bmad-module-skill-forge 0.4.0 → 0.6.0

package/src/workflows/setup-forge/steps-c/step-03-auto-index.md

@@ -1,6 +1,6 @@
 ---
 name: 'step-03-auto-index'
-description: 'Verify and clean QMD collections against the forge-tier.yaml registry (Deep tier only)'
+description: 'Verify and clean QMD collections against the forge-tier.yaml registry (Deep tier only) and CCC index registry hygiene (Forge+/Deep)'
 
 nextStepFile: './step-04-report.md'
 ---
@@ -11,7 +11,7 @@ nextStepFile: './step-04-report.md'
 
 If the detected tier is Deep, verify the health of existing QMD collections by cross-referencing them against the `qmd_collections` registry in `forge-tier.yaml`. Identify orphaned collections (in QMD but not in registry) and stale registry entries (in registry but collection missing from QMD). Prompt the user before removing orphaned collections.
 
-For Quick and Forge tiers, skip silently and proceed.
+For Quick and Forge tiers (without ccc), skip silently and proceed. For Forge+ tier, skip QMD hygiene but the step routes correctly to the next step.
 
 ## MANDATORY EXECUTION RULES (READ FIRST):
 
@@ -41,7 +41,7 @@ For Quick and Forge tiers, skip silently and proceed.
 - 🎯 Follow the MANDATORY SEQUENCE exactly
 - 💾 QMD hygiene only verifies and cleans — it does NOT index new content
 - 📖 Use {calculated_tier} from step-01 context
-- 🚫 FORBIDDEN to attempt hygiene for Quick or Forge tiers
+- 🚫 FORBIDDEN to attempt QMD hygiene for Quick, Forge, or Forge+ tiers (Forge+ has no qmd)
 
 ## CONTEXT BOUNDARIES:
 
@@ -59,7 +59,9 @@ For Quick and Forge tiers, skip silently and proceed.
 
 Read `{calculated_tier}` from context.
 
-**If tier is NOT Deep:** Proceed directly to section 6 (Auto-Proceed) — no output, no messaging.
+**If tier is Quick or Forge:** Proceed directly to section 6 (Auto-Proceed) — no output, no messaging.
+
+**If tier is Forge+:** Skip QMD hygiene (qmd is not available at Forge+). Proceed directly to section 5b (CCC Index Registry Hygiene) — no QMD output, no messaging.
 
 **If tier IS Deep:** Continue to section 2.
 
@@ -132,6 +134,26 @@ Update forge-tier.yaml with the cleaned registry.
 
 **If no stale entries:** Skip this section silently.
 
+### 5b. CCC Index Registry Hygiene (Forge+ and Deep with ccc)
+
+**IF `tools.ccc` is true in forge-tier.yaml (regardless of whether QMD hygiene ran):**
+
+Read the `ccc_index_registry` array from forge-tier.yaml.
+
+For each entry, verify the indexed path still exists on disk:
+
+**Healthy** — path exists: no action needed.
+
+**Stale** — path does not exist (source directory removed or moved):
+- Remove the stale entry from `ccc_index_registry`
+- Log: "Removed stale CCC index registry entry: {path} (path no longer exists)"
+
+Update forge-tier.yaml with the cleaned registry.
+
+Store `{ccc_registry_stale_cleaned: count}` in context for step-04 reporting.
+
+**IF `tools.ccc` is false:** Skip this section silently.
+
 ### 6. Store Hygiene Results and Auto-Proceed
 
