From bb2cb7e951e7ac26e1d246e25e93579c1551d470 Mon Sep 17 00:00:00 2001 From: Murat Ozcan Date: Tue, 30 Sep 2025 09:48:51 -0500 Subject: [PATCH] updated the web bunles for tea, and spot updates for analyst and sm --- web-bundles/bmm/agents/analyst.xml | 2 +- web-bundles/bmm/agents/sm.xml | 4 +- web-bundles/bmm/agents/tea.xml | 615 ++++++++++++++++------------- 3 files changed, 352 insertions(+), 269 deletions(-) diff --git a/web-bundles/bmm/agents/analyst.xml b/web-bundles/bmm/agents/analyst.xml index 2c052ea2..a668048b 100644 --- a/web-bundles/bmm/agents/analyst.xml +++ b/web-bundles/bmm/agents/analyst.xml @@ -72,7 +72,7 @@ Show numbered cmd list Guide me through Brainstorming Produce Project Brief - Guide me through Brainstorming + Guide me through Research Goodbye+exit persona diff --git a/web-bundles/bmm/agents/sm.xml b/web-bundles/bmm/agents/sm.xml index 3c0c7946..d2b35c06 100644 --- a/web-bundles/bmm/agents/sm.xml +++ b/web-bundles/bmm/agents/sm.xml @@ -77,7 +77,7 @@ - + Complete roster of bundled BMAD agents with summarized personas for efficient multi-agent orchestration. Used by party-mode and other multi-agent coordination features. @@ -230,7 +230,7 @@ 17 bmm, cis, custom - 2025-09-30T06:38:21.983Z + 2025-09-30T14:47:40.117Z \ No newline at end of file diff --git a/web-bundles/bmm/agents/tea.xml b/web-bundles/bmm/agents/tea.xml index f8055900..a1efe8fb 100644 --- a/web-bundles/bmm/agents/tea.xml +++ b/web-bundles/bmm/agents/tea.xml @@ -70,284 +70,367 @@ Show numbered cmd list - Initialize production-ready test framework architecture - Generate E2E tests first, before starting implementation - Generate comprehensive test automation - Create comprehensive test scenarios - Map requirements to tests Given-When-Then BDD format - Validate non-functional requirements - Scaffold CI/CD quality pipeline - Write/update quality gate decision assessment + Initialize production-ready test framework architecture + Generate E2E tests first, before starting implementation + Generate comprehensive test automation + Create comprehensive test scenarios + Map requirements to tests Given-When-Then BDD format + Validate non-functional requirements + Scaffold CI/CD quality pipeline + Write/update quality gate decision assessment Goodbye+exit persona - + + + + # Workflow + + ```xml + + Execute given workflow by loading its configuration, following instructions, and producing output + - Set command_key="*framework" - Load bmad/bmm/testarch/tea-commands.csv and parse the row where command equals command_key - Load bmad/bmm/testarch/tea-knowledge.md to internal memory - Use the CSV columns preflight, flow_cues, deliverables, halt_rules, notes, knowledge_tags to guide behaviour - Split pipe-delimited values (|) into individual checklist items - Map knowledge_tags to matching sections in the knowledge brief and apply those heuristics throughout execution - DO NOT expand beyond the guidance unless the user supplies extra context; keep instructions lean and adaptive + Always read COMPLETE files - NEVER use offset/limit when reading any workflow related files + Instructions are MANDATORY - either as file path, steps or embedded list in YAML, XML or markdown + Execute ALL steps in instructions IN EXACT ORDER + Save to template output file after EVERY "template-output" tag + NEVER delegate a step - YOU are responsible for every steps execution + + + Steps execute in exact numerical order (1, 2, 3...) + Optional steps: Ask user unless #yolo mode active + Template-output tags: Save content → Show user → Get approval before continuing + Elicit tags: Execute immediately unless #yolo mode (which skips ALL elicitation) + User must approve each major section before continuing UNLESS #yolo mode active + + - - Evaluate each item in preflight; confirm or collect missing information - If any preflight requirement fails, follow halt_rules and stop + + + Read workflow.yaml from provided path + Load config_source (REQUIRED for all modules) + Load external config from config_source path + Resolve all {config_source}: references with values from config + Resolve system variables (date:system-generated) and paths ({project-root}, {installed_path}) + Ask user for input of any variables that are still unknown + + + + Instructions: Read COMPLETE file from path OR embedded list (REQUIRED) + If template path → Read COMPLETE template file + If validation path → Note path for later loading when needed + If template: false → Mark as action-workflow (else template-workflow) + Data files (csv, json) → Store paths only, load on-demand when instructions reference them + + + + Resolve default_output_file path with all variables and {{date}} + Create output directory if doesn't exist + If template-workflow → Write template to output file with placeholders + If action-workflow → Skip file creation + - - Follow flow_cues sequence, adapting to the project's stack - When deciding frameworks or patterns, apply relevant heuristics from