bmad-module-skill-forge 0.4.0 → 0.6.0

package/src/workflows/create-skill/steps-c/step-01-load-brief.md

@@ -61,10 +61,11 @@ Halt with: "Forge halted: No forge configuration found. Run [SF] Setup Forge fir
 
 **If file exists:**
 Extract and report:
-- `tier`: Quick, Forge, or Deep
-- `tools`: which tools are available (gh, ast-grep, qmd)
+- `tier`: Quick, Forge, Forge+, or Deep
+- `tools`: which tools are available (gh, ast-grep, ccc, qmd)
+- `ccc_index`: ccc index state (status, indexed_path, last_indexed) — needed by step-02b
 
-**Apply tier override:** Read `{preferencesFile}`. 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 `{preferencesFile}`. If `tier_override` is set and is a valid tier value (Quick, Forge, Forge+, or Deep), use it instead of the detected tier.
 
 ### 2. Discover Skill Brief
 
@@ -138,6 +139,7 @@ Proceeding to ecosystem check..."
 Where tier_description follows positive capability framing:
 - Quick: "Source reading and spec validation"
 - Forge: "AST-backed structural extraction"
+- Forge+: "Semantic-guided precision — ccc pre-ranks files before AST extraction"
 - Deep: "Full intelligence — structural + contextual + temporal"
 
 ### 6. Menu Handling Logic

package/src/workflows/create-skill/steps-c/step-02-ecosystem-check.md

@@ -1,7 +1,7 @@
 ---
 name: 'step-02-ecosystem-check'
 description: 'Check agentskills.io ecosystem for existing official skill before compilation'
-nextStepFile: './step-03-extract.md'
+nextStepFile: './step-02b-ccc-discover.md'
 ---
 
 # Step 2: Ecosystem Check
@@ -131,7 +131,7 @@ If no match is found, this step auto-proceeds with no user interaction.
 - Match presented factually with clear options if found
 - No-match case auto-proceeds silently
 - User decision respected (Proceed/Install/Abort)
-- Auto-proceeded to step-03 (when no match or user chose Proceed)
+- Auto-proceeded to step-02b (when no match or user chose Proceed)
 