 Store in context for step-04 reporting:
@@ -141,6 +163,7 @@ Store in context for step-04 reporting:
 {hygiene_orphaned_removed: count}
 {hygiene_orphaned_kept: count}
 {hygiene_stale_cleaned: count}
+{ccc_registry_stale_cleaned: count}
 ```
 
 "**Proceeding to forge status report...**"
@@ -170,7 +193,7 @@ ONLY WHEN the hygiene check has been performed (or skipped for non-Deep tiers) w
 - Orphaned collections flagged and user prompted before removal
 - Stale registry entries cleaned from forge-tier.yaml
 - Hygiene results stored for step-04 reporting
-- Quick/Forge tier: skipped silently with no negative messaging
+- Quick/Forge/Forge+ tier: skipped silently with no negative messaging
 - Workflow continues regardless of hygiene outcome
 - Auto-proceeded to step-04
 
@@ -178,7 +201,7 @@ ONLY WHEN the hygiene check has been performed (or skipped for non-Deep tiers) w
 
 - Creating new QMD collections (that's create-skill's responsibility)
 - Silently deleting collections without user prompt
-- Attempting QMD hygiene for Quick or Forge tiers
+- Attempting QMD hygiene for Quick, Forge, or Forge+ tiers
 - Displaying "skipped" or "missing" messages for non-Deep tiers
 - Halting the workflow due to QMD hygiene failure
 - Indexing project directories (old auto-index behavior — removed)

package/src/workflows/setup-forge/steps-c/step-04-report.md

@@ -43,7 +43,8 @@ Display the forge status report with positive capability framing, report tier ch
 
 - Available: {detected_tools}, {calculated_tier}, {previous_tier}, {tier_override} from step-01
 - Available: tool version strings from step-01
-- Available: {hygiene_result}, {hygiene_healthy}, {hygiene_orphaned_removed}, {hygiene_orphaned_kept}, {hygiene_stale_cleaned} from step-03
+- Available: {hygiene_result}, {hygiene_healthy}, {hygiene_orphaned_removed}, {hygiene_orphaned_kept}, {hygiene_stale_cleaned}, {ccc_registry_stale_cleaned} from step-03
+- Available: {ccc_index_result} from step-01b (values: "fresh", "created", "failed", "none")
 - Focus: report display only — no file modifications
 - Dependencies: steps 01-03 must have completed
 
@@ -75,13 +76,24 @@ Load and read {tierRulesData} for the tier capability descriptions and re-run me
   {hygiene_healthy} collection(s) healthy
   {if hygiene_orphaned_removed > 0: {hygiene_orphaned_removed} orphaned collection(s) removed}
   {if hygiene_orphaned_kept > 0: {hygiene_orphaned_kept} orphaned collection(s) kept}
-  {if hygiene_stale_cleaned > 0: {hygiene_stale_cleaned} stale registry entry/entries cleaned}
+  {if hygiene_stale_cleaned > 0: {hygiene_stale_cleaned} stale QMD registry entry/entries cleaned}
+  {end if}
+
+  {if ccc_registry_stale_cleaned > 0:}
+  CCC Registry: {ccc_registry_stale_cleaned} stale entry/entries cleaned
   {end if}
 
   {if hygiene_result is "completed" and hygiene_healthy is 0:}
   QMD Registry: empty — collections are created automatically when you run [CS] Create Skill.
   {end if}
 
+  {if tools.ccc is true:}
+  CCC Index:
+  {if ccc_index_result is "fresh": up to date — semantic discovery ready}
+  {if ccc_index_result is "created": indexed this run — semantic discovery ready}
+  {if ccc_index_result is "failed": indexing failed — semantic discovery unavailable this session}
+  {end if}
+
 {if tier_override is active:}
   Note: Tier override active (set in preferences.yaml)
 

package/src/workflows/setup-forge/validation-report.md

@@ -403,7 +403,7 @@ No subprocess optimization needed. The workflow is appropriately simple and sequ
 |-------------|------------|---------|
 | Initialize forge environment | Yes — all 4 steps address this | High |
 | Detect tools (ast-grep, gh, qmd) | Yes — step-01 verifies all 3 | High |
-| Set tier (Quick/Forge/Deep) | Yes — step-01 calculates, step-02 writes | High |
+| Set tier (Quick/Forge/Forge+/Deep) | Yes — step-01 calculates, step-02 writes | High |
 | Auto-index project | Yes — step-03 (Deep tier only) | High |
 
 #### Classification Attributes

package/src/workflows/setup-forge/workflow-plan-setup-forge.md

@@ -32,7 +32,7 @@ Initialize forge environment, detect tools, set tier, auto-index project
 ### Original Steps (Complete List)
 
 **Step 1:** detect-tools - Check for gh, ast-grep, QMD availability
-**Step 2:** determine-tier - Set Quick/Forge/Deep based on tools found
+**Step 2:** determine-tier - Set Quick/Forge/Forge+/Deep based on tools found
 **Step 3:** create-config - Generate forge-config.yaml with tier and tool flags
 **Step 4:** auto-index - Index current project as QMD collection (Deep only)
 **Step 5:** report - Display forge status, tier, and capabilities
@@ -65,7 +65,7 @@ Initialize forge environment, detect tools, set tier, auto-index project
 
 **What works well in original:**
 - Clear 5-step decomposition with logical progression
-- Well-defined progressive tier system (Quick/Forge/Deep)
+- Well-defined progressive tier system (Quick/Forge/Forge+/Deep)
 - Three distinct output artifacts with clear purposes
 - Correctly identified as foundation workflow all others depend on
 
@@ -104,9 +104,9 @@ Initialize forge environment, detect tools, set tier, auto-index project
 
 **Structure Implications:**
 - Simple `steps-c/` folder only, no edit/validate modes
-- No `step-01b-continue.md` needed
+- step-01b added for CCC index verification (Forge+ integration)
 - No document template — output is config files written directly
-- Standard init step without continuation logic
+- Standard init step with step-01b bridge to config writing
 
 ---
 
@@ -179,7 +179,7 @@ Initialize forge environment, detect tools, set tier, auto-index project
