skf-create-stack-skill
Consolidated project stack skill with integration patterns — code-mode (analyzes manifests) or compose-mode (synthesizes from existing skills + architecture doc). Use when the user requests to "create a stack skill", "forge a stack", or "stack this project".
Install
npx skills add https://github.com/armelhbobdad/bmad-module-skill-forge/tree/main/src/skf-create-stack-skill
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install armelhbobdad-bmad-module-skill-forge@llmmart
git clone https://github.com/armelhbobdad/bmad-module-skill-forge.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole armelhbobdad/bmad-module-skill-forge collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Create Stack Skill
Overview
Produces a consolidated stack skill documenting how libraries connect. Code-mode analyzes dependency manifests and co-import patterns from actual source code. Compose-mode synthesizes from pre-generated individual skills and architecture documents when no codebase exists yet. Every finding must trace to its source with file:line citations.
Conventions
- Bare paths (e.g.
references/<name>.md) resolve from the skill root, inside areferences/file too: only a stage's frontmatternextStepFileandcomposeNextStepFilename a file beside it. - Module-level path exception: bare paths beginning with
knowledge/orshared/resolve from the SKF module root ({project-root}/_bmad/skf/installed,src/in dev), not the skill root; e.g.knowledge/tool-resolution.md,knowledge/version-paths.mdandshared/references/feasibility-report-schema.md. - Sibling skills: a path that names another SKF skill's folder (
skf-<name>/...) resolves from the SKF module root, and that skill must be installed with this one. {skill-root}resolves to this skill's installed directory (wherecustomize.tomllives, if present).{project-root}-prefixed paths resolve from the project working directory.{skill-name}resolves to the skill directory's basename.
Role
You are a dependency analyst and integration architect; the user brings their project knowledge and scope preferences.
Workflow Rules
These rules apply to every step in this workflow:
- Only load one step file at a time — never preload future steps
- If any instruction references a subprocess or tool you lack, achieve the outcome in your main context thread, with two exceptions: never decide by hand whether SKF generated a folder (the ownership check), and never work out by hand what a shared helper computes where its step names a
helper-missingHALT: that helper resolving to no path stops the run with exit 3helper-missing(references/invocation-contract.mdlists every such halt). Where a step says what to do without its helper (an advisory check, a default value), do as it says - Run every subagent in the foreground, passing
run_in_background: falseon every Agent call (Claude Code runs a subagent in the background when the flag is left out), with parallel ones as several such calls in one message, and wait for every long-running command to exit before the next instruction; in a headless run, never end a turn while either still runs, since underclaude -pa run stops when its turn ends. - Never write into a skill folder SKF did not generate: step 1 runs the inventory's write check before any prior metadata is read, step 7 again before staging
- Always communicate in
{communication_language} - If
{headless_mode}is true, auto-proceed through confirmation gates with their default action, and record each auto-decision in the run sink the moment the gate takes it, with therecord --decisioncommand the gate shows - Every HARD HALT names its exit code,
halt_reasonand phase, and prints its envelope through the shared emitter with the command its step file shows (theinit:emitterhalt, with no emitter, only displays its message); never type anSKF_STACK_RESULT_JSONline
Workflow state contract
Every step that emits a warning appends an entry to workflow_warnings[], the one accumulator for the whole workflow, and records it in the run sink at once, as the step shows. An entry has the shape {step: "step-NN", severity: "info|warn|error", code: "<short-slug>", message: "<human text>", context: {<optional fields>}}, its context fields folded into the message. The sink, {run_dir}/warnings.jsonl, is the list: step 7 §8b lists it in evidence-report.md, step 9 §1 renders it, and the result envelope carries it.
Resume only at the review gate: the run's state lives in {run_dir}, the run folder step 1 creates under {project-root}/_bmad-output/.skf-run/, a step 1 binding lost to compaction is re-read from its run.json, and an interrupted run starts again from step 1 unless step 1 resumes an interactive one at step 6's review gate.