 ### ❌ SYSTEM FAILURE:
 

package/src/workflows/create-skill/steps-c/step-02b-ccc-discover.md

@@ -0,0 +1,157 @@
+---
+name: 'step-02b-ccc-discover'
+description: 'CCC semantic discovery pass — Forge+ and Deep tiers when ccc is available, skip for Quick/Forge'
+nextStepFile: './step-03-extract.md'
+---
+
+# Step 2b: CCC Semantic Discovery
+
+## STEP GOAL:
+
+If tier is Forge+ or Deep AND ccc is available, perform a semantic discovery pass over the source code to identify the most relevant files for the skill being created. Store ranked discovery results in context to pre-rank the file extraction queue in step-03.
+
+For Quick and Forge tiers, or when ccc is unavailable, skip silently and proceed.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+
+- 📖 CRITICAL: Read the complete step file before taking any action
+- 🎯 ALWAYS follow the exact instructions in the step file
+- 🔄 CRITICAL: When loading next step, ensure entire file is read
+- ⚙️ TOOL/SUBPROCESS FALLBACK: If any instruction references a tool you do not have access to, you MUST still achieve the outcome in your main context thread
+- ✅ YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`
+
+### Role Reinforcement:
+
+- ✅ You are a skill compilation engine performing semantic pre-discovery
+- ✅ CCC discovery is a hint layer — it guides extraction, it does not replace it
+- ✅ Discovery failure is graceful degradation, not an error
+
+### Step-Specific Rules:
+
+- 🎯 Focus ONLY on running ccc semantic search and storing results
+- 🚫 FORBIDDEN to extract exports — that is step-03
+- 🚫 FORBIDDEN to modify brief data or source resolution
+- 🚫 FORBIDDEN to block the workflow if ccc fails
+- ⏱️ Quick and Forge tiers: skip this step entirely and silently
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Follow MANDATORY SEQUENCE exactly
+- 💾 Discovery results stored in context as `{ccc_discovery}`
+- 📖 Results are consumed by step-03 to pre-rank the file extraction queue
+- 🚫 Never treat ccc results as verified extractions
+
+## CONTEXT BOUNDARIES:
+
+- Available: tier, tools.ccc, ccc_index from forge-tier.yaml (loaded in step-01)
+- Available: brief_data (name, scope, description) from step-01
+- Available: source_root (resolved source path) from step-01
+- Focus: Semantic discovery only — no extraction, no compilation
+- Dependencies: step-02 must have completed
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise.
+
+### 1. Check Tier Eligibility
+
+**If tier is Quick or Forge:**
+
+Set `{ccc_discovery: []}` in context. Auto-proceed silently. Display no message. Immediately load, read entire file, then execute `{nextStepFile}`.
+
+**If tier is Forge+ or Deep:**
+
+Check `tools.ccc` from forge-tier.yaml. If `tools.ccc` is false, set `{ccc_discovery: []}` in context and auto-proceed to section 5.
+
+If `tools.ccc` is true, continue to section 2.
+
+### 2. Check CCC Index State
+
+Read `ccc_index` from forge-tier.yaml:
+
+- If `ccc_index.status` is `"fresh"`: continue to section 3.
+- If `ccc_index.status` is `"stale"`: display brief note — "CCC index is stale — discovery results may miss recent changes." Continue to section 3.
+- If `ccc_index.status` is `"none"` or `"failed"`: attempt lazy indexing via `ccc_bridge.ensure_index(source_root)`. If indexing succeeds, continue to section 3. If indexing fails, set `{ccc_discovery: []}` and auto-proceed to section 5.
+
+### 3. Construct Semantic Query
+
+Build the discovery query from the brief data:
+
+**Primary query:** `"{brief.name} {brief.scope}"`
+
+Where:
+- `brief.name` is the skill name from the brief
+- `brief.scope` is the scope field (e.g., "Full library", "Public API", or specific module names)
+
+**Query length cap:** Truncate to 80 characters if longer — ccc semantic search is sensitive to overly long queries. When truncating, keep the full skill name and trim `brief.scope` from the end. If `brief.scope` is very short (< 10 chars), append terms from `brief.description` to fill the remaining space.
+
+### 4. Execute CCC Semantic Search
+
+Run `ccc_bridge.search(query, source_root, top_k=20)`:
+
+**If search succeeds:**
+
+Store results as `{ccc_discovery: [{file, score, snippet}]}` in context.
+
+Display brief discovery summary:
+
+"**CCC semantic discovery: {N} relevant regions identified across {M} unique files.**"
+
+Where:
+- `{N}` is the total result count
+- `{M}` is the count of unique file paths in results
+
+**If search fails (any error):**
+
+Set `{ccc_discovery: []}` in context.
+
+Display: "CCC discovery unavailable — proceeding with standard extraction."
+
+Do NOT halt. This is not an error.
+
+**If search returns empty results:**
+
+Set `{ccc_discovery: []}` in context.
+
+No message needed — empty results are normal for small or highly focused libraries.
+
+### 5. Auto-Proceed
+
+Immediately load, read entire file, then execute `{nextStepFile}`.
+
+#### EXECUTION RULES:
+
+- This is an auto-proceed step with no user choices
+- Quick/Forge tiers skip directly with no output
+- Forge+/Deep with ccc displays brief discovery summary then auto-proceeds
+- CCC failures do not halt — degrade and proceed
+
+## CRITICAL STEP COMPLETION NOTE
+
+ONLY WHEN discovery is complete (Forge+/Deep with ccc) or the step is skipped (Quick/Forge or ccc unavailable) will you proceed to load `{nextStepFile}` for AST extraction.
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- Quick/Forge tiers: skipped silently with no output, auto-proceeded
+- Forge+/Deep with ccc: semantic query constructed from brief data
+- Forge+/Deep with ccc: ccc_bridge.search executed, results stored as `{ccc_discovery}` in context
+- Discovery summary displayed (count of regions and unique files)
+- CCC failures handled gracefully (empty discovery, continue)
+- Auto-proceeded to step-03
+
+### ❌ SYSTEM FAILURE:
+
+- Halting on CCC unavailability or search failures
+- Extracting exports or signatures (that is step-03)
+- Displaying skip messages for Quick/Forge tiers
+- Treating CCC discovery results as verified extractions
+- Not storing `{ccc_discovery}` in context (even if empty)
+- Beginning compilation or SKILL.md assembly in this step
+
+**Master Rule:** CCC discovery is a hint layer. It improves extraction coverage but never replaces structural verification. Failures degrade gracefully.