 - Frequency: Single execution per run (idempotent, safe to re-run)
 
 **Success Criteria:**
-- All 3 tools (ast-grep, gh, qmd) verified via version/status commands, results accurately recorded
+- All 4 tools (ast-grep, gh, qmd, ccc) verified via version/status commands, results accurately recorded
 - Correct tier assigned from tool availability (or tier_override respected if set)
 - forge-tier.yaml written with tools, tier, and tier_detected_at timestamp
 - preferences.yaml exists with defaults (created on first run, preserved on re-run)
@@ -233,6 +233,7 @@ setup-forge/
 │   └── tier-rules.md             # Tier calculation rules + capability descriptions
 └── steps-c/
     ├── step-01-detect-and-tier.md
+    ├── step-01b-ccc-index.md
     ├── step-02-write-config.md
     ├── step-03-auto-index.md
     └── step-04-report.md
@@ -244,9 +245,10 @@ No templates/ directory (non-document workflow).
 
 | Step | File | Type | Menu | Goal |
 |------|------|------|------|------|
-| 01 | step-01-detect-and-tier.md | Init (Non-Continuable) | Auto-proceed | Verify 3 tools functional, check tier_override, calculate tier, read previous tier |
+| 01 | step-01-detect-and-tier.md | Init (Non-Continuable) | Auto-proceed | Verify 4 tools functional (ast-grep, gh, qmd, ccc), check tier_override, calculate tier, read previous tier |
+| 01b | step-01b-ccc-index.md | Middle (Simple + Conditional) | Auto-proceed | Verify/create CCC index for Forge+/Deep tiers when ccc available, skip silently otherwise |
 | 02 | step-02-write-config.md | Middle (Simple) | Auto-proceed | Write forge-tier.yaml, create preferences.yaml defaults if missing, ensure forge-data/ exists |
-| 03 | step-03-auto-index.md | Middle (Simple + Conditional) | Auto-proceed | QMD index project (Deep only), skip gracefully otherwise |
+| 03 | step-03-auto-index.md | Middle (Simple + Conditional) | Auto-proceed | QMD index project (Deep only) + CCC registry hygiene, skip gracefully otherwise |
 | 04 | step-04-report.md | Final Step | None | Display status with positive framing, handle --update-spec, report tier changes |
 
 ### Step Detail: step-01-detect-and-tier
@@ -384,8 +386,8 @@ step-01 ──→ step-02 ──→ step-03 ──→ step-04
 - Type: Init (Non-Continuable)
 - Input Discovery: No
 - Menu: Auto-proceed (Pattern 3)
-- Next Step: step-02-write-config.md
-- No step-01b needed (single-session)
+- Next Step: step-01b-ccc-index.md
+- step-01b handles CCC index verification before config writing
 
 **Supporting Files:**
 - data/tier-rules.md (created in foundation step)

package/src/workflows/setup-forge/workflow.md

@@ -7,7 +7,7 @@ installed_path: '{project-root}/_bmad/skf/workflows/skillforge/setup-forge'
 
 # Setup Forge
 
-**Goal:** Initialize the forge environment by detecting available tools, determining the capability tier (Quick/Forge/Deep), writing persistent configuration, and optionally indexing the project for deep search.
+**Goal:** Initialize the forge environment by detecting available tools, determining the capability tier (Quick/Forge/Forge+/Deep), writing persistent configuration, and optionally indexing the project for deep search.
 
 **Your Role:** You are a system executor performing environment resolution. This is a fully autonomous workflow — no user interaction is required during execution. Run each step in sequence, write configuration files, and report results at completion.
 

package/src/workflows/test-skill/data/scoring-rules.md

@@ -27,6 +27,10 @@ When running in naive mode (no coherence category):
 
 When neither skill-check nor tessl is available, redistribute the 10% external validation weight proportionally to the other active categories. When only one tool is available, use that tool's score as the external validation score.
 
+## tessl and Split-Body Interaction
+
+tessl evaluates SKILL.md body content only — it does not read `references/*.md` files. After split-body extraction, the tessl content score will drop significantly (e.g., 65% to 38%) because Tier 2 content is no longer inline. This is expected behavior and does not reflect actual content quality. When reporting scores for a split-body skill, note: "tessl content score reflects post-split inline content only. Use the pre-split tessl score as the content quality baseline."
+
 ## Tier-Dependent Scoring
 
 ### Quick Tier (no tools)
@@ -41,6 +45,11 @@ When neither skill-check nor tessl is available, redistribute the 10% external v
 - Type Coverage: AST-verified type completeness
 - Full scoring formula applied
 
+### Forge+ Tier (ast-grep + ccc)
+- Same scoring as Forge tier — ccc provides pre-ranking but does not change scoring weights
+- Improved extraction coverage (from ccc pre-discovery) may increase T1 count, but scoring formula is identical to Forge
+- Full scoring formula applied
+
 ### Deep Tier (ast-grep + gh + QMD)
 - All Forge tier checks plus:
 - Cross-repository reference verification
@@ -78,5 +87,10 @@ If no integration patterns exist, combined coherence equals reference validity.
 | High | Signature mismatch between source and SKILL.md |
 | Medium | Missing type or interface documentation |
 | Medium | Migration section present/absent mismatch with T2-future annotation data (Deep tier) |
+| Medium | Script/asset directory exists but no Scripts & Assets section in SKILL.md |
+| Medium | Scripts & Assets section references file not found in scripts/ or assets/ directory |
+| Low | Script/asset file present without provenance entry in provenance-map.json file_entries |
 | Low | Missing optional metadata or examples |
+| Low | Description trigger optimization recommended (third-person voice, negative triggers, or keyword coverage gaps) |