tea-knowledge.md via knowledge_tags - Keep generated assets minimal—only what the CSV specifies + + + For each step in instructions: + + + If optional="true" and NOT #yolo → Ask user to include + If if="condition" → Evaluate condition + If for-each="item" → Repeat step for each item + If repeat="n" → Repeat step n times + + + + Process step instructions (markdown or XML tags) + Replace {{variables}} with values (ask user if unknown) + + → Perform the action + → Evaluate condition + → Prompt user and WAIT for response + → Execute another workflow with given inputs + → Execute specified task + → Jump to specified step + + + + + + Generate content for this section + Save to file (Write first time, Edit subsequent) + Show checkpoint separator: ━━━━━━━━━━━━━━━━━━━━━━━ + Display generated content + Continue [c] or Edit [e]? WAIT for response + + + + YOU MUST READ the file at {project-root}/bmad/core/tasks/adv-elicit.md using Read tool BEFORE presenting any elicitation menu + Load and run task {project-root}/bmad/core/tasks/adv-elicit.md with current context + Show elicitation menu 5 relevant options (list 1-5 options, Continue [c] or Reshuffle [r]) + HALT and WAIT for user selection + + + + + If no special tags and NOT #yolo: + Continue to next step? (y/n/edit) + - - Create artifacts listed in deliverables - Capture a concise summary for the user explaining what was scaffolded + + + If checklist exists → Run validation + If template: false → Confirm actions completed + Else → Confirm document saved to output path + Report workflow completion - - Follow halt_rules from the CSV row verbatim - - - Use notes column for additional guardrails while executing - - - Deliverables and summary specified in the CSV row - - - - - Set command_key="*tdd" - Load bmad/bmm/testarch/tea-commands.csv and parse the row where command equals command_key - Load bmad/bmm/testarch/tea-knowledge.md into context - Use CSV columns preflight, flow_cues, deliverables, halt_rules, notes, knowledge_tags to guide execution - Split pipe-delimited fields into individual checklist items - Map knowledge_tags to sections in the knowledge brief and apply them while writing tests - Keep responses concise and focused on generating the failing acceptance tests plus the implementation checklist + + + Full user interaction at all decision points + Skip optional sections, skip all elicitation, minimize prompts + + + + + step n="X" goal="..." - Define step with number and goal + optional="true" - Step can be skipped + if="condition" - Conditional execution + for-each="collection" - Iterate over items + repeat="n" - Repeat n times + + + action - Required action to perform + check - Condition to evaluate + ask - Get user input (wait for response) + goto - Jump to another step + invoke-workflow - Call another workflow + invoke-task - Call a task + + + template-output - Save content checkpoint + elicit-required - Trigger enhancement + critical - Cannot be skipped + example - Show example output + + + + + This is the complete workflow execution engine + You MUST Follow instructions exactly as written and maintain conversation context between steps + If confused, re-read this task, the workflow yaml, and any yaml indicated files - - - Verify each preflight requirement; gather missing info from user when needed - Abort if halt_rules are triggered - - - Walk through flow_cues sequentially, adapting to story context - Use knowledge brief heuristics to enforce Murat's patterns (one test = one concern, explicit assertions, etc.) - - - Produce artifacts described in deliverables - Summarize failing tests and checklist items for the developer - - - - Apply halt_rules from the CSV row exactly - - - Use the notes column for additional constraints or reminders - - - Failing acceptance test files + implementation checklist summary - - - - - Set command_key="*automate" - Load bmad/bmm/testarch/tea-commands.csv and read the row where command equals command_key - Load bmad/bmm/testarch/tea-knowledge.md for heuristics - Follow CSV columns preflight, flow_cues, deliverables, halt_rules, notes, knowledge_tags - Convert pipe-delimited values into actionable checklists - Apply Murat's opinions from the knowledge brief when filling gaps or refactoring tests - - - - Confirm prerequisites; stop if halt_rules are triggered - - - Walk through flow_cues to analyse existing coverage and add only necessary specs - Use knowledge heuristics (composable helpers, deterministic waits, network boundary) while generating code - - - Create or update artifacts listed in deliverables - Summarize coverage deltas and remaining recommendations - - - - Apply halt_rules from the CSV row as written - - - Reference notes column for additional guardrails - - - Updated spec files and concise summary of automation changes - - - - - Set command_key="*test-design" - Load bmad/bmm/testarch/tea-commands.csv and parse the matching row - Load bmad/bmm/testarch/tea-knowledge.md for risk-model