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

@@ -3,6 +3,7 @@ name: 'step-03-extract'
 description: 'Tier-dependent source code extraction — AST or source reading for exports, signatures, and types'
 nextStepFile: './step-03b-fetch-temporal.md'
 extractionPatternsData: '../data/extraction-patterns.md'
+extractionPatternsTracingData: '../data/extraction-patterns-tracing.md'
 tierDegradationRulesData: '../data/tier-degradation-rules.md'
 sourceResolutionData: '../data/source-resolution-protocols.md'
 ---
@@ -91,7 +92,16 @@ Load `{sourceResolutionData}` completely. Follow the **Remote Source Resolution*
 5. Infer types from JSDoc, docstrings, type annotations
 6. Confidence: All results T1-low — `[SRC:{file}:L{line}]`
 
-**Forge/Deep Tier (AST available):**
+**Forge/Forge+/Deep Tier (AST available):**
+
+**CCC Discovery Integration (Forge+ and Deep with ccc only):**
+
+If `{ccc_discovery}` is in context and non-empty (populated by step-02b):
+- Sort the filtered file list by CCC relevance score: files appearing in `{ccc_discovery}` results move to the front of the extraction queue, sorted by their relevance score descending
+- Files NOT in CCC results remain in the queue after ranked files — they are not excluded, only deprioritized
+- Display: "**CCC discovery: {N} files pre-ranked by semantic relevance** — extraction will prioritize these first."
+
+If `{ccc_discovery}` is empty or not in context: proceed with existing file ordering (no change to current behavior).
 
 ⚠️ **CRITICAL:** Before executing AST extraction, load the **AST Extraction Protocol** section from `{extractionPatternsData}`. Follow the decision tree based on the file count from step-01's file tree. This determines whether to use the MCP tool, scoped YAML rules, or CLI streaming. Never use `ast-grep --json` (without `=stream`) — it loads the entire result set into memory and will fail on large codebases.
 
@@ -118,7 +128,7 @@ Degrade to Quick tier extraction. Note the degradation reason in context for the
 
 **Re-export tracing (Forge/Deep only):**
 
-After the initial AST scan, check for public exports from the entry point (`__init__.py`, `index.ts`, `lib.rs`) that were NOT found by AST extraction. These are likely module-level re-exports. Follow the **Re-Export Tracing** protocol in `{extractionPatternsData}` to resolve them to their actual definition files. This ensures module re-export patterns (common in Python libraries with clean public APIs) do not create gaps in the extraction inventory.
+After the initial AST scan, check for public exports from the entry point (`__init__.py`, `index.ts`, `lib.rs`) that were NOT found by AST extraction. These are likely module-level re-exports. Follow the **Re-Export Tracing** protocol in `{extractionPatternsTracingData}` to resolve them to their actual definition files. This ensures module re-export patterns (common in Python libraries with clean public APIs) do not create gaps in the extraction inventory.
 
 ### 4b. Validate Exports Against Package Entry Point
 
@@ -135,6 +145,20 @@ Use the entry point as the authoritative source for `metadata.json`'s `exports[]
 
 **If entry point is missing or unreadable:** Skip validation with a warning. Use the AST-extracted list as-is.
 
+### 4c. Detect and Inventory Scripts/Assets
+
+**If `scripts_intent: "none"` AND `assets_intent: "none"` in brief:** Skip this section.
+
+After export extraction, scan the source for scripts and assets using the detection patterns in `{extractionPatternsTracingData}`:
+
+1. Scan source tree for directories/files matching detection heuristics (scripts/, bin/, tools/, cli/ for scripts; assets/, templates/, schemas/, configs/, examples/ for assets)
+2. For each candidate: verify file exists, check size (flag if >500 lines for user confirmation), exclude binary files
+3. Compute SHA-256 content hash for each included file
+4. Extract purpose from file header comments, shebang, README references, or schema `title`/`description` fields. If no purpose found, use filename.
+5. Record: file_path, purpose, source_path, language (for scripts), type (for assets), content_hash, confidence (T1-low)
+
+Add results to `scripts_inventory[]` and `assets_inventory[]` alongside the existing export inventory.
+
 ### 5. Build Extraction Inventory
 
 Compile all extracted data into a structured inventory:
@@ -155,6 +179,10 @@ Compile all extracted data into a structured inventory:
 - Confidence breakdown (T1 count, T1-low count)
 - `top_exports[]` — sorted list of the top 10-20 public API function names by prominence (import frequency or documentation position). This named field is consumed by step-03b for targeted temporal fetching and cache fingerprinting.
 
+**Script/asset counts (when detected):**
+- `scripts_found`: count of scripts detected
+- `assets_found`: count of assets detected
+
 **Co-import patterns (Forge/Deep only):**
 - Libraries commonly imported alongside extracted exports
 - Integration point suggestions
@@ -170,6 +198,8 @@ Display the extraction findings for user confirmation:
 **Confidence:** {t1_count} T1 (AST-verified), {t1_low_count} T1-low (source reading)
 **Tier used:** {tier}
 **Co-import patterns:** {pattern_count} detected
+{if scripts_found > 0: **Scripts detected:** {scripts_found}}
+{if assets_found > 0: **Assets detected:** {assets_found}}
 