 | Info | Style suggestions, non-blocking observations |
+| Info | Discovery testing not performed — realistic prompt testing recommended before export |

package/src/workflows/test-skill/steps-c/step-01-init.md

@@ -112,7 +112,7 @@ Log each issue as a pre-check finding. Continue with testing — frontmatter iss
 Read `{sidecarFile}` to determine available analysis depth.
 
 **If forge-tier.yaml exists:**
-- Read `tier` value (Quick, Forge, or Deep)
+- Read `tier` value (Quick, Forge, Forge+, or Deep)
 - Read tool availability flags (ast_grep, gh_cli, qmd)
 
 **If forge-tier.yaml missing:**
@@ -124,7 +124,7 @@ Default to Quick tier and continue.
 
 ### 4b. Apply Tier Override (if set)
 
-Read `{sidecar_path}/preferences.yaml`. If `tier_override` is set and is a valid tier value (Quick, Forge, or Deep), update `detected_tier` to the override value for use in subsequent steps and output documents.
+Read `{sidecar_path}/preferences.yaml`. If `tier_override` is set and is a valid tier value (Quick, Forge, Forge+, or Deep), update `detected_tier` to the override value for use in subsequent steps and output documents.
 
 ### 5. Load Skill Metadata
 

package/src/workflows/test-skill/steps-c/step-03-coverage-check.md

@@ -85,6 +85,8 @@ Read SKILL.md and extract all documented items:
 
 Build the **documented inventory** — a list of everything the SKILL.md claims the source provides.
 
+**Split-body traversal:** If a `references/` directory exists alongside SKILL.md and SKILL.md's `## Full` headings are absent or stubs (not a stack skill's structural references), extend the documented inventory scan to include all `references/*.md` files. After split-body, Tier 2 content (Full API Reference, Full Type Definitions) lives in reference files — the inventory must reflect the full skill content regardless of where it resides.
+
 ### 2. Analyze Source Code (Tier-Dependent)
 
 Start from the package entry point (see 0b) and identify the public API surface. Then analyze those exports at the appropriate tier depth.
@@ -223,7 +225,7 @@ ONLY WHEN all source files have been analyzed, the Coverage Analysis section has
 
 ### ✅ SUCCESS:
 
-- All source files analyzed at appropriate tier depth
+- All source files analyzed at appropriate tier depth; split-body references/ traversed when present
 - Every finding has file:line citation (Forge/Deep) or file-level reference (Quick)
 - Per-export status table complete
 - Category scores calculated per scoring rules

package/src/workflows/test-skill/steps-c/step-04-coherence-check.md

@@ -72,6 +72,7 @@ Perform lightweight structural checks:
 - Section headers are properly formatted
 - Code examples have language annotations
 - No broken markdown (unclosed code blocks, malformed tables)
+- If `scripts/` or `assets/` directory exists alongside SKILL.md, a "Scripts & Assets" section (Section 7b) should be present
 
 **Internal consistency:**
 - Exports referenced in usage examples match exports listed in exports section
@@ -101,6 +102,7 @@ Scan SKILL.md for all cross-references:
 - Skill references (`See SKILL.md for {other-skill}`, `Integrates with {package}`)
 - Type imports (`import { Type } from './module'`)
 - Integration pattern references (middleware chains, plugin hooks, shared state)
+- Script/asset references (`scripts/{file}`, `assets/{file}`) in SKILL.md body
 
 Launch a subprocess to grep/regex SKILL.md for reference patterns and return all found references with line numbers as structured JSON (`references_found[]` with line, type, target fields). If subprocess unavailable, scan in main thread.
 
@@ -114,6 +116,7 @@ DO NOT BE LAZY — For EACH reference found, launch a subprocess that:
    - Type imports: type is actually exported from the referenced module
    - Skill references: referenced skill exists in skills output folder
    - Integration patterns: documented pattern matches actual implementation
+   - Script/asset references: verify the referenced file exists in the skill's `scripts/` or `assets/` directory
 3. Returns structured validation JSON per reference (reference, line, target_exists, type_match, signature_match, issues[])
 
 If subprocess unavailable, validate each reference in main thread.
@@ -147,7 +150,7 @@ Build integration completeness findings:
 
 **Only execute if forge tier is Deep.** Skip silently for Quick/Forge tiers.
 
-Check whether SKILL.md contains a "Migration & Deprecation Warnings" section (Section 4b). Then check the skill's `evidence-report.md` (at `forge-data/{skill_name}/evidence-report.md`) for T2-future annotation counts.
+Check whether SKILL.md contains a "Migration & Deprecation Warnings" section (Section 4b). Then check the skill's `evidence-report.md` (at `{forge_data_folder}/{skill_name}/evidence-report.md`) for T2-future annotation counts.
 
 - **If T2-future annotations > 0 AND Section 4b is absent:** Flag as Medium severity gap: "Migration section missing — T2-future annotations exist but Section 4b is not present in SKILL.md Tier 1."
 - **If T2-future annotations = 0 AND Section 4b is present:** Flag as Medium severity gap: "Migration section unexpected — Section 4b is present but no T2-future annotations were produced."

package/src/workflows/test-skill/steps-c/step-04b-external-validators.md

@@ -58,9 +58,13 @@ Read {outputFile} frontmatter to get the skill directory path (`skillDir`).
 
