Merge 1a85069b75 into e550df2474

Revert "feat(skills): YAML-based agent customization with Python resolver (#2282 )" (#2283 )
This reverts commit bd1c0053d5.
2026-04-19 19:33:50 -03:00 · 2026-04-19 11:09:21 -05:00 · 2026-04-18 23:13:31 -05:00 · 2026-03-11 19:38:13 -03:00
3 changed files with 95 additions and 0 deletions
--- a/src/core/tasks/validate-workflow/SKILL.md
+++ b/src/core/tasks/validate-workflow/SKILL.md
@ -0,0 +1,6 @@
+---
+name: validate-workflow
+description: "Run a checklist against a document with thorough analysis and produce a validation report"
+---
+
+Follow the instructions in [workflow.md](workflow.md).
--- a/src/core/tasks/validate-workflow/bmad-skill-manifest.yaml
+++ b/src/core/tasks/validate-workflow/bmad-skill-manifest.yaml
@ -0,0 +1 @@
+type: skill
--- a/src/core/tasks/validate-workflow/workflow.md
+++ b/src/core/tasks/validate-workflow/workflow.md
@ -0,0 +1,88 @@
+# Validate Workflow Output
+
+**Goal:** Run a checklist against a document with thorough analysis and produce a validation report.
+
+**Inputs:**
+
+- **workflow** (required) — Workflow path containing `checklist.md`
+- **checklist** (optional) — Checklist to validate against (defaults to the workflow's `checklist.md`)
+- **document** (optional) — Document to validate (ask user if not specified)
+
+## STEPS
+
+### Step 1: Setup
+
+- If checklist not provided, load `checklist.md` from the workflow location
+- Try to fuzzy-match files similar to the input document name; if document not provided or unsure, ask user: "Which document should I validate?"
+- Load both the checklist and document
+
+### Step 2: Validate (CRITICAL)
+
+**For EVERY checklist item, WITHOUT SKIPPING ANY:**
+
+1. Read the requirement carefully
+2. Search the document for evidence along with any ancillary loaded documents or artifacts (quotes with line numbers)
+3. Analyze deeply — look for explicit AND implied coverage
+
+**Mark each item as:**
+
+- **PASS** `✓` — Requirement fully met (provide evidence)
+- **PARTIAL** `⚠` — Some coverage but incomplete (explain gaps)
+- **FAIL** `✗` — Not met or severely deficient (explain why)
+- **N/A** `➖` — Not applicable (explain reason)
+
+**DO NOT SKIP ANY SECTIONS OR ITEMS.**
+
+### Step 3: Generate Report
+
+Create `validation-report-{timestamp}.md` in the document's folder with the following format:
+
+```markdown
+# Validation Report
+
+**Document:** {document-path}
+**Checklist:** {checklist-path}
+**Date:** {timestamp}
+
+## Summary
+
+- Overall: X/Y passed (Z%)
+- Critical Issues: {count}
+
+## Section Results
+
+### {Section Name}
+
+Pass Rate: X/Y (Z%)
+
+[MARK] {Item description}
+Evidence: {Quote with line# or explanation}
+{If FAIL/PARTIAL: Impact: {why this matters}}
+
+## Failed Items
+
+{All ✗ items with recommendations}
+
+## Partial Items
+
+{All ⚠ items with what's missing}
+
+## Recommendations
+
+1. Must Fix: {critical failures}
+2. Should Improve: {important gaps}
+3. Consider: {minor improvements}
+```
+
+### Step 4: Summary for User
+
+- Present section-by-section summary
+- Highlight all critical issues
+- Provide path to saved report
+- **HALT** — do not continue unless user asks
+
+## HALT CONDITIONS
+
+- HALT after presenting summary in Step 4
+- HALT with error if no checklist is found and none is provided
+- HALT with error if no document is found and user does not specify one
Author	SHA1	Message	Date
Nikolas de Hor	f2c531039b	Merge `1a85069b75` into `e550df2474`	2026-04-19 19:33:50 -03:00
Brian	e550df2474	Revert "feat(skills): YAML-based agent customization with Python resolver (#2282 )" (#2283 ) This reverts commit `bd1c0053d5`.	2026-04-19 11:09:21 -05:00
Brian	bd1c0053d5	feat(skills): YAML-based agent customization with Python resolver (#2282 ) Three-layer customization (skill defaults → team → user) for BMad agents and any skill that opts in. Users edit `_bmad/custom/{skill-name}.yaml` (team, committed) or `{skill-name}.user.yaml` (personal, gitignored); customizations survive updates. Resolver is a Python script using PEP 723 inline metadata, invoked via `uv run` so deps auto-install into a cached isolated env on first call. This aligns with Anthropic's Agent Skills spec and BMB conventions, and keeps the dependency declared (scannable by pip-audit/Dependabot) rather than vendored. ## Design choices - Agent identity is hardcoded in SKILL.md (name, title, Overview prose) so skills can be invoked reliably by role or default name. Brand recognition is preserved; customization shapes behavior, not identity. - Luminary-anchored personas (e.g. "Channels Martin Fowler's pragmatism and Werner Vogels's cloud-scale realism") deliver ~55% token savings per agent while preserving distinctive voice beats. - Universal per-field merge rules with v6.1-compatible agent semantics: metadata shallow-merge, persona replace, critical_actions and memories append, menu merge-by-code, all else deep-merge. - Workflow customization shares the same surface — `bmad-product-brief` pilots `activation_steps_prepend`, `activation_steps_append`, and `skill_end` hooks that any workflow-style skill can adopt. ## Infrastructure - `_bmad/scripts/` houses shared Python scripts (resolver + future). - `_bmad/custom/` is provisioned empty with a seeded `.gitignore` for `*.user.yaml` on fresh installs. - Installer filters ensure `scripts/`, `custom/`, and sidecar-generated `memory/` directories are never treated as modules. - Dead v6.1 code cleaned up: `_config/agents/` no longer created, `metadata.capabilities` removed from schema and CSV manifest.	2026-04-18 23:13:31 -05:00
Nikolas de Hor	1a85069b75	fix: restore validate-workflow as native skill directory The validate-workflow task was accidentally deleted during the XML-to-native-skill refactor in #1864. The schema, handler, and test fixtures still reference it, creating broken invocations. Recreates the task as a native skill directory following the established pattern (SKILL.md + bmad-skill-manifest.yaml + workflow.md), with the original validation logic preserved. Fixes #1530	2026-03-11 19:38:13 -03:00