview automatically. Preview is an explicit user action via `/xevy:deploy preview`.
24
57
 
25
- ## 4. Redeploy preview
26
- - `mcp__xevy__deploy_preview({ taskId, branch })`; report the URL (poll `get_deploy_status`). Non-blocking.
58
+ Report the refreshed PR and verification result.
@@ -1,31 +1,55 @@
1
1
  ---
2
2
  name: generate-image
3
- description: Generate an image from a text prompt and store it in the current Xevy project. Use when the user asks to "generate an image of X", "make a logo/mockup/illustration", or otherwise create a visual asset. The image is generated via OpenRouter, stored as a project attachment, and a usable URL is returned; it also appears in the project Gallery.
4
- argument-hint: "[prompt describing the image] [--model <id>] [--task <task-code>]"
5
- allowed-tools: "mcp__xevy__generate_image mcp__xevy__find_task mcp__xevy__get_current_user"
3
+ description: Generate an image from a text prompt and save it in the current Xevy project's Gallery. Use when the user asks to generate an image, logo, mockup, illustration, or other visual asset. Prefer the agent host's built-in image generation feature; use Xevy image generation only when the user explicitly requests it or when no built-in image generation feature is available.
6
4
  ---
7
5
 
8
- # /xevy:generate-image — generate an image into the project
6
+ # Generate an image
9
7
 
10
- Turn a text prompt into a stored image asset in the current Xevy project. The result is saved as a project attachment (`source=generated`) and returned as a URL, and it shows up in the project **Gallery** alongside uploaded media and generated videos.
8
+ Turn the user's prompt into an image with the best generation feature available in the current agent host, then save the result in the current Xevy project's Gallery.
11
9
 
12
- ## 1. Resolve context
13
- - Resolve `workspaceIdentifier` + `projectIdentifier` from `.xevy/project.json` when available; otherwise ask the user (or use `list_workspaces` / `list_projects`).
14
- - Generation requires **write access** to the project. If the user is a guest/read-only member the tool returns 403 — relay that plainly.
10
+ ## 1. Choose the generation path
15
11
 
16
- ## 2. Build the prompt
17
- - Use the user's description as the `prompt`. Keep it faithful to what they asked; don't silently restyle.
18
- - Optional inputs:
19
- - `model` — an OpenRouter image model id. Omit to use the project default (`google/gemini-3-pro-image-preview`).
20
- - `size` — a size hint like `1024x1024` (recorded with the asset).
21
- - `fileName` — a friendly file name.
22
- - `taskId` — when the image relates to a specific task, pass its UUID so the Gallery can link the asset back to that task. If the user references a task **code** (e.g. VI02-10), resolve it to a UUID with `find_task` first.
12
+ Use this order:
23
13
 
24
- ## 3. Generate
25
- - Call `generate_image` with `{ workspaceIdentifier, projectIdentifier, prompt, model?, size?, fileName?, taskId? }`.
26
- - It returns `{ attachmentId, url, fileName, mimeType, sizeBytes, prompt, model }`.
14
+ 1. If the user explicitly asks for Xevy image generation or a Xevy/OpenRouter model, use the **Xevy path**.
15
+ 2. Otherwise, if the agent host provides a built-in image generation feature, use the **built-in path**.
16
+ 3. If no built-in image generation feature is available, use the **Xevy path** as the fallback.
27
17
 