 ### 1b. Check for Recent Validation Results (Auto-Reuse)
 
-Before running external validators, check if `{forge_data_folder}/{skill_name}/evidence-report.md` contains validation results (a `## Validation Results` section with quality scores). If recent results exist (from a create-skill run that just completed), auto-reuse them — skip re-running validators and use the existing scores from the evidence report. Record: "External validation: reused from create-skill evidence report." Skip to section 5 (append results).
+Before running external validators, check if `{forge_data_folder}/{skill_name}/evidence-report.md` contains validation results (a `## Validation Results` section with quality scores).
 
-If no evidence report exists or it contains no validation section, proceed to section 2 (fresh run).
+**Staleness check:** Compare the evidence report's generation date against SKILL.md's last-modified timestamp (or `metadata.json` `generation_date`). If SKILL.md was modified after the evidence report was generated (e.g., after update-skill), the cached results are stale — skip auto-reuse and proceed to section 2 for a fresh run.
+
+If recent, non-stale results exist (from a create-skill run that just completed), auto-reuse them — skip re-running validators and use the existing scores. Record: "External validation: reused from create-skill evidence report." Skip to section 5 (append results).
+
+If no evidence report exists, it contains no validation section, or results are stale, proceed to section 2 (fresh run).
 
 ### 2. Run skill-check
 
@@ -118,7 +122,7 @@ Store in context: `tessl_description_score`, `tessl_content_score`, `tessl_avera
 
 **If tessl content score < 70%:** Flag a warning:
 
-"**Content quality warning:** tessl scored content at {score}%. This often indicates SKILL.md lacks inline actionable content (e.g., after split-body). Consider inlining Quick Start and common workflows directly in SKILL.md."
+"**Content quality warning:** tessl scored content at {score}%. This often indicates SKILL.md lacks inline actionable content (e.g., after split-body). If this is a split-body skill, the score drop is expected — tessl evaluates only SKILL.md body, not `references/*.md` (see scoring-rules.md). Consider using selective split to keep actionable content inline."
 
 **If tessl fails entirely:** Record `tessl_score: N/A`, log warning, continue.
 

package/src/workflows/test-skill/steps-c/step-05-score.md

@@ -5,7 +5,7 @@ description: 'Calculate completeness score from coverage and coherence findings'
 nextStepFile: './step-06-report.md'
 outputFile: '{forge_data_folder}/{skill_name}/test-report-{skill_name}.md'
 scoringRulesFile: '../data/scoring-rules.md'
-sourceAccessProtocol: '../data/{sourceAccessProtocol}'
+sourceAccessProtocol: '../data/source-access-protocol.md'
 ---
 
 # Step 5: Score

package/src/workflows/test-skill/steps-c/step-06-report.md

@@ -83,8 +83,13 @@ Load `{scoringRulesFile}` for gap severity classification:
 | **High** | Signature mismatch between source and SKILL.md |
 | **Medium** | Missing type or interface documentation |
 | **Medium** | Migration section present/absent mismatch with T2-future annotation data (Deep tier) |
+| **Medium** | Script/asset directory exists but no Scripts & Assets section in SKILL.md |
+| **Medium** | Scripts & Assets section references file not found in scripts/ or assets/ directory |
+| **Low** | Script/asset file present without provenance entry in provenance-map.json file_entries |
 | **Low** | Missing optional metadata or examples |
+| **Low** | Description trigger optimization recommended (third-person voice, negative triggers, or keyword coverage gaps) |
 | **Info** | Style suggestions, non-blocking observations |
+| **Info** | Discovery testing not performed — realistic prompt testing recommended before export |
 
 ### 3. Classify and Order Gaps
 
@@ -98,6 +103,25 @@ Load the Gap Report section format from `{outputFormatsFile}`. Count gaps by sev
 
 If no gaps found, append a clean pass message recommending **export-skill** workflow.
 
+### 4b. Discovery and Description Quality Recommendations
+
+After gap enumeration, append a **Discovery Quality** subsection to the gap report. Use the `Gap Entry Format` from `{outputFormatsFile}` for any Low/Info entries. The prose recommendations below are appended after the gap entries:
+
+**Description optimization:** If tessl `description_score` (from step 04b) is below 90%, or if skill-check flagged description issues, recommend description improvements:
+- Check that the description uses third-person voice consistently
+- Check for specific trigger keywords that match how users would phrase requests
+- Check for negative triggers ("NOT for: ...") to prevent false matches
+- Check for alternative skill references for excluded use cases
+
+**Discovery testing recommendation:** Regardless of pass/fail, always append:
+
+"**Discovery testing recommended.** Before export, test the skill with 3-5 realistic prompts phrased the way real users actually talk — with casual language, typos, incomplete context, and implicit references. A skill tested only with clean prompts may fail to trigger in production. Example realistic prompt patterns:
+- Vague: 'can you help me with this csv file my boss sent'
+- Implicit: 'why did revenue drop last quarter'
+- Abbreviated: 'run the {skill-name} thing on this data'"
+
+Record discovery testing status as Info-level in the gap table. This is advisory — it does not affect the score.
+
 ### 5. Finalize Output Document
 
 Update `{outputFile}` frontmatter:
@@ -132,6 +156,8 @@ Update `{outputFile}` frontmatter:
 
 ---
 
+**See Discovery Quality section in the report for description optimization and realistic prompt testing recommendations.**
+
 **Test report finalized.**"
 
 ### 7. Present MENU OPTIONS
@@ -163,6 +189,7 @@ This is the final step of the test-skill workflow. When the user selects C, the
