bmad-module-skill-forge 0.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (154) hide show
  1. package/.nvmrc +1 -0
  2. package/LICENSE +26 -0
  3. package/README.md +213 -0
  4. package/docs/404.md +20 -0
  5. package/docs/agents.md +73 -0
  6. package/docs/architecture.md +301 -0
  7. package/docs/examples.md +144 -0
  8. package/docs/getting-started.md +198 -0
  9. package/docs/index.md +75 -0
  10. package/docs/workflows.md +190 -0
  11. package/package.json +109 -0
  12. package/src/agents/forger.agent.yaml +93 -0
  13. package/src/forger/README.md +17 -0
  14. package/src/forger/forge-tier.yaml +13 -0
  15. package/src/forger/preferences.yaml +10 -0
  16. package/src/knowledge/agentskills-spec.md +158 -0
  17. package/src/knowledge/confidence-tiers.md +153 -0
  18. package/src/knowledge/manual-section-integrity.md +156 -0
  19. package/src/knowledge/overview.md +56 -0
  20. package/src/knowledge/progressive-capability.md +120 -0
  21. package/src/knowledge/provenance-tracking.md +163 -0
  22. package/src/knowledge/skf-knowledge-index.csv +9 -0
  23. package/src/knowledge/skill-lifecycle.md +150 -0
  24. package/src/knowledge/zero-hallucination.md +101 -0
  25. package/src/module-help.csv +12 -0
  26. package/src/module.yaml +22 -0
  27. package/src/workflows/README.md +148 -0
  28. package/src/workflows/analyze-source/data/skill-brief-schema.md +75 -0
  29. package/src/workflows/analyze-source/data/unit-detection-heuristics.md +88 -0
  30. package/src/workflows/analyze-source/steps-c/step-01-init.md +191 -0
  31. package/src/workflows/analyze-source/steps-c/step-01b-continue.md +144 -0
  32. package/src/workflows/analyze-source/steps-c/step-02-scan-project.md +208 -0
  33. package/src/workflows/analyze-source/steps-c/step-03-identify-units.md +199 -0
  34. package/src/workflows/analyze-source/steps-c/step-04-map-and-detect.md +222 -0
  35. package/src/workflows/analyze-source/steps-c/step-05-recommend.md +236 -0
  36. package/src/workflows/analyze-source/steps-c/step-06-generate-briefs.md +239 -0
  37. package/src/workflows/analyze-source/templates/analysis-report-template.md +41 -0
  38. package/src/workflows/analyze-source/validation-report.md +657 -0
  39. package/src/workflows/analyze-source/workflow-plan-analyze-source.md +385 -0
  40. package/src/workflows/analyze-source/workflow.md +61 -0
  41. package/src/workflows/audit-skill/data/drift-report-template.md +62 -0
  42. package/src/workflows/audit-skill/data/severity-rules.md +52 -0
  43. package/src/workflows/audit-skill/steps-c/step-01-init.md +195 -0
  44. package/src/workflows/audit-skill/steps-c/step-02-re-index.md +191 -0
  45. package/src/workflows/audit-skill/steps-c/step-03-structural-diff.md +194 -0
  46. package/src/workflows/audit-skill/steps-c/step-04-semantic-diff.md +199 -0
  47. package/src/workflows/audit-skill/steps-c/step-05-severity-classify.md +210 -0
  48. package/src/workflows/audit-skill/steps-c/step-06-report.md +217 -0
  49. package/src/workflows/audit-skill/validation-report.md +545 -0
  50. package/src/workflows/audit-skill/workflow-plan-audit-skill.md +318 -0
  51. package/src/workflows/audit-skill/workflow.md +63 -0
  52. package/src/workflows/brief-skill/data/skill-brief-schema.md +82 -0
  53. package/src/workflows/brief-skill/steps-c/step-01-gather-intent.md +184 -0
  54. package/src/workflows/brief-skill/steps-c/step-02-analyze-target.md +203 -0
  55. package/src/workflows/brief-skill/steps-c/step-03-scope-definition.md +225 -0
  56. package/src/workflows/brief-skill/steps-c/step-04-confirm-brief.md +185 -0
  57. package/src/workflows/brief-skill/steps-c/step-05-write-brief.md +156 -0
  58. package/src/workflows/brief-skill/validation-report.md +630 -0
  59. package/src/workflows/brief-skill/workflow-plan-brief-skill.md +360 -0
  60. package/src/workflows/brief-skill/workflow.md +57 -0
  61. package/src/workflows/create-skill/data/extraction-patterns.md +63 -0
  62. package/src/workflows/create-skill/data/skill-sections.md +166 -0