28
- ## 4. Report back
29
- - Give the user the returned **URL** (clickable) and the file name, and mention the image is now in the project Gallery.
30
- - Generation is a paid provider call — generate once per request; don't loop or retry on success.
31
- - Never print API keys or environment values. If generation fails, surface the error message from the tool (provider/storage boundary) without inventing a cause.
18
+ Use Xevy for Gallery storage regardless of which feature generates the image. Do not use Xevy's `generate_image` merely because the repository is linked to a Xevy project. If a built-in generation attempt fails, report that failure and ask before switching to Xevy's paid provider unless the user already requested Xevy. If neither built-in generation nor Xevy's `generate_image` tool is available, explain that no image generator is available and stop.
19
+
20
+ ## 2. Resolve Xevy context
21
+
22
+ - Resolve `workspaceIdentifier` and `projectIdentifier` from `.xevy/project.json` when available; otherwise ask the user or use Xevy's workspace and project discovery tools.
23
+ - Confirm the user has project write access before generating. Relay a 403 response plainly.
24
+ - Resolve an optional referenced task code such as `VI02-10` to its UUID with `find_task` so the Gallery asset can link back to the task.
25
+ - Stop before generation if the project cannot be resolved or the selected storage tool is unavailable. The completed request must include a Gallery attachment.
26
+
27
+ ## 3. Build the prompt
28
+
29
+ - Keep the prompt faithful to the user's request; do not silently change the subject, style, composition, text, or brand direction.
30
+ - Preserve exact text verbatim when the image must contain copy.
31
+ - Include supplied reference images when the selected generation feature supports them.
32
+
33
+ ## 4. Built-in path (default)
34
+
35
+ - Use the agent host's built-in image generation feature and follow its native tool instructions.
36
+ - Pass the user's image description and any supported reference images directly to that feature.
37
+ - After generation, call Xevy's `create_attachment` to save the output in the Gallery:
38
+ - Prefer `sourceUrl` when the built-in feature returns a public `http(s)` image URL.
39
+ - Pass a returned data URL directly as `dataBase64`. For a local file, encode its bytes as base64 and pass `dataBase64`; do not pass a local path as `sourceUrl`.
40
+ - Pass `mimeType`, a friendly `fileName`, the prompt as `description`, optional `taskId`, and `public: true`.
41
+ - Provide exactly one of `sourceUrl` or `dataBase64`; inline data must be no larger than 25 MB.
42
+ - Report the URL and file name returned by `create_attachment`, and state that the image is available in the project Gallery.
43
+ - If attachment creation fails, report that the image was generated but not saved to the Gallery. Do not claim the request completed successfully.
44
+
45
+ ## 5. Xevy path (explicit or fallback)
46
+
47
+ 1. Call Xevy's `generate_image` tool with:
48
+ - `workspaceIdentifier`
49
+ - `projectIdentifier`
50
+ - `prompt`
51
+ - optional `model`, `size`, and `fileName`; `size` accepts `512`, `1K`, `2K`, `4K`, or explicit pixels such as `1024x1024`
52
+ - optional resolved `taskId`
53
+ 2. Report the returned clickable URL and file name, and state that the image is available in the project Gallery.
54
+
55
+ `generate_image` stores the result in the Gallery and returns `{ attachmentId, url, fileName, mimeType, sizeBytes, prompt, model }`. Xevy generation is a paid provider call: generate once per request and do not retry after success. Never print API keys or environment values. On failure, surface the tool's error without inventing a cause.
@@ -16,7 +16,7 @@ allowed-tools: "Read Grep Bash Write Delete mcp__xevy__connector_list mcp__xevy_
16
16
 
17
17
  # /xevy:investigate — diagnose before fixing
18
18
 
19
- **Investigate first. Do not fix blindly.** Gather evidence with a small, disposable script, report findings, then let the user decide whether to fix (e.g. via `/xevy:fix-here`).
19
+ **Investigate first. Do not fix blindly.** Gather evidence with a small, disposable script, report findings, then let the user decide whether to fix (for example via `/xevy:fix`, which runs locally by default).
20
20
 
21
21
  ## When to use
22
22
 
@@ -1,24 +1,56 @@
1
1
  ---
2
2
  name: merge
3
- description: Merge a task's branch in the cloud — the Xevy server agent's 'merge' action verifies the open-subtasks gate, syncs the base branch into the feature to resolve conflicts, then lands the feature into the base/default branch (GitHub PR merge when possible, else a local merge + push of the base). Review the result and run tests after. Use /xevy:merge-here to merge locally.
4
- argument-hint: "[task]"
3
+ description: Merge a task branch locally in the current coding-agent session by default — merge it into the current branch without pushing, verify, and review. Pass --cloud to have the Xevy server agent land the branch into the remote base/default branch, then review the result.
4
+ argument-hint: "[task] [--cloud]"
5
5
  disable-model-invocation: true
6
- allowed-tools: "Read Grep Bash mcp__xevy__find_task mcp__xevy__start_ai_action mcp__xevy__get_ai_execution mcp__xevy__list_ai_executions mcp__xevy__deploy_main mcp__xevy__get_deploy_status"
6
+ allowed-tools: "Read Grep Edit Bash mcp__xevy__find_task mcp__xevy__start_ai_action mcp__xevy__get_ai_execution mcp__xevy__list_ai_executions mcp__xevy__deploy_main mcp__xevy__get_deploy_status"
7
7
  ---
8
8
 
9
- # /xevy:merge — merge in the cloud (then review)
9
+ # /xevy:merge — merge locally or in the cloud
10
10
 