 - Gaps classified by severity using scoring rules
 - Gaps ordered by severity (Critical first)
 - Every gap has a specific, actionable remediation suggestion
+- Discovery quality section appended with description optimization and testing recommendations
 - Remediation summary with counts and effort estimates
 - Output document finalized with all stepsCompleted
 - Correct next workflow recommended (export-skill or update-skill)

package/src/workflows/test-skill/templates/test-report-template.md

@@ -6,6 +6,7 @@ testMode: ''
 forgeTier: ''
 testResult: ''
 score: ''
+threshold: ''
 analysisConfidence: ''
 testDate: ''
 stepsCompleted: []
@@ -20,6 +21,8 @@ nextWorkflow: ''
 
 ## Coherence Analysis
 
+## External Validation
+
 ## Completeness Score
 
 ## Gap Report

package/src/workflows/test-skill/validation-report.md

@@ -247,7 +247,7 @@ Each step has explicit CONTEXT BOUNDARIES with FORBIDDEN markers preventing scop
 
 ### Error Handling: Good
 
-- step-01: Three-tier handling (hard stop for missing SKILL.md, warning for missing metadata.json, graceful default for missing forge-tier.yaml). Checks `preferences.yaml` for `tier_override` after loading forge tier.
+- step-01: Four-tier handling (hard stop for missing SKILL.md, warning for missing metadata.json, graceful default for missing forge-tier.yaml). Checks `preferences.yaml` for `tier_override` after loading forge tier.
 - step-03/04: Subprocess fallback rules at multiple locations
 - step-06: Zero-gaps clean pass path
 
@@ -299,7 +299,7 @@ Subprocess optimization correctly concentrated in steps 03 and 04 (heavy analysi
 ### Strengths:
 
 1. Rigorous traceability (zero hallucination with file:line citations)
-2. Three-tier depth scaling (Quick/Forge/Deep)
+2. Four-tier depth scaling (Quick/Forge/Forge+/Deep)
 3. Clean separation of concerns with explicit FORBIDDEN markers
 4. Well-designed subprocess optimization with structured return formats
 5. Actionable remediation quality rules with good/bad examples

package/src/workflows/test-skill/workflow-plan-test-skill.md

@@ -76,7 +76,7 @@ Cognitive completeness verification — Verifies that a skill is complete enough
 - No frontmatter configuration for steps
 - No data files, templates, or output format specifications
 - Batch mode mechanics are unspecified
-- No forge tier awareness — coverage depth must scale with Quick/Forge/Deep tiers
+- No forge tier awareness — coverage depth must scale with Quick/Forge/Forge+/Deep tiers
 - No reference to forge-tier.yaml sidecar state for tier detection
 - Zero hallucination principle not encoded — scoring must trace to AST citations
 
@@ -274,7 +274,7 @@ Ferris (Audit mode): methodical, precise, evidence-based. Zero hallucination —
 workflowType: 'test-skill'
 skillName: '{skill_name}'
 testMode: '{naive|contextual}'
-forgeTier: '{Quick|Forge|Deep}'
+forgeTier: '{Quick|Forge|Forge+|Deep}'
 testResult: '{pass|fail}'
 score: '{N%}'
 threshold: '{N%}'

package/src/workflows/update-skill/steps-c/step-01-init.md

@@ -89,14 +89,15 @@ Search for the test report at `{forge_data_folder}/{skill_name}/test-report-{ski
 ### 3. Load Forge Tier Configuration
 
 **Load `{sidecar_path}/forge-tier.yaml`:**
-- Extract: `tier` (Quick, Forge, or Deep), available tools
+- Extract: `tier` (Quick, Forge, Forge+, or Deep), available tools
 - If missing: **ABORT** — "No forge-tier.yaml found. Run setup-forge first to detect available tools."
 
-**Apply tier override:** Read `{sidecar_path}/preferences.yaml`. If `tier_override` is set and is a valid tier value (Quick, Forge, or Deep), use it instead of the detected tier.
+**Apply tier override:** Read `{sidecar_path}/preferences.yaml`. If `tier_override` is set and is a valid tier value (Quick, Forge, Forge+, or Deep), use it instead of the detected tier.
 
 **Determine analysis capabilities:**
 - **Quick:** text pattern matching only → T1-low confidence
 - **Forge:** AST structural extraction → T1 confidence
+- **Forge+:** AST structural extraction + CCC semantic ranking → T1 confidence (with ccc signals)
 - **Deep:** AST + QMD semantic enrichment → T1 + T2 confidence
 
 ### 4. Load Provenance Map

package/src/workflows/update-skill/steps-c/step-02-detect-changes.md

@@ -112,6 +112,14 @@ Launch subprocesses in parallel that compare source state against provenance map
 - Cross-reference deleted files/exports with added files/exports
 - If content similarity > 80%: classify as RENAMED instead of deleted+added
 
+**Category D — Script/asset file changes:**
+- Compare `file_entries` from provenance-map.json against current source files
+- For each file_entry: compute current SHA-256 content hash, compare against stored hash
+- Files with changed hashes → MODIFIED_FILE
+- Files in provenance but missing from source → DELETED_FILE
+- Files in source matching detection patterns (scripts/, bin/, assets/, templates/) but not in provenance → NEW_FILE
+- Files in `scripts/[MANUAL]/` or `assets/[MANUAL]/` → SKIP (user-authored, preserved)
+
 Aggregate all subprocess results into a unified change manifest.
 
 **If degraded mode (no provenance map):**
@@ -136,6 +144,9 @@ Change Manifest:
   exports_renamed: [count]
   exports_moved: [count]
 
+  scripts_modified, scripts_added, scripts_deleted: {counts}
+  assets_modified, assets_added, assets_deleted: {counts}
+
   Per-file detail:
     {file_path}:
       status: MODIFIED|ADDED|DELETED|MOVED

package/src/workflows/update-skill/steps-c/step-03-re-extract.md

@@ -103,7 +103,7 @@ Perform tier-aware extraction on only the changed files identified in step 02, p