 **Top exports:**
 {list top 10 exports with signatures}

package/src/workflows/create-skill/steps-c/step-03b-fetch-temporal.md

@@ -27,7 +27,7 @@ To fetch temporal context (issues, PRs, changelogs, release notes) from the sour
 
 ### Step-Specific Rules:
 
-- 🎯 Deep tier only — Quick and Forge tiers skip this step entirely and silently
+- 🎯 Deep tier only — Quick, Forge, and Forge+ tiers skip this step entirely and silently
 - 🎯 GitHub repositories only — other source types degrade gracefully
 - 🚫 FORBIDDEN to halt the workflow if fetching or indexing fails
 - 🚫 FORBIDDEN to modify extraction data from step-03 — this step only creates QMD collections
@@ -56,7 +56,7 @@ To fetch temporal context (issues, PRs, changelogs, release notes) from the sour
 
 Evaluate the following conditions sequentially. **If ANY condition fails, skip silently to section 5 (auto-proceed) with no output:**
 
-1. **Tier is Deep:** If tier is Quick or Forge, skip silently.
+1. **Tier is Deep:** If tier is Quick, Forge, or Forge+, skip silently.
 2. **Source is GitHub:** Verify `source_repo` is a GitHub URL (`https://github.com/...`) or `owner/repo` format. If the source is a local path, a non-GitHub URL, or any other format, skip silently.
 3. **`gh` CLI is available:** Run `gh auth status` to verify the CLI is installed and authenticated. If it fails, skip silently.
 
@@ -200,7 +200,7 @@ After temporal context is fetched and indexed (or skipped for any reason), immed
 #### EXECUTION RULES:
 
 - This is an auto-proceed step with no user choices
-- Quick/Forge tiers skip directly to next step with no output
+- Quick/Forge/Forge+ tiers skip directly to next step with no output
 - Non-GitHub sources skip directly to next step with no output
 - Cached collections (< 7 days old) skip with brief cache-hit message
 - Deep tier with fresh fetch displays brief confirmation then auto-proceeds
@@ -216,7 +216,7 @@ ONLY WHEN temporal context is indexed into QMD (or the step is skipped due to el
 
 ### ✅ SUCCESS:
 
-- Non-eligible scenarios (Quick/Forge tier, non-GitHub source, no `gh` CLI) skipped silently
+- Non-eligible scenarios (Quick/Forge/Forge+ tier, non-GitHub source, no `gh` CLI) skipped silently
 - Cached collections (< 7 days old) detected and re-fetch skipped
 - Temporal data fetched via `gh` CLI into staging directory (generic + targeted)
 - Targeted searches performed for up to 10 top_exports function names
@@ -231,7 +231,7 @@ ONLY WHEN temporal context is indexed into QMD (or the step is skipped due to el
 - Halting the workflow due to a `gh` CLI, QMD, or network failure
 - Leaving staging files on disk after indexing (must clean up)
 - Overwriting or modifying extraction data from step-03
-- Displaying skip messages for Quick/Forge tiers (should be silent)
+- Displaying skip messages for Quick/Forge/Forge+ tiers (should be silent)
 - Attempting to fetch temporal data from non-GitHub sources
 - Not registering the collection in forge-tier.yaml after successful indexing
 

package/src/workflows/create-skill/steps-c/step-04-enrich.md

@@ -1,6 +1,6 @@
 ---
 name: 'step-04-enrich'
-description: 'QMD knowledge enrichment for extracted functions — Deep tier only, skip for Quick/Forge'
+description: 'QMD knowledge enrichment for extracted functions — Deep tier only, skip for Quick/Forge/Forge+'
 nextStepFile: './step-05-compile.md'
 ---
 
@@ -8,7 +8,7 @@ nextStepFile: './step-05-compile.md'
 
 ## STEP GOAL:
 
-To enrich the extraction inventory with temporal context from QMD knowledge searches — issues, PRs, changelogs, and migration notes that add T2-confidence annotations to extracted functions. Deep tier only; Quick and Forge tiers skip this step entirely.
+To enrich the extraction inventory with temporal context from QMD knowledge searches — issues, PRs, changelogs, and migration notes that add T2-confidence annotations to extracted functions. Deep tier only; Quick, Forge, and Forge+ tiers skip this step entirely.
 