11
- Cloud is the default engine: the server agent verifies the open-subtasks gate, syncs the base branch into the feature to resolve conflicts, then **lands the feature into the base/default branch** — via the GitHub merge API when possible (honouring branch protection), otherwise a local merge + push of the base. No task-status change. **You then review.** To merge locally, use `/xevy:merge-here`.
11
+ Local-only merge is the default. Pass the exact standalone `--cloud` flag to have the Xevy server agent land the task branch into the remote base/default branch. These modes have materially different push semantics, so follow only the selected workflow.
12
+
13
+ ## 0. Choose the engine
14
+
15
+ - Parse `$ARGUMENTS` for the exact standalone `--cloud` token and remove that token before resolving the task. Do not treat similar text such as `--cloudy` as the flag.
16
+ - Without `--cloud`, follow the **Local workflow** and do not call `start_ai_action`.
17
+ - With `--cloud`, follow the **Cloud workflow**.
12
18
 
13
19
  ## 1. Resolve
14
- Resolve the task (`$ARGUMENTS` / context).
15
20
 
16
- ## 2. Run the cloud action
17
- - `mcp__xevy__start_ai_action({ taskId, action: "merge", stream: true })` — **always pass `stream: true`**. The call blocks and streams live per-step progress; report it as it arrives, plus any conflicts/verification results it reports. Do **NOT** use fire-and-forget or `sleep`/manual poll loops — streaming is the default and is reliable. Only if this streamed call returns *before* a terminal status (genuine disconnect — the run keeps going server-side) resume with `get_ai_execution`. On failure surface output.
21
+ Resolve the remaining task argument or the in-context task and its canonical feature branch.
22
+
23
+ ## 2A. Local workflow (default)
24
+
25
+ ### Merge locally
26
+
27
+ Merge the task branch into the current checked-out branch in the current worktree. Fetch and merge from remote if the task branch exists only there. If conflicts occur, resolve them directly, stage the resolutions, and complete the merge commit.
28
+
29
+ ### Review and correct
30
+
31
+ Run verification for the merged scope: inspect `git status`, then run the project's test, lint, and build checks. Report clear PASS/FAIL plus every conflict file resolved. Fix failures before finishing.
32
+
33
+ ### Local safety rules
34
+
35
+ - The merge is local only. Do not push and do not change task status; in particular, do not move the task to `done`. The user pushes manually from the main worktree.
36
+ - Keep the task worktree for iteration; do not delete it.
37
+
38
+ ## 2B. Cloud workflow (`--cloud`)
39
+
40
+ ### Run the server action
41
+
42
+ - Call `mcp__xevy__start_ai_action({ taskId, action: "merge", stream: true })`; always pass `stream: true`. Report live progress, conflicts, and verification results as they arrive. Do not use fire-and-forget or sleep/manual polling loops.
43
+ - Only if the streamed call returns before a terminal status because of a genuine disconnect, resume with `mcp__xevy__get_ai_execution` (use `list_ai_executions` if needed).
44
+ - On failure, surface the output and offer to retry or rerun `/xevy:merge` without `--cloud` for a local-only merge.
45
+
46
+ The server agent verifies the open-subtasks gate, syncs the base into the feature branch, then lands the feature into the remote base/default branch through the GitHub merge API when possible or a local merge and push otherwise. The action does not change task status.
47
+
48
+ ### Review and correct
49
+
50
+ - Fetch origin and inspect the merged branch. Confirm the merge is clean, the base was integrated, and build/tests pass.
51
+ - If conflicts remain or tests fail, fix them on the feature branch; never push a protected branch directly. Re-verify before finishing.
52
+ - Report PASS/PARTIAL/FAIL with evidence. Merge mode must not move the task to `done`.
18
53
 
19
- ## 3. Review & correct (MANDATORY)
20
- - `git fetch origin` and inspect the merged branch. Confirm the merge is clean, the base was integrated, and the build/tests still pass. If conflicts were left or tests fail, **fix them** on the feature branch (never push a protected branch directly) and re-verify.
21
- - Report PASS/PARTIAL/FAIL with evidence. Merge mode must NOT move the task to done.
54
+ ## 3. Main deploy (optional, policy-aware)
22
55
 