Stages
| # | Step | File | Auto-proceed |
|---|---|---|---|
| 1 | Initialize & Mode Detection | references/init.md | Conditional |
| 2 | Detect Manifests | references/detect-manifests.md; compose: references/compose-skills.md | Conditional (no manifest found) |
| 3 | Rank & Confirm Libraries | references/rank-and-confirm.md; compose: references/compose-scope.md first | No (confirm) |
| 4 | Parallel Extract | references/parallel-extract.md; compose: references/compose-extract.md | Yes |
| 5 | Detect Integrations | references/detect-integrations.md; compose: references/compose-pairs.md first | Yes |
| 6 | Compile Stack | references/compile-stack.md | No (review) |
| 7 | Generate Output | references/generate-output.md | Yes |
| 8 | Validate | references/validate.md | Yes |
| 9 | Report | references/report.md | Yes |
| 10 | Workflow Health Check | references/health-check.md | Yes |
Invocation Contract
references/invocation-contract.md holds the inputs, gates and outputs, the exit code and halt_reason of every HARD HALT, and the SKF_STACK_RESULT_JSON result envelope.
On Activation
Load config from
{project-root}/_bmad/skf/config.yamland resolve:project_name,output_folder,user_name,communication_language,document_output_language,skills_output_folder,forge_data_folder,sidecar_path
Resolve
{headless_mode}by the first rule that applies:falsewhen--headless=falseor--no-headlesswas passed, whatever the preferences say;truewhen--headlessor-Hwas passed without=false; otherwiseheadless_modefrom{sidecar_path}/preferences.yaml(trueorfalse); otherwisefalse.Resolve workflow customization. Bind
{resolveCustomizationHelper}←{project-root}/_bmad/skf/shared/scripts/skf-resolve-customization.py, else{project-root}/src/shared/scripts/skf-resolve-customization.py(the first that exists), and run:uv run {resolveCustomizationHelper} --skill {skill-root} --project-root {project-root} --key workflow --factsIt merges the bundled
{skill-root}/customize.tomlwith{project-root}/_bmad/custom/skf-create-stack-skill.toml(team overrides, committed) and.user.toml(personal overrides, gitignored). When it exits non-zero, prints no JSON or is missing, print one line,[activation/warn] customization_resolver_unavailable: <reason>(<reason>: its first stderr line,SKF helper skf-resolve-customization.py not foundwhen the script is missing,no JSONwhen it printed none). If the resolver cannot run, read{skill-root}/customize.tomlalone and use its bundled defaults: the{project-root}/_bmad/custom/overrides do not apply to this run. In that case keep the reason as{customization_resolver_unavailable}(unset when the resolver ran):references/init.mdrecords it as the run's first warning once its pre-flight has created{run_dir}.Bind these three as workflow-context variables, taking the default when the merged value is empty or absent:
{stackSkillTemplatePath}←workflow.stack_skill_template_path, elseassets/stack-skill-template.md(the SKILL.md, snippet and reference-file structures, less the linesskf-render-stack-metadata.pywrites; neverassets/metadata-contract.md){integrationPatternsPath}←workflow.integration_patterns_path, elsereferences/integration-patterns.md{onCompleteCommand}←workflow.on_complete, else empty (references/report.md§2c then runs no hook)
Run
workflow.activation_steps_prependnow and keepworkflow.persistent_factsas standing context (the bundled default loads everyproject-context.mdunder{project-root}, none in{project-root}/_bmad-output/.skf-run/; if the resolver ran,--factshas applied each!entry, which drops each earlier entry it names, and expanded each glob, so afile:entry names one file).Run each entry in
workflow.activation_steps_appendin order, then load, read the full file, and executereferences/init.mdto begin the workflow.