  63. package/src/workflows/create-skill/steps-c/step-01-load-brief.md +176 -0
  64. package/src/workflows/create-skill/steps-c/step-02-ecosystem-check.md +143 -0
  65. package/src/workflows/create-skill/steps-c/step-03-extract.md +184 -0
  66. package/src/workflows/create-skill/steps-c/step-04-enrich.md +152 -0
  67. package/src/workflows/create-skill/steps-c/step-05-compile.md +198 -0
  68. package/src/workflows/create-skill/steps-c/step-06-validate.md +162 -0
  69. package/src/workflows/create-skill/steps-c/step-07-generate-artifacts.md +165 -0
  70. package/src/workflows/create-skill/steps-c/step-08-report.md +160 -0
  71. package/src/workflows/create-skill/validation-report.md +189 -0
  72. package/src/workflows/create-skill/workflow-plan-create-skill.md +491 -0
  73. package/src/workflows/create-skill/workflow.md +52 -0
  74. package/src/workflows/create-stack-skill/data/integration-patterns.md +61 -0
  75. package/src/workflows/create-stack-skill/data/manifest-patterns.md +35 -0
  76. package/src/workflows/create-stack-skill/data/stack-skill-template.md +110 -0
  77. package/src/workflows/create-stack-skill/steps-c/step-01-init.md +142 -0
  78. package/src/workflows/create-stack-skill/steps-c/step-02-detect-manifests.md +145 -0
  79. package/src/workflows/create-stack-skill/steps-c/step-03-rank-and-confirm.md +161 -0
  80. package/src/workflows/create-stack-skill/steps-c/step-04-parallel-extract.md +155 -0
  81. package/src/workflows/create-stack-skill/steps-c/step-05-detect-integrations.md +154 -0
  82. package/src/workflows/create-stack-skill/steps-c/step-06-compile-stack.md +160 -0
  83. package/src/workflows/create-stack-skill/steps-c/step-07-generate-output.md +202 -0
  84. package/src/workflows/create-stack-skill/steps-c/step-08-validate.md +193 -0
  85. package/src/workflows/create-stack-skill/steps-c/step-09-report.md +137 -0
  86. package/src/workflows/create-stack-skill/validation-report.md +401 -0
  87. package/src/workflows/create-stack-skill/workflow-plan-create-stack-skill.md +481 -0
  88. package/src/workflows/create-stack-skill/workflow.md +59 -0
  89. package/src/workflows/export-skill/data/managed-section-format.md +70 -0
  90. package/src/workflows/export-skill/data/snippet-format.md +32 -0
  91. package/src/workflows/export-skill/steps-c/step-01-load-skill.md +184 -0
  92. package/src/workflows/export-skill/steps-c/step-02-package.md +153 -0
  93. package/src/workflows/export-skill/steps-c/step-03-generate-snippet.md +166 -0
  94. package/src/workflows/export-skill/steps-c/step-04-update-context.md +222 -0
  95. package/src/workflows/export-skill/steps-c/step-05-token-report.md +126 -0
  96. package/src/workflows/export-skill/steps-c/step-06-summary.md +167 -0
  97. package/src/workflows/export-skill/validation-report.md +263 -0
  98. package/src/workflows/export-skill/workflow-plan-export-skill.md +369 -0
  99. package/src/workflows/export-skill/workflow.md +56 -0
  100. package/src/workflows/quick-skill/data/registry-resolution.md +91 -0
  101. package/src/workflows/quick-skill/data/skill-template.md +66 -0
  102. package/src/workflows/quick-skill/steps-c/step-01-resolve-target.md +165 -0
  103. package/src/workflows/quick-skill/steps-c/step-02-ecosystem-check.md +143 -0
  104. package/src/workflows/quick-skill/steps-c/step-03-quick-extract.md +177 -0
  105. package/src/workflows/quick-skill/steps-c/step-04-compile.md +180 -0
  106. package/src/workflows/quick-skill/steps-c/step-05-validate.md +150 -0
  107. package/src/workflows/quick-skill/steps-c/step-06-write.md +160 -0
  108. package/src/workflows/quick-skill/validation-report.md +543 -0
  109. package/src/workflows/quick-skill/workflow-plan-quick-skill.md +405 -0
  110. package/src/workflows/quick-skill/workflow.md +56 -0
  111. package/src/workflows/setup-forge/data/tier-rules.md +50 -0
  112. package/src/workflows/setup-forge/steps-c/step-01-detect-and-tier.md +140 -0
  113. package/src/workflows/setup-forge/steps-c/step-02-write-config.md +141 -0