 DO NOT BE LAZY — For EACH file in the change manifest with status MODIFIED, ADDED, or RENAMED, launch a subprocess that:
 
 1. Loads the source file
-2. Performs tier-appropriate extraction (Quick/Forge/Deep)
+2. Performs tier-appropriate extraction (Quick/Forge/Forge+/Deep)
 3. For each export found:
    - Record: export name, type (function/class/type/constant), signature
    - Record: file path, start line, end line
@@ -119,6 +119,23 @@ DO NOT BE LAZY — For EACH file in the change manifest with status MODIFIED, AD
 
 **Re-export tracing (Forge/Deep only):** After extracting changed files, check if any public exports from the package entry point (`__init__.py`, `index.ts`, `lib.rs`) are unresolved — particularly when a changed file is part of a module re-export chain. Follow the **Re-Export Tracing** protocol in `{extractionPatternsData}` to trace unresolved symbols to their actual definition files.
 
+### 2b. CCC Semantic Ranking (Forge+ and Deep with ccc)
+
+**IF `tools.ccc` is true in forge-tier.yaml:**
+
+Before aggregating extraction results, use CCC to assess semantic significance of changes:
+
+1. Run `ccc_bridge.search("{skill_name}", source_root, top_k=15)` to get the skill's most semantically central files
+2. Cross-reference the change manifest files with CCC results
+3. Files appearing in BOTH the change manifest AND CCC's top results are **semantically significant changes** — flag them for priority in the merge step
+4. Store `{ccc_significant_changes: [{file, score}]}` in context
+
+This helps the merge step (section 4) prioritize which changes are most likely to affect the skill's core content vs. peripheral modifications.
+
+CCC failures: skip ranking silently, all changes treated equally.
+
+**IF `tools.ccc` is false:** Skip this section silently.
+
 ### 3. Deep Tier QMD Enrichment (Conditional)
 
 **ONLY if forge_tier == Deep:**
@@ -200,7 +217,7 @@ ONLY WHEN all changed files have been extracted and results compiled will you lo
 - Every changed file from manifest extracted with tier-appropriate method
 - All exports labeled with confidence tier (T1/T1-low/T2)
 - AST file:line citations on every extracted export
-- QMD enrichment performed for Deep tier (skipped with notice for Quick/Forge)
+- QMD enrichment performed for Deep tier (skipped with notice for Quick/Forge/Forge+)
 - Extraction results compiled with per-file detail
 - Summary displayed before auto-proceeding
 - No unchanged files extracted

package/src/workflows/update-skill/steps-c/step-04-merge.md

@@ -100,6 +100,14 @@ Follow the merge priority order from {mergeConflictRulesFile}:
 - Place before any [MANUAL] blocks at section boundary
 - No conflicts expected (new content, no existing [MANUAL])
 
+**Priority 6 — Process script/asset file changes (from Category D in change manifest):**
+- MODIFIED_FILE: queue file for re-copy from source, update `file_entries` content_hash
+- DELETED_FILE: queue file for removal from `scripts/` or `assets/`, remove from `file_entries`
+- NEW_FILE: queue file for copy from source, add to `file_entries`
+- Files in `scripts/[MANUAL]/` or `assets/[MANUAL]/` are never modified (user-authored)
+- Update Section 7b manifest table to reflect changes
+- Update `metadata.json` `scripts[]`/`assets[]` arrays and `stats.scripts_count`/`stats.assets_count`
+
 ### 4. Check for Conflicts
 
 Scan all merge operations for flagged conflicts:

package/src/workflows/update-skill/steps-c/step-05-validate.md

@@ -73,7 +73,7 @@ Launch subprocesses in parallel for each validation category, aggregating result
 
 **If available**, run: `npx skill-check check <skill-dir> --fix --format json --no-security-scan`
 
-Parse JSON output for quality score (0-100), auto-fixed issues, and remaining diagnostics. If `body.max_lines` reported, run: `npx skill-check split-body <skill-dir> --write`
+Parse JSON output for quality score (0-100), auto-fixed issues, and remaining diagnostics. If `body.max_lines` reported, prefer selective split: extract only the largest Tier 2 section(s) to `references/`, keeping all Tier 1 content inline (selective split preserves agent accuracy — inline passive context achieves 100% task accuracy vs 79% for on-demand retrieval per Vercel research). Fall back to `npx skill-check split-body <skill-dir> --write` only if selective split is not feasible. After any split, verify `#quick-start` and `#key-types` anchors still resolve in SKILL.md.
 
 **If unavailable**, perform manual check: validate merged SKILL.md structure, verify required sections (exports, usage patterns, conventions), verify export entries have name/type/signature/file:line reference, flag missing sections.
 

package/src/workflows/update-skill/steps-c/step-06-write.md

@@ -96,6 +96,11 @@ Write to `{forge_data_folder}/{skill_name}/provenance-map.json`:
 **For new exports:**
 - Add new entry with full structured fields: `export_name`, `export_type`, `params[]`, `return_type`, `source_file`, `source_line`, `confidence`, `extraction_method`, `ast_node_type`
 
+**For script/asset file changes (if `file_entries` exists):**
+- MODIFIED_FILE: copy updated file to `scripts/` or `assets/`, update `content_hash` in `file_entries`
+- DELETED_FILE: remove file from `scripts/` or `assets/`, remove entry from `file_entries`
+- NEW_FILE: copy file to `scripts/` or `assets/`, add entry to `file_entries` with `file_name`, `file_type`, `source_file`, `confidence: "T1-low"`, `extraction_method: "file-copy"`, `content_hash`
+
 **Add update operation metadata:**
 ```json
 {
@@ -110,7 +115,7 @@ Write to `{forge_data_folder}/{skill_name}/provenance-map.json`:
 