 ## MANDATORY EXECUTION RULES (READ FIRST):
 
@@ -31,7 +31,7 @@ To enrich the extraction inventory with temporal context from QMD knowledge sear
 - 🚫 FORBIDDEN to modify extraction results — enrichment is additive only
 - 🚫 FORBIDDEN to begin compilation — that's step-05
 - 💬 QMD failures degrade gracefully — continue without enrichment
-- ⏱️ Quick and Forge tiers: skip this step entirely, auto-proceed
+- ⏱️ Quick, Forge, and Forge+ tiers: skip this step entirely, auto-proceed
 
 ## EXECUTION PROTOCOLS:
 
@@ -53,7 +53,7 @@ To enrich the extraction inventory with temporal context from QMD knowledge sear
 
 ### 1. Check Tier Eligibility
 
-**If tier is Quick or Forge:**
+**If tier is Quick, Forge, or Forge+:**
 
 Auto-proceed silently. Display no message. Immediately load, read entire file, then execute `{nextStepFile}`.
 
@@ -145,13 +145,13 @@ After enrichment is complete (or skipped for non-Deep tiers), immediately load,
 #### EXECUTION RULES:
 
 - This is an auto-proceed step with no user choices
-- Quick/Forge tiers skip directly to next step with no output
+- Quick/Forge/Forge+ tiers skip directly to next step with no output
 - Deep tier displays brief enrichment summary then auto-proceeds
 - QMD failures do not halt — degrade and proceed
 
 ## CRITICAL STEP COMPLETION NOTE
 
-ONLY WHEN enrichment is complete (Deep tier) or the step is skipped (Quick/Forge) will you proceed to load `{nextStepFile}` for SKILL.md compilation.
+ONLY WHEN enrichment is complete (Deep tier) or the step is skipped (Quick/Forge/Forge+) will you proceed to load `{nextStepFile}` for SKILL.md compilation.
 
 ---
 
@@ -159,7 +159,7 @@ ONLY WHEN enrichment is complete (Deep tier) or the step is skipped (Quick/Forge
 
 ### ✅ SUCCESS:
 
-- Quick/Forge tiers: skipped silently with no output, auto-proceeded
+- Quick/Forge/Forge+ tiers: skipped silently with no output, auto-proceeded
 - Deep tier: collection inventory checked before searching
 - Deep tier: no temporal collections → reported and auto-proceeded (not silently skipped)
 - Deep tier: temporal collections exist → QMD searches performed per public API function (10-20, not all exports) with module context derived from extraction inventory source paths
@@ -172,7 +172,7 @@ ONLY WHEN enrichment is complete (Deep tier) or the step is skipped (Quick/Forge
 
 - Halting on QMD unavailability or search failures
 - Modifying T1 extraction results with QMD data
-- Displaying skip messages for Quick/Forge tiers (should be silent)
+- Displaying skip messages for Quick/Forge/Forge+ tiers (should be silent)
 - Pre-emptively skipping all searches without checking the collection inventory
 - Searching all 800+ exports instead of scoping to public API surface (10-20)
 - Using bare function names without module context when source path is available in extraction inventory

package/src/workflows/create-skill/steps-c/step-05-compile.md

@@ -61,7 +61,7 @@ Load `{skillSectionsData}` and `{assemblyRulesData}` completely. These define th
 
 ### 2. Build SKILL.md Content
 
-Assemble each section in order using the assembly rules data file (`{assemblyRulesData}`). The data file specifies frontmatter format, Tier 1 section details (Sections 1-8), Tier 2 section details (Sections 9-11), and assembly ordering rules. Follow it exactly.
+Assemble each section in order using the assembly rules data file (`{assemblyRulesData}`). The data file specifies frontmatter format, Tier 1 section details (Sections 1-8, including conditional Section 7b for scripts/assets), Tier 2 section details (Sections 9-11), and assembly ordering rules. Follow it exactly. Assemble Section 7b (Scripts & Assets) only if `scripts_inventory` or `assets_inventory` is non-empty.
 
 ### 3. Build context-snippet.md Content
 
@@ -97,7 +97,11 @@ Following the structure from the skill-sections data file:
   - `exports_total`: `exports_public_api` + `exports_internal`
   - `public_api_coverage`: `exports_documented / exports_public_api` (1.0 when all public API exports are documented; `null` if `exports_public_api` is 0)
   - `total_coverage`: `exports_documented / exports_total` (may be low for large codebases — this is expected; `null` if `exports_total` is 0)
+- Set `description` from the SKILL.md frontmatter `description` field (already assembled in section 2)
+- Set `language` from source analysis (e.g., `"typescript"`, `"python"`) — use the primary language of the entry point file
+- Set `ast_node_count` from extraction stats if ast-grep was used (Forge/Deep tier), otherwise omit
 - Set `tool_versions` based on tier and available tools. Resolve `{skf_version}` from the SKF module's `package.json` `version` field (run `node -p "require('./node_modules/bmad-module-skill-forge/package.json').version"` or read the installed module's `package.json`). If unresolvable, fall back to `git describe --tags --abbrev=0` in the SKF module root. Never hardcode the version.
+- If `scripts_inventory` is non-empty, populate `scripts[]` array and set `stats.scripts_count`. If `assets_inventory` is non-empty, populate `assets[]` array and set `stats.assets_count`. Omit these fields entirely when inventories are empty.
 