  114. package/src/workflows/setup-forge/steps-c/step-03-auto-index.md +116 -0
  115. package/src/workflows/setup-forge/steps-c/step-04-report.md +131 -0
  116. package/src/workflows/setup-forge/validation-report.md +504 -0
  117. package/src/workflows/setup-forge/workflow-plan-setup-forge.md +428 -0
  118. package/src/workflows/setup-forge/workflow.md +49 -0
  119. package/src/workflows/test-skill/data/output-section-formats.md +96 -0
  120. package/src/workflows/test-skill/data/scoring-rules.md +74 -0
  121. package/src/workflows/test-skill/steps-c/step-01-init.md +185 -0
  122. package/src/workflows/test-skill/steps-c/step-02-detect-mode.md +162 -0
  123. package/src/workflows/test-skill/steps-c/step-03-coverage-check.md +222 -0
  124. package/src/workflows/test-skill/steps-c/step-04-coherence-check.md +249 -0
  125. package/src/workflows/test-skill/steps-c/step-05-score.md +222 -0
  126. package/src/workflows/test-skill/steps-c/step-06-report.md +175 -0
  127. package/src/workflows/test-skill/templates/test-report-template.md +24 -0
  128. package/src/workflows/test-skill/validation-report.md +390 -0
  129. package/src/workflows/test-skill/workflow-plan-test-skill.md +288 -0
  130. package/src/workflows/test-skill/workflow.md +57 -0
  131. package/src/workflows/update-skill/data/manual-section-rules.md +44 -0
  132. package/src/workflows/update-skill/data/merge-conflict-rules.md +62 -0
  133. package/src/workflows/update-skill/steps-c/step-01-init.md +208 -0
  134. package/src/workflows/update-skill/steps-c/step-02-detect-changes.md +184 -0
  135. package/src/workflows/update-skill/steps-c/step-03-re-extract.md +187 -0
  136. package/src/workflows/update-skill/steps-c/step-04-merge.md +230 -0
  137. package/src/workflows/update-skill/steps-c/step-05-validate.md +187 -0
  138. package/src/workflows/update-skill/steps-c/step-06-write.md +204 -0
  139. package/src/workflows/update-skill/steps-c/step-07-report.md +201 -0
  140. package/src/workflows/update-skill/validation-report.md +559 -0
  141. package/src/workflows/update-skill/workflow-plan-update-skill.md +441 -0
  142. package/src/workflows/update-skill/workflow.md +56 -0
  143. package/tools/cli/commands/install.js +33 -0
  144. package/tools/cli/commands/status.js +195 -0
  145. package/tools/cli/commands/uninstall.js +226 -0
  146. package/tools/cli/commands/update.js +63 -0
  147. package/tools/cli/lib/compiler.js +306 -0
  148. package/tools/cli/lib/ide-commands.js +244 -0
  149. package/tools/cli/lib/installer.js +307 -0
  150. package/tools/cli/lib/manifest.js +109 -0
  151. package/tools/cli/lib/ui.js +277 -0
  152. package/tools/cli/lib/version-check.js +86 -0
  153. package/tools/cli/skf-cli.js +45 -0
  154. package/tools/skf-npx-wrapper.js +36 -0
@@ -0,0 +1,144 @@
1
+ ---
2
+ title: Examples
3
+ description: Real-world scenarios, tips, and troubleshooting for Skill Forge
4
+ ---
5
+
6
+ # Examples & Use Cases
7
+
8
+ This section provides practical examples for using SKF: Skill Forge.
9
+
10
+ ---
11
+
12
+ ## Example Workflows
13
+
14
+ ### Quick Skill — 47 Seconds
15
+
16
+ Developer adds [cognee](https://github.com/topoteretes/cognee) to a Python project for AI memory management. Agent keeps hallucinating method signatures and config options.
17
+
18
+ ```
19
+ @Ferris QS https://github.com/topoteretes/cognee
20
+ ```
21
+
22
+ Ferris reads the repository, extracts the public API via source reading, validates against spec. Skill appears in `skills/cognee/`. Agent stops hallucinating. Forty-seven seconds. Done.
23
+
24
+ ### Brownfield Platform — 8 Minutes
25
+
26
+ Alex's team adopts BMAD for 10 microservices (TypeScript, Go, Rust).
27
+
28
+ ```
29
+ @Ferris SF # Setup — Deep mode detected
30
+ @Ferris AN # Analyze — 10 services mapped
31
+ @Ferris CS --batch # Create — batch generation
32
+ ```
33
+
34
+ 10 individual skills + 1 platform stack skill. BMM architect navigates cross-service flows with verified knowledge.
35
+
36
+ ### Release Prep — Trust Builder
37
+
38
+ Sarah prepares v3.0.0 with breaking changes.