23
- ## 4. Main deploy (optional, policy-aware)
24
- - If the user wants main updated, `mcp__xevy__deploy_main` deploys the project's REMOTE default branch. NEVER push protected branches (master/main/develop/staging) to make main reflect local work — land via PR first; warn that main shows the remote/PR-merged state. Report the main URL.
56
+ If the user wants main updated, `mcp__xevy__deploy_main` deploys the project's remote default branch. Never push protected branches (`master`, `main`, `develop`, `staging`) to make main reflect local work; land changes through a PR first and warn that main shows the remote/PR-merged state. In the local workflow, an unpushed merge will not appear in main. Report the main URL.
@@ -1,21 +1,55 @@
1
1
  ---
2
2
  name: move-to-qa
3
- description: Move a task to QA in the cloud — run the Xevy server agent's 'move-to-qa' action (creates/updates QA Notes, sets status for_qa), then review the QA Notes for completeness. Use /xevy:move-to-qa-here to do it locally.
4
- argument-hint: "[task]"
3
+ description: Move a task to QA locally in the current coding-agent session by default — write or update non-technical QA Notes, set for_qa, and review. Pass --cloud to delegate the QA handoff to the Xevy server agent, then review and correct its result.
4
+ argument-hint: "[task] [--cloud]"
5
5
  disable-model-invocation: true
6
- allowed-tools: "Read Bash mcp__xevy__find_task mcp__xevy__list_task_notes mcp__xevy__get_task_note mcp__xevy__start_ai_action mcp__xevy__get_ai_execution mcp__xevy__list_ai_executions"
6
+ allowed-tools: "Read Grep Bash mcp__xevy__find_task mcp__xevy__list_task_notes mcp__xevy__get_task_note mcp__xevy__create_task_note mcp__xevy__update_task_note mcp__xevy__update_task_status mcp__xevy__start_ai_action mcp__xevy__get_ai_execution mcp__xevy__list_ai_executions"
7
7
  ---
8
8
 
9
- # /xevy:move-to-qa — move to QA in the cloud (then review)
9
+ # /xevy:move-to-qa — move to QA locally or in the cloud
10
10
 
11
- Cloud is the default engine: the server agent creates/updates QA Notes and sets status to `for_qa`. **You then review the notes.** To do it locally, use `/xevy:move-to-qa-here`.
11
+ Local QA handoff is the default. Pass the exact standalone `--cloud` flag to delegate it to the Xevy server agent.
12
+
13
+ ## 0. Choose the engine
14
+
15
+ - Parse `$ARGUMENTS` for the exact standalone `--cloud` token and remove that token before resolving the task. Do not treat similar text such as `--cloudy` as the flag.
16
+ - Without `--cloud`, follow the **Local workflow** and do not call `start_ai_action`.
17
+ - With `--cloud`, follow the **Cloud workflow**.
12
18
 
13
19
  ## 1. Resolve
14
- Resolve the task (`$ARGUMENTS` / context).
15
20
 
16
- ## 2. Run the cloud action
17
- - `mcp__xevy__start_ai_action({ taskId, action: "move-to-qa", stream: true })` — **always pass `stream: true`**. The call blocks and streams live per-step progress; report it as it arrives. Do **NOT** use fire-and-forget or `sleep`/manual poll loops — streaming is the default and is reliable. Only if this streamed call returns *before* a terminal status (genuine disconnect — the run keeps going server-side) resume with `get_ai_execution`. On failure surface output.
21
+ Resolve the remaining task argument or the in-context task. Read the implementation and what changed.
22
+
23
+ ## 2A. Local workflow (default)
24
+
25
+ ### Write QA Notes
26
+
27
+ Create or update a note titled `QA Re-Testing Guide` with `create_task_note` or `update_task_note`. Keep it non-technical and UI-verifiable, with these sections in order:
28
+
29
+ 1. Pre-Test Preconditions — deployment, context, and account readiness.
30
+ 2. Reproduction Steps — a step table with expected vs actual and pass/fail.
31
+ 3. Expected vs Actual Behaviour — plus an edge-case checklist.
32
+ 4. Validation Checks — functional, UI/UX, data/state, and integration.
33
+ 5. Screenshots/Logs/Evidence — what to capture and how.
34
+ 6. Final Verdict — Pass, Fail, or Partial plus follow-ups.
35
+
36
+ ### Set status and review
37
+
38
+ Set the task to `for_qa` with `update_task_status`; never move it to `done`. Re-read the notes and confirm a non-technical QA can follow every step in the UI and that expected results are concrete. Fix gaps before finishing. Report the task URL and a short summary.
39
+
40
+ ## 2B. Cloud workflow (`--cloud`)
41
+
42
+ ### Run the server action
43
+
44
+ - Call `mcp__xevy__start_ai_action({ taskId, action: "move-to-qa", stream: true })`; always pass `stream: true`. Report live progress as it arrives. Do not use fire-and-forget or sleep/manual polling loops.
45
+ - Only if the streamed call returns before a terminal status because of a genuine disconnect, resume with `mcp__xevy__get_ai_execution` (use `list_ai_executions` if needed).
46
+ - On failure, surface the output and offer to retry or rerun `/xevy:move-to-qa` without `--cloud`.
47
+
48
+ ### Review and correct
49
+
50
+ - Read the QA Notes with `list_task_notes` then `get_task_note`.
51
+ - Verify they are non-technical and UI-verifiable, covering preconditions, step-by-step reproduction with expected versus actual results, validation checks, evidence to capture, and a final verdict.
52
+ - If the notes are thin or too technical, repair them with `update_task_note` using the same structure as the Local workflow.
53
+ - Confirm task status is `for_qa`, never `done`.
18
54
 