 ### 5. Build references/ Content
 
@@ -111,7 +115,7 @@ Group functions logically by module, file, or functional area.
 
 ### 6. Build provenance-map.json Content
 
-One entry per extracted export: export_name, export_type, params[] (typed strings), return_type, source_file, source_line, confidence tier (T1/T1-low/T2), extraction_method, ast_node_type. See `{skillSectionsData}` for full schema.
+One entry per extracted export: export_name, export_type, params[] (typed strings), return_type, source_file, source_line, confidence tier (T1/T1-low/T2), extraction_method, ast_node_type. If `scripts_inventory` or `assets_inventory` is non-empty, add `file_entries[]` with file_name, file_type, source_file, content_hash, confidence, extraction_method. See `{skillSectionsData}` for full schema.
 
 ### 7. Build evidence-report.md Content
 

package/src/workflows/create-skill/steps-c/step-06-validate.md

@@ -101,10 +101,16 @@ If fails: auto-fix (deterministic), re-validate once, record result. If passes:
 
 **If step 2 reported `body.max_lines` failure:**
 
+**Preferred approach — selective split:** Rather than a full `split-body`, identify which Tier 2 section(s) are largest (usually `## Full API Reference`) and manually extract only those to `references/`. Keep all Tier 1 content and smaller Tier 2 sections inline. This preserves agent accuracy — inline passive context achieves 100% task accuracy vs 79% for on-demand retrieval (per Vercel research). The rationale: inline passive context achieves 100% task accuracy vs 79% for on-demand retrieval (per Vercel research).
+
+**If manual selective split is not feasible**, fall back to the automated full split:
+
 ```bash
 npx skill-check split-body <staging-skill-dir> --write
 ```
 
+After any split (selective or full), verify that context snippet section anchors (`#quick-start`, `#key-types`) still resolve to headings in SKILL.md.
+
 Then re-validate: `npx skill-check check <staging-skill-dir> --format json --no-security-scan`
 
 **If skill-check unavailable or no body size issue:** Skip.
@@ -123,15 +129,7 @@ Record any security warnings in evidence-report. Security findings are advisory
 
 **If security scan fails due to missing SNYK_TOKEN:**
 
-Display actionable guidance:
-
-"Security scan requires a Snyk API token. **Important:** The Snyk API requires an Enterprise plan ([authentication docs](https://docs.snyk.io/snyk-api/authentication-for-api)). To enable:
-1. Obtain a Snyk Enterprise account with API access
-2. Get your API token from Account Settings → API Token
-3. Set `SNYK_TOKEN=your-token` in your environment or `.env`
-4. Re-run [SF] Setup Forge to update tool detection, then re-run [CS] Create Skill
-
-If you don't have an Enterprise account, use `--no-security-scan` flag in skill-check to skip, or `--security-scan-runner pipx|uvx|local` to control the execution method. Security scanning is optional and does not affect tier level or block skill compilation."
+Display: "Security scan requires a Snyk Enterprise API token ([docs](https://docs.snyk.io/snyk-api/authentication-for-api)). Set `SNYK_TOKEN=your-token` in environment or `.env`, then re-run [SF] Setup Forge. Without Enterprise, use `--no-security-scan` to skip. Security scanning is optional and does not block skill compilation."
 
 Record: "Security scan skipped — SNYK_TOKEN not configured"
 
@@ -185,6 +183,7 @@ Cross-check metadata.json against extraction inventory:
 - `stats.public_api_coverage` and `stats.total_coverage` are correctly computed (null when denominator is 0)
 - `confidence_t1`, `confidence_t2`, `confidence_t3` match actual counts
 - `spec_version` is "1.3"
+- If `scripts[]` or `assets[]` arrays present: verify `stats.scripts_count`/`stats.assets_count` match array lengths; verify `file_entries` count in provenance-map.json matches
 
 Auto-fix any discrepancies (these are computed values).
 

