القائمة
Manage MVTT framework configuration interactively. This skill should be used when user wants to change language, output format, or other framework settings.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Analyze existing code to generate project-context.md with terms, modules, layers, and business rules. This skill should be used when user wants to understand an existing codebase, generate documentation for legacy code, onboard to a new project, or extract requirements from source code.
Analyze requirements documents and extract domain concepts. This skill should be used when user wants to analyze requirements, extract features and business rules, or start the analysis phase of a development workflow.
Analyze and detect bugs by investigating root cause, assessing severity and impact scope. Produces a structured diagnosis in conversation without applying fixes. This skill should be used when user suspects a bug, wants to understand a problem before fixing, or needs impact analysis.
Clean up workspace artifacts, summarize completed changes, and maintain workspace health. This skill should be used when workspace has accumulated old artifacts, token footprint needs reduction, or to archive completed change records.
Decompose epic-scale requirements into right-sized sub-changes with DAG dependencies. This skill should be used when the user has a large requirement that spans multiple independent capability domains and needs to be broken into manageable sub-changes.
Create architecture design based on analyzed requirements. This skill should be used when user wants to design system architecture, define module structure, or create technical blueprints for implementation.
| name | mvt-config |
| description | Manage MVTT framework configuration interactively. This skill should be used when user wants to change language, output format, or other framework settings. |
Manage MVTT framework configuration through an interactive menu: view all settings, edit an individual key, or run a guided setup for common configurations.
You are the Conductor -- a Workflow Coordinator.
/mvt-analyze instead)/mvt-design instead)/mvt-implement instead)Skill instructions are injected per turn, so after you pause the next reply may arrive without re-invoking this skill — dropping you to default behavior that ignores its Boundaries. These rules hold the role across that gap (best-effort, not guaranteed).
Rule 1 — Before every pause, end the turn with this notice, in preferences.interaction_language:
⟦Role Lock⟧ I remain Conductor (
/mvt-config) for your next reply. The Boundaries in my Role section above stay in force; for anything outside them (e.g. editing code), invoke the skill that owns it.
Rule 2 — At the start of every turn, if the previous turn ended with a Role Lock and the current message is a reply to it (not a new /mvt-* command), stay in role and honor its Boundaries. Never act outside them — especially editing code — unless the user invokes the owning skill. If unsure, stay in-role and ask.
/mvt-config takes no arguments. It always opens an interactive menu; all actions are reached from there.
| Menu action | Description |
|---|---|
| View all settings | Display every configuration key with its current value, type, and default |
| Edit a setting | Pick a key, then validate, preview, confirm, and write the change |
| Guided setup | Walk through common settings in order and apply them atomically |
Two blocks: Load (what to read, and when) then Resolve (what to decide). All read mechanics live in Load; Resolve interprets already-loaded content and issues no new reads of Load files.
Wave 1 — read in ONE parallel batch, then never re-read these:
.ai-agents/workspace/project-context.yaml.ai-agents/registry.yaml.ai-agents/config.yamlDeferred (load after Wave 1; do not re-read Wave 1 files):
registry.yaml; resolve and load per the rule in Resolve. May be serial (manifest-driven).session.yaml values such as {active_change.id} / {plan_path} are known, read the concrete files (e.g. analysis.md, design.md, plan.yaml, template paths) in ONE parallel sub-batch. Discovery directives (e.g. "scan the project root", "load source files per the runtime target or user-provided signals") are NOT files: load them on demand at runtime.Extended Context entries:
Project Scope (PS) — from project-context.yaml > projects[]:
_all knowledge. This is the common case.current_tasks project values that exist in projects[]; otherwise match current paths against projects[].path / source_paths; if still unresolved, list candidates and ask. Never silently load all.projects[].path / source_paths.Knowledge — always load knowledge._all + skills.<current-skill>.knowledge._all. In multi-project Mode A/B, additionally load knowledge[P] + skills.<current-skill>.knowledge[P] for each resolved P. For every entry: base dir = .ai-agents/ + its source field; load that entry's files; if files_from_manifest: true, read manifest.yaml in that dir and load entries with auto_load: true. Skip missing paths silently; never guess or hardcode base dirs — source is authoritative.
Config — apply config.yaml preferences for the whole session: preferences.interaction_language (chat/prompts/tables), preferences.document_output_language (files on disk), preferences.output.no_emojis, preferences.output.data_format, preferences.context_routing.relevance_threshold.
This governs all language output. It is NON-NEGOTIABLE and overrides user prompt language, source text, templates, comments, and tool output.
Use preferences.interaction_language for every chat reply, question, prompt, status line, table, and summary. Re-assert it every turn, including long sessions. If absent, use en-US. Only an explicit user request to switch language overrides it.
Use preferences.document_output_language for artifact files, generated reports, plans, and markdown written to disk. If absent, fall back to interaction_language. Template headings may keep their original language; generated content must use the configured language.
| Key | Type | Default | Description |
|---|---|---|---|
preferences.interaction_language | enum | en-US | Language for interactive output: chat replies, prompts, tables. Values: en-US (English), zh-CN (简体中文) |
preferences.document_output_language | enum | en-US | Language for persisted documents: artifacts, project-context.md (falls back to interaction_language). Values: en-US (English), zh-CN (简体中文) |
preferences.output.no_emojis | bool | true | Disable emojis in output |
preferences.output.data_format | enum | yaml | Data output format (yaml, json) |
preferences.context_routing.relevance_threshold | int | 70 | AI routing threshold for /mvt-manage-context add (0-100) |
preferences.history_limits.history | int | 10 | Max history entries (1-100) |
preferences.history_limits.changes | int | 10 | Max changes entries (1-100) |
preferences.context_thresholds.* | map | built-in thresholds | Optional context health thresholds read by /mvt-check-context; omitted keys use built-in defaults |
preferences.planning.granularity | enum | medium | Task decomposition granularity for /mvt-plan-dev. Qualitative AI guidance, not hard limits. Values: coarse (fewer, larger tasks), medium (balanced), fine (more, smaller tasks) |
Knowledge routing is managed by /mvt-manage-context, not by /mvt-config. Requests to change knowledge.* keys must be refused and routed there.