39
+
40
+ ```
41
+ @Ferris AS # Audit — finds 3 renames, 1 removal, 1 addition
42
+ @Ferris US # Update — preserves [MANUAL] sections, adds annotations
43
+ @Ferris TS # Test — verify completeness
44
+ @Ferris EX # Export — package for npm release
45
+ ```
46
+
47
+ Ships with npm release. Consumers upgrade — their agents use the correct function names. Zero hallucination tickets.
48
+
49
+ ### Stack Skill — Integration Intelligence
50
+
51
+ Armel's full-stack project: Next.js + Serwist + SpacetimeDB + better-auth.
52
+
53
+ ```
54
+ @Ferris SS
55
+ ```
56
+
57
+ Ferris detects 8 significant dependencies, finds 5 co-import integration points. Generates a consolidated stack skill. The agent now knows: "When you modify the auth flow, update the Serwist cache exclusion at `src/sw.ts:L23`." Integration intelligence no other tool provides.
58
+
59
+ ---
60
+
61
+ ## Common Scenarios
62
+
63
+ ### Scenario A: Greenfield + BMM Integration
64
+
65
+ BMAD user starts a new project. BMM architect suggests skill generation after retrospective.
66
+
67
+ ```
68
+ @Ferris BS # Brief — scope the skill
69
+ @Ferris CS # Create — compile from brief
70
+ @Ferris TS # Test — verify completeness
71
+ @Ferris EX # Export — inject into CLAUDE.md
72
+ ```
73
+
74
+ Skills accumulate over sprints. Agent gets smarter every iteration.
75
+
76
+ ### Scenario B: Multi-Repo Platform
77
+
78
+ Alex needs cross-service knowledge for 10 microservices.
79
+
80
+ One forge project, multiple QMD collections, hub-and-spoke skills with integration patterns.
81
+
82
+ ### Scenario C: External Dependency
83
+
84
+ Developer needs skills for a library that doesn't have official skills.
85
+
86
+ ```
87
+ @Ferris QS better-auth
88
+ ```
89
+
90
+ Checks ecosystem first. If no official skill exists: generates from source. `source_authority: community`.
91
+
92
+ ### Scenario D: Docs-Only (SaaS/Closed Source)
93
+
94
+ No source code available — only documentation.
95
+
96
+ Generate from docs + QMD-indexed content. T2/T3 confidence only. `source_authority: community`.
97
+
98
+ ---
99
+
100
+ ## Tips & Tricks
101
+
102
+ ### Progressive Capability
103
+
104
+ Start with Quick mode (no setup required), upgrade to Forge (install ast-grep), then Deep (install QMD). Each tier builds on the previous — you never lose capability.
105
+
106
+ ### Batch Operations
107
+
108
+ Use `--batch` with `create-skill` and `test-skill` to process multiple skills at once. Progress is checkpointed — use `--continue` to resume if interrupted.
109
+
110
+ ### Stack Skills + Individual Skills
111
+
112
+ Stack skills focus on integration patterns. Individual skills focus on API surface. Use both together for maximum coverage.
113
+
114
+ ### The Loop
115
+
116
+ After each sprint's refactor, run `@Ferris US` to regenerate changed components. Export updates CLAUDE.md automatically. Skill generation becomes routine — like running tests.
117
+
118
+ ---
119
+
120
+ ## Troubleshooting
121
+
122
+ ### Common Issues
123
+
124
+ **"Forge halted: ast-grep not found"**
125
+ Install ast-grep to unlock Forge mode: <https://ast-grep.github.io>
126
+
127
+ **"No brief found"**
128
+ Run `@Ferris BS` first to create a skill brief, or use `@Ferris QS` for brief-less generation.
129
+
130
+ **"Ecosystem check: official skill exists"**
131
+ An official skill already exists for this package. Consider installing it with `npx skills add` instead of generating your own.
132
+
133
+ **Quick mode skills have lower confidence**
134
+ Quick mode reads source without AST analysis. Install ast-grep to upgrade to Forge mode for structural truth (T1 confidence).
135
+
136
+ ---
137
+
138
+ ## Getting More Help
139
+
140
+ - Run `/bmad-help` — analyzes your current state and suggests what to do next
141
+ (e.g. `/bmad-help my batch creation failed halfway, how do I resume?`)
142
+ - Run `@Ferris SF` to check your current tier and tool availability
143
+ - Review `forge-config.yaml` for runtime configuration
144
+ - Check module configuration in your BMAD settings
@@ -0,0 +1,198 @@
1
+ ---
2
+ title: Getting Started
3
+ description: Installation, prerequisites, first steps, and common use cases for Skill Forge
4
+ ---
5
+
6
+ # Getting Started with SKF: Skill Forge
7
+
8
+ Welcome to Skill Forge! This guide will help you get up and running.