 ### 4. Write Updated evidence-report.md
 
-Append update operation section to `{forge_data_folder}/{skill_name}/evidence-report.md`:
+Append update operation section to `{forge_data_folder}/{skill_name}/evidence-report.md` (create the file with a standard header if it does not yet exist):
 
 ```markdown
 ## Update Operation — {current_date}
@@ -177,7 +182,7 @@ External tool checks deferred from step-05 now run against the written files:
 
 **If skill-check available:**
 - Run: `npx skill-check check {skills_output_folder}/{skill_name} --fix --format json --no-security-scan`
-- If `body.max_lines` reported, run: `npx skill-check split-body {skills_output_folder}/{skill_name} --write`
+- If `body.max_lines` reported, prefer selective split — extract only the largest Tier 2 section(s) to `references/`, keeping Tier 1 inline (inline passive context achieves 100% task accuracy vs 79% for on-demand retrieval). Fall back to `npx skill-check split-body {skills_output_folder}/{skill_name} --write` if not feasible. Verify anchors resolve after split.
 - Run: `npx skill-check diff` if original version was preserved
 - Run: `npx skill-check check {skills_output_folder}/{skill_name} --format json` for security scan
 

package/src/workflows/update-skill/validation-report.md

@@ -413,7 +413,7 @@ This workflow is a well-architected surgical pipeline that achieves its goal of
 
 1. **Zero-hallucination principle** enforced throughout — every statement must trace to actual artifacts
 2. **[MANUAL] section preservation** treated as highest priority with multiple safeguards (inventory in step-01, preservation in step-04, integrity verification in step-05, write verification in step-06)
-3. **Tier-aware extraction** well-implemented across Quick/Forge/Deep with graceful degradation
+3. **Tier-aware extraction** well-implemented across Quick/Forge/Forge+/Deep with graceful degradation
 4. **Subprocess optimization** strategically placed at the right steps (02-parallel, 03-per-file, 03-QMD, 05-parallel)
 5. **Error handling** is comprehensive (missing artifacts → abort with helpful message, missing provenance → degraded mode, [MANUAL] conflicts → user resolution)
 6. **Workflow chaining** properly integrated with input/output contracts

package/src/workflows/update-skill/workflow-plan-update-skill.md

@@ -125,7 +125,7 @@ Document-producing workflow that outputs:
 
 ### Missing Features to Add During Conversion
 
-1. Tier-aware re-extraction (Quick/Forge/Deep graceful degradation)
+1. Tier-aware re-extraction (Quick/Forge/Forge+/Deep graceful degradation)
 2. Degraded mode for missing provenance map (fallback to full re-extraction)
 3. Stack skill multi-file update support
 4. Batch mode with checkpoint resume