19
- ## 3. Review & correct (MANDATORY)
20
- - Read the QA Notes (`list_task_notes` → `get_task_note`). Verify they are non-technical and UI-verifiable, with: pre-test preconditions, step-by-step reproduction (expected vs actual), validation checks, evidence to capture, and a final verdict section.
21
- - If thin or technical, **fix** them (rewrite via the local variant or `update_task_note`). Confirm status is `for_qa` (not `done`). Report what you corrected and the task URL.
55
+ Report what you corrected and the task URL.
@@ -1,25 +1,64 @@
1
1
  ---
2
2
  name: plan
3
- description: Plan a task in the cloud — run the Xevy server agent's 'plan' action (writes plan spec + ordered subtasks), then review and correct the plan. Use /xevy:plan-here to plan locally.
4
- argument-hint: "[task]"
3
+ description: Plan a task locally in the current coding-agent session by default — inspect the codebase, write the plan spec and ordered subtasks, then review them. Pass --cloud to delegate planning to the Xevy server agent, then review and correct its result.
4
+ argument-hint: "[task] [--cloud]"
5
5
  disable-model-invocation: true
6
- allowed-tools: "Read Grep Bash mcp__xevy__find_task mcp__xevy__list_specs mcp__xevy__get_spec mcp__xevy__list_subtasks mcp__xevy__start_ai_action mcp__xevy__get_ai_execution mcp__xevy__list_ai_executions"
6
+ allowed-tools: "Read Grep Bash Agent mcp__xevy__find_task mcp__xevy__create_spec mcp__xevy__update_spec mcp__xevy__list_specs mcp__xevy__get_spec mcp__xevy__create_subtask mcp__xevy__update_subtask mcp__xevy__list_subtasks mcp__xevy__list_task_decisions mcp__xevy__create_decision mcp__xevy__answer_decision mcp__xevy__get_process_owners mcp__xevy__update_task_status mcp__xevy__start_ai_action mcp__xevy__get_ai_execution mcp__xevy__list_ai_executions"
7
7
  ---
8
8
 
9
- # /xevy:plan — plan in the cloud (then review)
9
+ # /xevy:plan — plan locally or in the cloud
10
10
 
11
- Cloud is the default engine: the server agent writes the plan spec + ordered subtask checklist; **you then review and correct it**. To plan locally, use `/xevy:plan-here`.
11
+ Local planning is the default. Pass the exact standalone `--cloud` flag to delegate planning to the Xevy server agent.
12
+
13
+ ## 0. Choose the engine
14
+
15
+ - Parse `$ARGUMENTS` for the exact standalone `--cloud` token and remove that token before resolving the task. Do not treat similar text such as `--cloudy` as the flag.
16
+ - Without `--cloud`, follow the **Local workflow** and do not call `start_ai_action`.
17
+ - With `--cloud`, follow the **Cloud workflow**.
12
18
 
13
19
  ## 1. Resolve the task
14
- Resolve from `$ARGUMENTS` or context. The task should be analyzed first (a `## Analysis` section). If not, suggest `/xevy:analyze` and stop.
15
20
 