package/src/workflows/create-skill/steps-c/step-07-generate-artifacts.md

@@ -62,6 +62,9 @@ skills/{name}/references/
 forge-data/{name}/
 ```
 
+If `scripts_inventory` is non-empty, also create: `skills/{name}/scripts/`
+If `assets_inventory` is non-empty, also create: `skills/{name}/assets/`
+
 Where `{name}` is the skill name from the brief (kebab-case).
 
 If directories already exist, do not error — proceed with file writing (overwrites existing files).
@@ -85,6 +88,14 @@ Write these 4 files from the compiled content:
 - One file per function group or type
 - Progressive disclosure detail files
 
+**Files 4b (conditional):** `skills/{name}/scripts/*`
+- One file per detected script, copied from source with content preserved
+- Only created when `scripts_inventory` is non-empty
+
+**Files 4c (conditional):** `skills/{name}/assets/*`
+- One file per detected asset, copied from source with content preserved
+- Only created when `assets_inventory` is non-empty
+
 ### 3. Write Workspace Artifacts to forge-data/{name}/
 
 Write these 3 files from the compiled content:
@@ -101,7 +112,7 @@ Write these 3 files from the compiled content:
 ### 4. Verify Write Completion
 
 After all files are written, verify:
-- All 7 files exist at their expected paths
+- All 7 base files exist at their expected paths, plus scripts/ and assets/ files when inventories are non-empty
 - List each file with its path and size
 
 **If any write failed:**
@@ -116,6 +127,8 @@ Display brief confirmation:
 - SKILL.md
 - context-snippet.md
 - metadata.json
+{if scripts: - scripts/ ({scripts_count} files)}
+{if assets: - assets/ ({assets_count} files)}
 - references/ ({reference_count} files)
 
 **Workspace (forge-data/{name}/):**
@@ -170,6 +183,38 @@ Write the updated forge-tier.yaml.
 
 **IF forge tier is NOT Deep:** Skip this section silently. No messaging.
 
+### 5b. CCC Index Registry Registration (Forge+ and Deep with ccc)
+
+**IF `tools.ccc` is true in forge-tier.yaml (Forge+ or Deep with ccc available):**
+
+Ensure the source path used for extraction is indexed by ccc and registered in the `ccc_index_registry` array.
+
+**Index verification:**
+
+Dispatch to ccc CLI (`ccc index {source_root}`) or ccc MCP tool — `ccc_bridge.ensure_index` is a conceptual interface, not a callable function. This is a no-op if the source was already indexed during setup-forge or step-02b.
+
+**Registry update:**
+
+Read `{forgeTierConfig}` and update the `ccc_index_registry` array.
+
+Deduplicate by `source_repo` (the canonical upstream URL from brief_data) combined with `skill_name` — NOT by local `path`, which may be an ephemeral clone path that changes on every run for remote repos. If an entry with matching `source_repo` + `skill_name` already exists, replace it. Otherwise, append:
+
+```yaml
+  - source_repo: "{brief.source_repo}"
+    path: "{source_root}"
+    skill_name: "{name}"
+    indexed_at: "{current ISO date}"
+    source_workflow: "create-skill"
+```
+
+Write the updated forge-tier.yaml.
+
+**Error handling:**
+- If ccc indexing fails: log the error, continue. Do NOT fail the workflow.
+- If forge-tier.yaml update fails: log the error, continue.
+
+**IF `tools.ccc` is false:** Skip this section silently. No messaging.
+
 ### 6. Menu Handling Logic
 
 **Auto-proceed step — no user interaction.**

package/src/workflows/create-skill/steps-c/step-08-report.md

@@ -74,6 +74,7 @@ Where `{primary_confidence}` is the predominant confidence tier (T1 if Forge/Dee
 | T1 (AST) | {t1_count} | Structurally verified via ast-grep |
 | T1-low (Source) | {t1_low_count} | Inferred from source reading |
 | T2 (QMD) | {t2_count} | Enriched with temporal context |
+| T3 (External) | {t3_count} | Sourced from external documentation URLs |
 
 **Output Files:**
 - `skills/{name}/SKILL.md` — Active skill with trigger-based usage

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

@@ -146,7 +146,7 @@ Linear pipeline with tool-delegated heavy lifting. No high-priority subprocess o
 
 - Data flows logically: brief → ecosystem → extraction → enrichment → compilation → validation → generation → report
 - No contradictions between steps
-- Tier-dependent behavior consistent across all 8 steps (Quick/Forge/Deep)
+- Tier-dependent behavior consistent across all 8 steps (Quick/Forge/Forge+/Deep)
 - Error handling consistent: graceful degradation everywhere except file write failures (which correctly halt)
 - Provenance citation format consistent (`[AST:{file}:L{line}]`, `[SRC:{file}:L{line}]`, `[QMD:{collection}:{doc}]`)
 - Overall narrative is a clear compilation pipeline