9
+
10
+ ---
11
+
12
+ ## What This Module Does
13
+
14
+ Skill Forge is an automated skill compiler for the AI agent ecosystem. It transforms code repositories, documentation websites, and developer discourse into agentskills.io-compliant, version-pinned, provenance-backed agent skills. Every instruction traces to actual code — zero hallucination tolerance.
15
+
16
+ ---
17
+
18
+ ## Installation
19
+
20
+ There are three ways to install SKF, depending on your setup.
21
+
22
+ ### Standalone (recommended for trying SKF)
23
+
24
+ ```bash
25
+ npx skill-forge install
26
+ ```
27
+
28
+ Or equivalently: `npx bmad-module-skill-forge install`
29
+
30
+ Installs SKF on its own. You'll be prompted for project name, output folders, and which IDEs to configure. The installer generates IDE-specific command files (e.g. `.claude/commands/`, `.cursor/commands/`) so workflows appear in your IDE's command palette.
31
+
32
+ ### As a custom module during BMad Method installation
33
+
34
+ ```bash
35
+ npx bmad-method install
36
+ ```
37
+
38
+ When prompted **"Add custom modules from your computer?"**, select Yes and provide the path to the SKF `src/` folder (clone this repo first):
39
+
40
+ ```
41
+ Path to custom module folder: /path/to/bmad-module-skill-forge/src/
42
+ ```
43
+
44
+ This installs BMad core + SKF together with full IDE integration, manifests, and help catalog. Best when you want the complete BMad development workflow.
45
+
46
+ ### Add SKF to an existing BMad project
47
+
48
+ If you already have BMad installed, you can add SKF afterward by running the standalone installer in the same directory:
49
+
50
+ ```bash
51
+ npx skill-forge install
52
+ ```
53
+
54
+ The installer detects the existing `_bmad/` directory and installs SKF alongside your current modules.
55
+
56
+ ---
57
+
58
+ ## Prerequisites
59
+
60
+ | Tool | Required For | Install |
61
+ |------------------------------------------------------------------------|--------------------|-----------------------------|
62
+ | `gh` (GitHub CLI) | All modes | <https://cli.github.com> |
63
+ | `ast-grep` (CLI tool for code structural search, lint, and rewriting) | Forge + Deep modes | <https://ast-grep.github.io> |
64
+ | `qmd` (local hybrid search engine for markdown) | Deep mode | <https://github.com/tobi/qmd> |
65
+
66
+ Don't worry if you don't have all tools — SKF detects what's available and sets your tier automatically.
67
+
68
+ ---
69
+
70
+ ## First Steps
71
+
72
+ ### 1. Setup Your Forge
73
+
74
+ ```
75
+ @Ferris SF
76
+ ```
77
+
78
+ This detects your tools, sets your capability tier, and initializes the forge environment. You only need to do this once per project.
79
+
80
+ ### 2. Generate Your First Skill
81
+
82
+ **Fastest path (Quick Skill):**
83
+ ```
84
+ @Ferris QS https://github.com/bmad-code-org/BMAD-METHOD
85
+ ```
86
+
87
+ Ferris reads the repository, extracts the public API, and generates a skill in under a minute.
88
+
89
+ **Full quality path:**
90
+ ```
91
+ @Ferris BS # Brief — scope and design the skill
92
+ @Ferris CS # Create — compile from the brief
93
+ @Ferris TS # Test — verify completeness
94
+ @Ferris EX # Export — package for distribution
95
+ ```
96
+
97
+ ### 3. Stack Skill (for full projects)
98
+
99
+ ```
100
+ @Ferris SS
101
+ ```
102
+
103
+ Analyzes your project's dependencies and generates a consolidated stack skill with integration patterns.
104
+
105
+ ---
106
+
107
+ ## Common Use Cases
108
+
109
+ ### My agent keeps hallucinating API calls
110
+
111
+ Your agent invents function signatures that don't exist. Generate a verified skill so it works from structural truth instead of guessing.
112
+
113
+ ```
114
+ @Ferris QS https://github.com/org/library
115
+ ```
116
+
117
+ The skill pins every function to its actual source location. Hallucinations stop.
118
+
119
+ ### I'm adopting a new library and need my agent to use it correctly
120
+
121
+ You added a dependency but your agent doesn't know its API yet. Quick Skill resolves package names across npm, PyPI, and crates.io.
122
+
123
+ ```
124
+ @Ferris QS cognee
125
+ ```
126
+
127
+ Ferris resolves the package to its GitHub repo, extracts the public API, and generates a skill your agent can reference immediately.