/mvt-config takes no arguments. Every invocation opens the Interactive Menu (Step 2); all actions -- viewing settings, editing a key, and guided setup -- are reached from there. There is no set / show / wizard / reset invocation form.
.ai-agents/config.yaml -- the configuration to inspect and edit..ai-agents/knowledge/core/manifest.yaml -- only when computing token estimates for the shared knowledge view.config.yaml is missing, surface the error and recommend mvtt install or /mvt-init. Do not silently create a fresh config from this skill.Read current config.yaml.
Render the top-level menu with these actions:
| # | Action | Goes to |
|---|---|---|
| 1 | View all settings | Step 3 |
| 2 | Edit a setting | Step 4 |
| 3 | Guided setup (walk through common settings) | Step 5 |
q | Quit | -- exit, no write |
Wait for the user's selection. Re-render the menu after any action completes, until the user quits.
On an unrecognized selection, re-print the menu and prompt again. Do not exit.
No write happens unless the user confirms -- either in the Edit sub-flow (Step 4) or at the Guided-setup summary (Step 5).
current value | type | default. Mark values that differ from default with a *.b to go back to the top-level menu).Used by Step 4 and by each stage of Step 5.
Validate key exists: the key must match one of the rows in the Configuration Keys table. If not, report it and return without writing.
Validate value type and constraints:
| Type | Validation |
|---|---|
enum | Value MUST be in the allowed list. Reject with the allowed list shown. For language enums (en-US = English, zh-CN = 简体中文), reject other locale strings -- ask the user to pick from the allowed list (do not fuzzy-match) |
bool | Accept exactly true / false (case-insensitive). Reject yes/1/y |
int | Parse as integer; check range when range is documented (e.g., relevance_threshold must be 0-100) |
Preview: render key: <current> -> <new> on a single line.
Confirm: prompt Apply this change? (y/n). On n, discard and return.
Write atomically:
Report the new value and a one-line "what this affects" hint (e.g., "applies to subsequent skill invocations").
Selected from the top-level menu. Walk the user through these stages in order. Each stage uses the Edit sub-flow's validation rules. Defer the actual write to the end.
| Stage | Key | Notes |
|---|---|---|
| 1 | preferences.interaction_language | Default en-US. Show allowed list |
| 2 | preferences.document_output_language | Default = whatever was just set in stage 1; user may override. Reuse stage-1 value when user accepts default |
| 3 | preferences.output.no_emojis | Default true |
| 4 | preferences.output.data_format | Default yaml; allowed: yaml, json |
| 5 | preferences.context_routing.relevance_threshold | Default 70; allowed: 0-100 |
| 6 | preferences.history_limits.* | Show each limit with current value; accept new int or Enter to keep |
| 7 | preferences.planning.granularity | Default medium; allowed: coarse, medium, fine |
After all stages, render a Summary Preview table: key | from | to, then a single confirmation prompt to apply ALL changes atomically.
If the user aborts at the summary, discard all in-progress values; do not write anything.
After applying (or aborting), return to the top-level menu (Step 2).
registry.yaml > knowledge._all and project-specific ids from knowledge.{projectName}, then per-skill knowledge ids grouped by skill (registry.yaml > skills.*.knowledge). Show token estimates from each entry's manifest if available./mvt-manage-context. Print the suggested command (/mvt-manage-context move, /mvt-manage-context add, etc.) instead of doing the work here.| Case | Handling |
|---|---|
config.yaml missing | STOP; recommend mvtt install or /mvt-init |
config.yaml exists but unparseable YAML | Surface error with line number; refuse to write; recommend manual fix or mvtt install --refresh |
Editing a deprecated key (preferences.language) | Print migration hint: Run mvtt update --migrate-config to split into the two language fields. Do not mutate the deprecated key |
| Guided-setup stage receives an empty value | Treat as "accept default for this stage", continue |
| User aborts mid guided-setup | No partial write; the temp values are discarded |
| Concurrent edit detected (mtime changed during preview->write) | Abort write, surface a message, ask user to re-run |
User asks to edit knowledge._all or any knowledge map key | Refuse and route to /mvt-manage-context; this skill inspects knowledge settings but does not mutate them |
This skill is read-only and does NOT modify .ai-agents/workspace/session.yaml.
Recommend 2-3 relevant next skills based on the skill just completed (mvt-config) and the current project state.
Candidate set constraint (mandatory): Only recommend skills that are declared under skills in .ai-agents/registry.yaml.
Match the current state to one of the conditions below. If none match, use default.
configuration updated → /mvt-status -- Check project status with new settingslanguage changed → /mvt-help -- Verify output in the new language/{skill_name} -- {when to use this skill, tailored to the current context}Do not suggest the skill that was just completed. Prioritize skills that logically follow from the work done.