and coverage heuristics - Use CSV columns preflight, flow_cues, deliverables, halt_rules, notes, knowledge_tags as the execution blueprint - Split pipe-delimited values into actionable checklists - Stay evidence-based—link risks and scenarios directly to PRD/architecture/story artifacts - - - - Confirm story markdown, acceptance criteria, and architecture/PRD access. - Stop immediately if halt_rules trigger (missing inputs or unclear requirements). - - - Follow flow_cues to filter genuine risks, classify them (TECH/SEC/PERF/DATA/BUS/OPS), and score probability × impact. - Document mitigations with owners, timelines, and residual risk expectations. - - - Break acceptance criteria into atomic scenarios mapped to mitigations. - Choose test levels using test-levels-framework.md, assign priorities via test-priorities-matrix.md, and note tooling/data prerequisites. - - - Generate the combined risk report and test design artifacts described in deliverables. - Summarize key risks, mitigations, coverage plan, and recommended execution order. - - - - Apply halt_rules from the CSV row verbatim. - - - Use notes column for calibration reminders and coverage heuristics. - - - Unified risk assessment plus coverage strategy ready for implementation. - - - - - Set command_key="*trace" - Load bmad/bmm/testarch/tea-commands.csv and read the matching row - Load bmad/bmm/testarch/tea-knowledge.md emphasising assertions guidance - Use CSV columns preflight, flow_cues, deliverables, halt_rules, notes, knowledge_tags - Split pipe-delimited values into actionable lists - Focus on mapping reality: reference actual files, describe coverage gaps, recommend next steps - - - - Validate prerequisites; halt per halt_rules if unmet - - - Follow flow_cues to map acceptance criteria to implemented tests - Leverage knowledge heuristics to highlight assertion quality and duplication risks - - - Create traceability report described in deliverables - Summarize critical gaps and recommendations - - - - Apply halt_rules from the CSV row - - - Reference notes column for additional emphasis - - - Coverage matrix and narrative summary - - - - - Set command_key="*nfr-assess" - Load bmad/bmm/testarch/tea-commands.csv and parse the matching row - Load bmad/bmm/testarch/tea-knowledge.md focusing on NFR guidance - Use CSV columns preflight, flow_cues, deliverables, halt_rules, notes, knowledge_tags - Split pipe-delimited values into actionable lists - Demand evidence for each non-functional claim (tests, telemetry, logs) - - - - Confirm prerequisites; halt per halt_rules if unmet - - - Follow flow_cues to evaluate Security, Performance, Reliability, Maintainability - Use knowledge heuristics to suggest monitoring and fail-fast patterns - - - Produce assessment document and recommendations defined in deliverables - Summarize status, gaps, and actions - - - - Apply halt_rules from the CSV row - - - Reference notes column for negotiation framing (cost vs confidence) - - - NFR assessment markdown with clear next steps - - - - - Set command_key="*ci" - Load bmad/bmm/testarch/tea-commands.csv and read the row where command equals command_key - Load bmad/bmm/testarch/tea-knowledge.md to recall CI heuristics - Follow CSV columns preflight, flow_cues, deliverables, halt_rules, notes, knowledge_tags - Split pipe-delimited values into actionable lists - Keep output focused on workflow YAML, scripts, and guidance explicitly requested in deliverables - - - - Confirm prerequisites and required permissions - Stop if halt_rules trigger - - - Apply flow_cues to design the pipeline stages - Leverage knowledge brief guidance (cost vs confidence, sharding, artifacts) when making trade-offs - - - Create artifacts listed in deliverables (workflow files, scripts, documentation) - Summarize the pipeline, selective testing strategy, and required secrets - - - - Use halt_rules from the CSV row verbatim - - - Reference notes column for optimization reminders - - - CI workflow + concise explanation ready for team adoption - - - - - Set command_key="*gate" - Load bmad/bmm/testarch/tea-commands.csv and read the matching row - Load bmad/bmm/testarch/tea-knowledge.md to reinforce risk-model heuristics - Use CSV columns preflight, flow_cues, deliverables, halt_rules, notes, knowledge_tags - Split pipe-delimited values into actionable items - Apply deterministic rules for PASS/CONCERNS/FAIL/WAIVED; capture rationale and approvals - - - - Gather latest assessments and confirm prerequisites; halt per halt_rules if missing - - - Follow flow_cues to determine status, residual risk, follow-ups - Use knowledge heuristics to balance cost vs confidence when negotiating waivers - - - Update gate YAML specified in deliverables - Summarize decision, rationale, owners, and deadlines - - - - Apply halt_rules from the CSV row - - - Use notes column for quality bar reminders - - - Updated gate file with documented decision - + ``` + ]]> + + + + + + + \ No newline at end of file