128
+
129
+ ### I want my agent to understand my entire project stack
130
+
131
+ Individual skills cover single libraries. Stack Skill maps how your dependencies interact — shared types, co-import patterns, integration points.
132
+
133
+ ```
134
+ @Ferris SS
135
+ ```
136
+
137
+ Ferris detects your manifests, ranks dependencies by significance, and generates a consolidated skill with cross-library integration patterns.
138
+
139
+ ### I'm onboarding a large existing codebase
140
+
141
+ A brownfield repo with dozens of modules. You need to know what's worth skilling before you start.
142
+
143
+ ```
144
+ @Ferris AN
145
+ ```
146
+
147
+ Analyze Source scans the project, identifies skillable units, maps exports, and generates recommended briefs you can batch-create with `@Ferris CS --batch`.
148
+
149
+ ### I want the highest accuracy possible
150
+
151
+ Quick mode reads source files. Forge mode adds AST parsing for structural truth. Deep mode goes further — QMD indexes your project's markdown (docs, changelogs, issues, migration guides) into searchable collections, then uses BM25 keyword search, vector semantic search, and LLM-powered re-ranking to surface context no other tool can find.
152
+
153
+ ```
154
+ @Ferris SF # Setup detects your tools and sets tier automatically
155
+ ```
156
+
157
+ If `ast-grep` and `qmd` are available, Ferris activates Deep mode. Every skill gets AST-verified signatures (T1) enriched with deep knowledge search (T2) — deprecation warnings, breaking change history, common pitfalls surfaced by hybrid search across your indexed documentation.
158
+
159
+ ### I maintain an OSS library and want official skills
160
+
161
+ You want maximum quality with full provenance for distribution. Use the full pipeline with Deep mode for the richest output.
162
+
163
+ ```
164
+ @Ferris BS # Scope and design the skill
165
+ @Ferris CS # Compile — AST extraction + QMD enrichment (Deep)
166
+ @Ferris TS # Verify completeness before publishing
167
+ @Ferris EX # Package for distribution
168
+ ```
169
+
170
+ Export with `source_authority: official`. Consumers get verified skills that update with each release.
171
+
172
+ ### A dependency shipped breaking changes
173
+
174
+ Your existing skill is now out of date. Audit detects the drift, Update regenerates while preserving your manual additions.
175
+
176
+ ```
177
+ @Ferris AS # Find what changed
178
+ @Ferris US # Regenerate — [MANUAL] sections survive
179
+ @Ferris TS # Verify the update
180
+ ```
181
+
182
+ ---
183
+
184
+ ## What's Next?
185
+
186
+ - Check out the [Agents Reference](../agents.md) to learn about Ferris
187
+ - Browse the [Workflows Reference](../workflows.md) to see all available commands
188
+ - See [Examples](../examples.md) for real-world usage scenarios
189
+
190
+ ---
191
+
192
+ ## Need Help?
193
+
194
+ If you run into issues:
195
+ 1. Run `/bmad-help` — analyzes your current state and suggests what to do next
196
+ (e.g. `/bmad-help my quick skill has low confidence scores, how do I improve them?`)
197
+ 2. Run `@Ferris SF` to check your tool availability and tier
198
+ 3. Check `forge-config.yaml` for your current configuration
package/docs/index.md ADDED
@@ -0,0 +1,75 @@
1
+ ---
2
+ title: Skill Forge (SKF)
3
+ description: AST-verified, provenance-backed agent skills from code repositories, documentation, and developer discourse
4
+ template: splash
5
+ hero:
6
+ title: Skill Forge (SKF)
7
+ tagline: AST-verified, provenance-backed agent skills from code repositories, documentation, and developer discourse
8
+ actions:
9
+ - text: Getting Started
10
+ link: ./getting-started/
11
+ icon: right-arrow
12
+ variant: primary
13
+ - text: View on GitHub
14
+ link: https://github.com/armelhbobdad/bmad-module-skill-forge
15
+ icon: external
16
+ ---
17
+
18
+ ## What is Skill Forge?
19
+
20
+ Skill Forge is an automated skill compiler for the AI agent ecosystem. It transforms code repositories, documentation, and developer discourse into [agentskills.io](https://agentskills.io)-compliant, version-pinned, provenance-backed agent skills. Every instruction traces to verifiable sources — zero hallucination tolerance.
21
+
22
+ - **AST-Verified**: Structural truth via ast-grep — no guessing, no hallucination.
23
+ - **Provenance-Backed**: Every claim traces to source code with file and line references.
24
+ - **Progressive Tiers**: Quick (no setup) → Forge (ast-grep) → Deep (QMD knowledge).
25
+ - **Ecosystem-First**: Checks for official skills before generating community ones.