Files (bmad-module-skill-forge)
-
assets
-
metadata-contract.md 2.2 KB
Loading… -
provenance-map-schema.md 5.8 KB
Loading… -
stack-skill-template.md 6.9 KB
Loading…
-
-
references
-
compile-stack.md 10 KB
Loading… -
compose-extract.md 8.5 KB
Loading… -
compose-mode-rules.md 2.2 KB
Loading… -
compose-pairs.md 11.9 KB
Loading… -
compose-scope.md 5.6 KB
Loading… -
compose-skills.md 4.9 KB
Loading… -
detect-integrations.md 11.8 KB
Loading… -
detect-manifests.md 6.6 KB
Loading… -
generate-output.md 22.8 KB
Loading… -
health-check.md 867 B
Loading… -
init.md 20.7 KB
Loading… -
integration-patterns.md 1.5 KB
Loading… -
invocation-contract.md 6.9 KB
Loading… -
manifest-patterns.md 6.6 KB
Loading… -
parallel-extract.md 12.7 KB
Loading… -
rank-and-confirm.md 11.5 KB
Loading… -
report.md 9.7 KB
Loading… -
validate.md 13.4 KB
Loading…
-
-
customize.toml 5.5 KB
Loading… -
SKILL.md 8.4 KB
--- name: skf-create-stack-skill description: Consolidated project stack skill with integration patterns — code-mode (analyzes manifests) or compose-mode (synthesizes from existing skills + architecture doc). Use when the user requests to "create a stack skill", "forge a stack", or "stack this project". --- # Create Stack Skill ## Overview Produces a consolidated stack skill documenting how libraries connect. **Code-mode** analyzes dependency manifests and co-import patterns from actual source code. **Compose-mode** synthesizes from pre-generated individual skills and architecture documents when no codebase exists yet. Every finding must trace to its source with file:line citations. ## Conventions - Bare paths (e.g. `references/<name>.md`) resolve from the skill root, inside a `references/` file too: only a stage's frontmatter `nextStepFile` and `composeNextStepFile` name a file beside it. - **Module-level path exception:** bare paths beginning with `knowledge/` or `shared/` resolve from the SKF module root (`{project-root}/_bmad/skf/` installed, `src/` in dev), not the skill root; e.g. `knowledge/tool-resolution.md`, `knowledge/version-paths.md` and `shared/references/feasibility-report-schema.md`. - **Sibling skills:** a path that names another SKF skill's folder (`skf-<name>/...`) resolves from the SKF module root, and that skill must be installed with this one. - `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives, if present). - `{project-root}`-prefixed paths resolve from the project working directory. - `{skill-name}` resolves to the skill directory's basename. ## Role You are a dependency analyst and integration architect; the user brings their project knowledge and scope preferences. ## Workflow Rules These rules apply to every step in this workflow: - Only load one step file at a time — never preload future steps - If any instruction references a subprocess or tool you lack, achieve the outcome in your main context thread, with two exceptions: never decide by hand whether SKF generated a folder (the ownership check), and never work out by hand what a shared helper computes where its step names a `helper-missing` HALT: that helper resolving to no path stops the run with exit 3 `helper-missing` (`references/invocation-contract.md` lists every such halt). Where a step says what to do without its helper (an advisory check, a default value), do as it says - Run every subagent in the foreground, passing `run_in_background: false` on every Agent call (Claude Code runs a subagent in the background when the flag is left out), with parallel ones as several such calls in one message, and wait for every long-running command to exit before the next instruction; in a headless run, never end a turn while either still runs, since under `claude -p` a run stops when its turn ends. - Never write into a skill folder SKF did not generate: step 1 runs the inventory's write check before any prior metadata is read, step 7 again before staging - Always communicate in `{communication_language}` - If `{headless_mode}` is true, auto-proceed through confirmation gates with their default action, and record each auto-decision in the run sink the moment the gate takes it, with the `record --decision` command the gate shows - Every HARD HALT names its exit code, `halt_reason` and phase, and prints its envelope through the shared emitter with the command its step file shows (the `init:emitter` halt, with no emitter, only displays its message); never type an `SKF_STACK_RESULT_JSON` line ## Workflow state contract Every step that emits a warning appends an entry to `workflow_warnings[]`, the one accumulator for the whole workflow, and records it in the run sink at once, as the step shows. An entry has the shape `{step: "step-NN", severity: "info|warn|error", code: "<short-slug>", message: "<human text>", context: {<optional fields>}}`, its `context` fields folded into the message. The sink, `{run_dir}/warnings.jsonl`, is the list: step 7 §8b lists it in `evidence-report.md`, step 9 §1 renders it, and the result envelope carries it. **Resume only at the review gate:** the run's state lives in `{run_dir}`, the run folder step 1 creates under `{project-root}/_bmad-output/.skf-run/`, a step 1 binding lost to compaction is re-read from its `run.json`, and an interrupted run starts again from step 1 unless step 1 resumes an interactive one at step 6's review gate. ## Stages | # | Step | File | Auto-proceed | |---|------|------|--------------| | 1 | Initialize & Mode Detection | references/init.md | Conditional | | 2 | Detect Manifests | references/detect-manifests.md; compose: references/compose-skills.md | Conditional (no manifest found) | | 3 | Rank & Confirm Libraries | references/rank-and-confirm.md; compose: references/compose-scope.md first | No (confirm) | | 4 | Parallel Extract | references/parallel-extract.md; compose: references/compose-extract.md | Yes | | 5 | Detect Integrations | references/detect-integrations.md; compose: references/compose-pairs.md first | Yes | | 6 | Compile Stack | references/compile-stack.md | No (review) | | 7 | Generate Output | references/generate-output.md | Yes | | 8 | Validate | references/validate.md | Yes | | 9 | Report | references/report.md | Yes | | 10 | Workflow Health Check | references/health-check.md | Yes | ## Invocation Contract `references/invocation-contract.md` holds the inputs, gates and outputs, the exit code and `halt_reason` of every HARD HALT, and the `SKF_STACK_RESULT_JSON` result envelope. ## On Activation 1. Load config from `{project-root}/_bmad/skf/config.yaml` and resolve: - `project_name`, `output_folder`, `user_name`, `communication_language`, `document_output_language`, `skills_output_folder`, `forge_data_folder`, `sidecar_path` 2. **Resolve `{headless_mode}`** by the first rule that applies: `false` when `--headless=false` or `--no-headless` was passed, whatever the preferences say; `true` when `--headless` or `-H` was passed without `=false`; otherwise `headless_mode` from `{sidecar_path}/preferences.yaml` (`true` or `false`); otherwise `false`. 3. **Resolve workflow customization.** Bind `{resolveCustomizationHelper}` ← `{project-root}/_bmad/skf/shared/scripts/skf-resolve-customization.py`, else `{project-root}/src/shared/scripts/skf-resolve-customization.py` (the first that exists), and run: ```bash uv run {resolveCustomizationHelper} --skill {skill-root} --project-root {project-root} --key workflow --facts ``` It merges the bundled `{skill-root}/customize.toml` with `{project-root}/_bmad/custom/skf-create-stack-skill.toml` (team overrides, committed) and `.user.toml` (personal overrides, gitignored). When it exits non-zero, prints no JSON or is missing, print one line, `[activation/warn] customization_resolver_unavailable: <reason>` (`<reason>`: its first stderr line, `SKF helper skf-resolve-customization.py not found` when the script is missing, `no JSON` when it printed none). If the resolver cannot run, read `{skill-root}/customize.toml` alone and use its bundled defaults: the `{project-root}/_bmad/custom/` overrides do not apply to this run. In that case keep the reason as `{customization_resolver_unavailable}` (unset when the resolver ran): `references/init.md` records it as the run's first warning once its pre-flight has created `{run_dir}`. Bind these three as workflow-context variables, taking the default when the merged value is empty or absent: - `{stackSkillTemplatePath}` ← `workflow.stack_skill_template_path`, else `assets/stack-skill-template.md` (the SKILL.md, snippet and reference-file structures, less the lines `skf-render-stack-metadata.py` writes; never `assets/metadata-contract.md`) - `{integrationPatternsPath}` ← `workflow.integration_patterns_path`, else `references/integration-patterns.md` - `{onCompleteCommand}` ← `workflow.on_complete`, else empty (`references/report.md` §2c then runs no hook) Run `workflow.activation_steps_prepend` now and keep `workflow.persistent_facts` as standing context (the bundled default loads every `project-context.md` under `{project-root}`, none in `{project-root}/_bmad-output/.skf-run/`; if the resolver ran, `--facts` has applied each `!` entry, which drops each earlier entry it names, and expanded each glob, so a `file:` entry names one file). 4. Run each entry in `workflow.activation_steps_append` in order, then load, read the full file, and execute `references/init.md` to begin the workflow.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.