16
- ## 2. Run the cloud action
17
- - `mcp__xevy__start_ai_action({ taskId, action: "plan", stream: true })` — **always pass `stream: true`**. The call blocks and streams live per-step progress; report it as it arrives. Do **NOT** use fire-and-forget or `sleep`/manual poll loops — streaming is the default and is reliable. Only if this streamed call returns *before* a terminal status (genuine disconnect — the run keeps going server-side) resume with `get_ai_execution`. On failure, surface the output and offer retry or `/xevy:plan-here`.
21
+ Resolve the remaining task argument or the in-context task. It should already have a `## Analysis` section. If it does not, suggest `/xevy:analyze` and stop.
22
+
23
+ ## 2A. Local workflow (default)
24
+
25
+ ### Decisions gate and recon
26
+
27
+ Call `mcp__xevy__list_task_decisions`. If any decision is **open**, resolve it first: present it through the host's user-question mechanism, record the answer with `mcp__xevy__answer_decision`, and reflect it in the plan. Open decisions block AI work, so never guess or bypass them.
28
+
29
+ When the host supports subagents, dispatch a **scout** for codebase recon covering relevant files, callers/callees, similar patterns, and baseline health. Otherwise perform the same recon in this session.
30
+
31
+ ### Write the plan
32
+
33
+ - Create a plan spec with `mcp__xevy__create_spec` using kind `plan`. Include step-by-step changes with file paths and line ranges plus a trace matrix: requirement → files → strategy → test.
34
+ - Create ordered subtasks with `mcp__xevy__create_subtask`. Group work into reviewable end-to-end pieces; keep frontend and backend work for one capability together.
35
+
36
+ ### Plan-review
37
+
38
+ When the host supports subagents, dispatch a **plan-reviewer** to cross-check every matrix item against requirements, find orphans and gaps, verify cross-flow risks and “must NOT” constraints, and confirm tests hit the exact branches. Otherwise perform a separate self-review pass. Fold the findings into the spec and subtasks.
39
+
40
+ If planning surfaces a genuine question a human must resolve, record it with `mcp__xevy__create_decision` using preset choices and explanations instead of guessing.
41
+
42
+ ### Final check
43
+
44
+ Confirm the final plan is complete and feasible against the actual code and fix every remaining gap. Call `mcp__xevy__list_task_decisions` again and surface any decision that remains open. Do not change task status as a side effect of local planning. Draft is preparation-only; the user explicitly submits it to Ready. When planning is configured Refine work for a Ready task, completion moves it to Planned through the server-owned Process Owner flow. Do not start execution.
45
+
46
+ Report a PASS/PARTIAL verdict, the matrix summary, open decisions, resulting status, and task URL.
47
+
48
+ ## 2B. Cloud workflow (`--cloud`)
49
+
50
+ ### Run the server action
51
+
52
+ - Call `mcp__xevy__start_ai_action({ taskId, action: "plan", stream: true })`; always pass `stream: true`. Report live progress as it arrives. Do not use fire-and-forget or sleep/manual polling loops.
53
+ - Only if the streamed call returns before a terminal status because of a genuine disconnect, resume with `mcp__xevy__get_ai_execution` (use `list_ai_executions` if needed).
54
+ - On failure, surface the output and offer to retry or rerun `/xevy:plan` without `--cloud`.
55
+
56
+ ### Review and correct
18
57
 
19
- ## 3. Review & correct (MANDATORY — act as plan-reviewer)
20
58
  - Read the produced plan spec (`list_specs` → `get_spec`) and subtasks (`list_subtasks`).
21
- - Build a quick trace matrix: every requirement from the task/Analysis → a subtask/step that covers it. Flag orphans (requirements with no step) and gaps (steps with no requirement). Inspect the code with Read/Grep to confirm the plan is feasible and references real files.
22
- - Check cross-flow risks (guards, context rehydration, effects, async side effects) are addressed, and that any "must NOT" constraints have explicit verification.
23
- - **Fix** gaps: edit the spec / add or reorder subtasks via MCP. Re-review until the matrix has no orphans.
24
- - Do **not** change the task status or start execution yourself. The server applies Process Owner automation when the run succeeds: AI Agent-owned stages advance automatically; human-owned stages wait for the user.
25
- - Report a PASS/PARTIAL verdict, the gaps you closed, the resulting task status, and the task URL.
59
+ - Build a trace matrix from every task/Analysis requirement to a subtask or plan step. Flag orphaned requirements and unjustified steps. Inspect the code with Read/Grep to confirm referenced files and approaches are real and feasible.
60
+ - Check cross-flow risks such as guards, context rehydration, effects, and async side effects. Every “must NOT” constraint needs explicit verification.
61
+ - Fix gaps by editing the spec or adding/reordering subtasks through MCP. Re-review until the matrix has no orphans.
62
+ - Do not change task status or start execution yourself. The server applies Process Owner automation after a successful run.
63
+
64
+ Report a PASS/PARTIAL verdict, gaps closed, resulting task status, and task URL.