26
+
27
+ ## Quick Install
28
+
29
+ **Standalone:**
30
+
31
+ ```bash
32
+ npx skill-forge install
33
+ ```
34
+
35
+ **Or as a custom module with BMad Method** (for the full development workflow):
36
+
37
+ ```bash
38
+ npx bmad-method install # select "Add custom modules" and point to src/
39
+ ```
40
+
41
+ Then interact with the forge agent:
42
+
43
+ ```
44
+ @Ferris SF # Setup your forge environment
45
+ @Ferris QS # Quick Skill — generate in under a minute
46
+ ```
47
+
48
+ See the [Getting Started](./getting-started.md) guide for all installation methods.
49
+
50
+ ## Core Workflows
51
+
52
+ | Workflow | Trigger | Purpose |
53
+ |----------|---------|---------|
54
+ | [Setup Forge](/workflows/#setup-forge-sf) | SF | Initialize forge, detect tools, set tier |
55
+ | [Brief Skill](/workflows/#brief-skill-bs) | BS | Scope and design a skill |
56
+ | [Create Skill](/workflows/#create-skill-cs) | CS | Compile a skill from a brief |
57
+ | [Quick Skill](/workflows/#quick-skill-qs) | QS | Fast skill, no brief needed |
58
+ | [Stack Skill](/workflows/#stack-skill-ss) | SS | Consolidated project stack skill |
59
+ | [Update Skill](/workflows/#update-skill-us) | US | Regenerate after source changes |
60
+ | [Audit Skill](/workflows/#audit-skill-as) | AS | Drift detection |
61
+ | [Test Skill](/workflows/#test-skill-ts) | TS | Verify completeness |
62
+ | [Export Skill](/workflows/#export-skill-ex) | EX | Package for distribution |
63
+ | [Analyze Source](/workflows/#analyze-source-an) | AN | Discover what to skill |
64
+
65
+ ## Documentation
66
+
67
+ - **[Getting Started](./getting-started.md)** — Installation, prerequisites, first steps
68
+ - **[Architecture](./architecture.md)** — Output format, confidence model, tiers, tool ecosystem
69
+ - **[Agents](./agents.md)** — Ferris agent: modes, capabilities, communication style
70
+ - **[Workflows](./workflows.md)** — All 10 workflows with commands and connection diagram
71
+ - **[Examples](./examples.md)** — Real-world scenarios, tips, and troubleshooting
72
+
73
+ ## Support
74
+
75
+ - **Issues**: [GitHub Issues](https://github.com/armelhbobdad/bmad-module-skill-forge/issues)
@@ -0,0 +1,190 @@
1
+ ---
2
+ title: Workflows
3
+ description: All 10 SKF workflows with commands, steps, and connection diagram
4
+ ---
5
+
6
+ # Workflows Reference
7
+
8
+ SKF includes 10 workflows organized by purpose:
9
+
10
+ ---
11
+
12
+ ## Core Workflows
13
+
14
+ ### Setup Forge (SF)
15
+
16
+ **Command:** `@Ferris SF`
17
+
18
+ **Purpose:** Initialize forge environment, detect tools, set capability tier, auto-index project.
19
+
20
+ **When to Use:** First time using SKF in a project. Run once per project.
21
+
22
+ **Key Steps:** Detect tools → Determine tier → Create forge-config.yaml → Auto-index (Deep)
23
+
24
+ **Agent:** Ferris (Architect mode)
25
+
26
+ ---
27
+
28
+ ### Brief Skill (BS)
29
+
30
+ **Command:** `@Ferris BS`
31
+
32
+ **Purpose:** Scope and design a skill through guided discovery.
33
+
34
+ **When to Use:** Before `Create Skill` when you want maximum control over what gets compiled.
35
+
36
+ **Key Steps:** Gather intent → Analyze target → Define scope → Write skill-brief.yaml
37
+
38
+ **Agent:** Ferris (Architect mode)
39
+
40
+ ---
41
+
42
+ ### Create Skill (CS)
43
+
44
+ **Command:** `@Ferris CS`
45
+
46
+ **Purpose:** Compile a skill from a brief. Supports `--batch` for multiple briefs.
47
+
48
+ **When to Use:** After Brief Skill, or with an existing skill-brief.yaml.
49
+
50
+ **Key Steps:** Load brief → Ecosystem check → AST extract → QMD enrich → Compile → Validate → Generate
51
+
52
+ **Agent:** Ferris (Architect mode)
53
+
54
+ ---
55
+
56
+ ### Update Skill (US)
57
+
58
+ **Command:** `@Ferris US`
59
+
60
+ **Purpose:** Smart regeneration preserving `[MANUAL]` sections. Detects individual vs stack internally.