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

@@ -138,7 +138,7 @@ Compile a skill from a brief — the core compilation engine. Takes a skill-brie
 - Pattern: Linear with conditional branches within steps (tier-dependent)
 - Phases: Load → Check → Extract → Enrich → Compile → Validate → Generate → Report
 - Estimated steps: 8
-- Conditional logic: Steps 03/04 branch internally by forge tier (Quick/Forge/Deep)
+- Conditional logic: Steps 03/04 branch internally by forge tier (Quick/Forge/Forge+/Deep)
 - No branching steps — conditions stay within each step
 
 **User Interaction:**
@@ -225,6 +225,7 @@ create-skill/
 └── steps-c/
     ├── step-01-load-brief.md           (~150 lines, Init with Input Discovery)
     ├── step-02-ecosystem-check.md      (~120 lines, conditional gate)
+    ├── step-02b-ccc-discover.md        (~160 lines, conditional auto-proceed)
     ├── step-03-extract.md              (~200 lines, complex middle)
     ├── step-03b-fetch-temporal.md      (~240 lines, conditional auto-proceed)
     ├── step-03c-fetch-docs.md          (~215 lines, conditional auto-proceed)
@@ -241,6 +242,7 @@ create-skill/
 |------|------|------|-------------|------|
 | 01 | load-brief | Init (Input Discovery) | Auto-proceed (P3) | Load brief, resolve source, load forge tier |
 | 02 | ecosystem-check | Middle (Simple) | Conditional: auto if no match, user choice if match | Check ecosystem |
+| 02b | ccc-discover | Middle (Simple) | Auto-proceed (P3) — Forge+/Deep only | CCC semantic discovery to pre-rank files for extraction |
 | 03 | extract | Middle (Standard) | C only (P2) — Gate 2 | Tier-dependent extraction |
 | 03b | fetch-temporal | Middle (Simple) | Auto-proceed (P3) — Deep only | Fetch temporal context (issues, PRs, changelogs) and index into QMD |
 | 03c | fetch-docs | Middle (Simple) | Auto-proceed (P3) — when doc_urls present | Fetch remote documentation from brief-specified URLs for T3-confidence content |
@@ -257,7 +259,7 @@ create-skill/
 - If --batch: discover all briefs in specified directory
 - Load and validate brief structure (required fields: name, version, source_repo, language, scope)
 - Resolve source code location (local path or GitHub owner/repo)
-- Load forge-tier.yaml from sidecar — determine tier (Quick/Forge/Deep)
+- Load forge-tier.yaml from sidecar — determine tier (Quick/Forge/Forge+/Deep)
 - If forge-tier.yaml missing: halt with "Run [SF] Setup Forge first"
 - Auto-proceed to step-02
 

package/src/workflows/create-skill/workflow.md

@@ -18,7 +18,7 @@ installed_path: '{project-root}/_bmad/skf/workflows/skillforge/create-skill'
 - **Micro-file Design**: Each step of the overall goal is a self contained instruction file that you will adhere too 1 file as directed at a time
 - **Just-In-Time Loading**: Only 1 current step file will be loaded, read, and executed to completion - never load future step files until told to do so
 - **Sequential Enforcement**: Sequence within the step files must be completed in order, no skipping or optimization allowed
-- **Tier-Aware Execution**: Steps adapt behavior based on forge tier (Quick/Forge/Deep) loaded from sidecar at init
+- **Tier-Aware Execution**: Steps adapt behavior based on forge tier (Quick/Forge/Forge+/Deep) loaded from sidecar at init
 - **Zero Hallucination**: Every claim requires a provenance citation — uncitable content is excluded, not guessed
 
 ### Step Processing Rules

package/src/workflows/create-stack-skill/data/stack-skill-template.md

@@ -69,7 +69,7 @@ Indexed format targeting ~80-120 tokens per stack:
   "name": "{project}-stack",
   "version": "1.0.0",
   "generation_date": "{ISO-8601}",
-  "confidence_tier": "{Quick|Forge|Deep}",
+  "confidence_tier": "{Quick|Forge|Forge+|Deep}",
   "source_authority": "{official|community|internal}",
   "exports": [],
   "library_count": 0,

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

@@ -67,11 +67,11 @@ STOP — do not proceed.
 **If forge-tier.yaml exists:**
 
 Extract:
-- `forge_tier` — Quick, Forge, or Deep
+- `forge_tier` — Quick, Forge, Forge+, or Deep
 - `available_tools` — list of detected tools (gh_bridge, ast_bridge, qmd_bridge, skill-check)
 - `project_root` — project root path
 
-**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.
 
 ### 2. Validate Available Tools
 
@@ -109,6 +109,7 @@ If no optional inputs provided, auto-detection will be used.
 **Forge Tier:** {tier_description}
 - Quick: Source reading and import counting
 - Forge: + AST-backed structural analysis
+- Forge+: + CCC semantic co-import augmentation
 - Deep: + Temporal integration evolution
 
 **Available Tools:** {tool_list}