61
+
62
+ **When to Use:** After source code changes when an existing skill needs updating.
63
+
64
+ **Key Steps:** Load existing → Detect changes → Re-extract → Merge (preserve MANUAL) → Validate → Write
65
+
66
+ **Agent:** Ferris (Surgeon mode)
67
+
68
+ ---
69
+
70
+ ## Feature Workflows
71
+
72
+ ### Quick Skill (QS)
73
+
74
+ **Command:** `@Ferris QS <package-or-url>`
75
+
76
+ **Purpose:** Brief-less fast skill with package-to-repo resolution.
77
+
78
+ **When to Use:** When you need a skill quickly — no brief needed. Accepts package names or GitHub URLs.
79
+
80
+ **Key Steps:** Resolve target → Ecosystem check → Quick extract → Compile → Validate → Write
81
+
82
+ **Agent:** Ferris (Architect mode)
83
+
84
+ ---
85
+
86
+ ### Stack Skill (SS)
87
+
88
+ **Command:** `@Ferris SS`
89
+
90
+ **Purpose:** Consolidated project stack skill with integration patterns.
91
+
92
+ **When to Use:** When you want your agent to understand your entire project stack — not just individual libraries.
93
+
94
+ **Key Steps:** Detect manifests → Rank dependencies → Scope confirmation → Parallel extract → Detect integrations → Compile stack → Generate references
95
+
96
+ **Agent:** Ferris (Architect mode)
97
+
98
+ ---
99
+
100
+ ### Analyze Source (AN)
101
+
102
+ **Command:** `@Ferris AN`
103
+
104
+ **Purpose:** Decomposition engine — discover what to skill, recommend stack skill.
105
+
106
+ **When to Use:** Brownfield onboarding of large repos or multi-service projects.
107
+
108
+ **Key Steps:** Scan project → Identify units → Map exports → Detect integrations → Recommend → Generate briefs
109
+
110
+ **Agent:** Ferris (Architect mode)
111
+
112
+ ---
113
+
114
+ ### Audit Skill (AS)
115
+
116
+ **Command:** `@Ferris AS`
117
+
118
+ **Purpose:** Drift detection between skill and current source.
119
+
120
+ **When to Use:** To check if a skill has fallen out of date with its source code.
121
+
122
+ **Key Steps:** Load skill → Re-index source → Structural diff → Semantic diff (Deep) → Classify severity → Report
123
+
124
+ **Agent:** Ferris (Audit mode)
125
+
126
+ ---
127
+
128
+ ### Test Skill (TS)
129
+
130
+ **Command:** `@Ferris TS`
131
+
132
+ **Purpose:** Cognitive completeness verification. Quality gate before export.
133
+
134
+ **When to Use:** After creating or updating a skill, before exporting.
135
+
136
+ **Key Steps:** Load skill → Detect mode → Coverage check → Coherence check → Score → Gap report
137
+
138
+ **Agent:** Ferris (Audit mode)
139
+
140
+ ---
141
+
142
+ ## Utility Workflows
143
+
144
+ ### Export Skill (EX)
145
+
146
+ **Command:** `@Ferris EX`
147
+
148
+ **Purpose:** Package for distribution + platform-aware context injection into CLAUDE.md/AGENTS.md.
149
+
150
+ **When to Use:** When a skill is ready for distribution or CLAUDE.md integration.
151
+
152
+ **Key Steps:** Load skill → Package → Generate snippet → Update CLAUDE.md → Token report → Summary
153
+
154
+ **Agent:** Ferris (Delivery mode)
155
+
156
+ ---
157
+
158
+ ## Workflow Connections
159
+
160
+ ```
161
+ setup-forge (one-time)
162
+
163
+ ┌──────────────┼──────────────┐
164
+ │ │ │
165
+ analyze-source quick-skill create-stack-skill
166
+ │ │ │
167
+ brief-skill │ │
168
+ │ │ │
169
+ create-skill │ │
170
+ │ │ │
171
+ └──────┬───────┘──────────────┘
172
+
173
+ test-skill (quality gate)
174
+
175
+ ┌──────┼──────┐
176
+ │ │
177
+ export-skill audit-skill
178
+
179
+ update-skill (loops back to test)
180
+ ```
181
+
182
+ ---
183
+
184
+ ## Build Priority
185
+
186
+ | Phase | Workflows | Notes |
187
+ |-------|-----------|-------|
188
+ | 1a (Core Engine) | setup-forge, create-skill, test-skill, export-skill | Must build first |
189
+ | 1b (Entry Points) | quick-skill, brief-skill, create-stack-skill | Complete v1.0 |
190
+ | 2 (Lifecycle) | audit-skill, update-skill, analyze-source | Post-launch |