Claude Skill

skf-verify-stack

Pre-code stack feasibility verification against architecture and PRD documents. Use when the user requests to "verify a tech stack" or "verify stack."

LLM Mart · 0 points · 1 views 0 listing impressions 0 install-command copies
Download armelhbobdad-bmad-module-skill-forge-src_skf-verify-stack-484edd0.zip · 89 KB

Install

skills CLI npx skills add https://github.com/armelhbobdad/bmad-module-skill-forge/tree/main/src/skf-verify-stack
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install armelhbobdad-bmad-module-skill-forge@llmmart
Git 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

Verify Stack

Overview

Cross-references generated skills against architecture and PRD documents to produce a feasibility report with evidence-backed integration verdicts, coverage analysis, and requirements mapping. Read-only: it reads skills and input documents and writes only the feasibility report, its result files and a scratch run folder (see Workflow Rules).

Schema contract: This skill is the producer of the SKF shared feasibility report schema — every report conforms to it.

Conventions

  • Bare paths (e.g. references/<name>.md) resolve from the skill root, inside a references/ file too: only a stage's frontmatter nextStepFile names a file beside it.
  • references/ holds the workflow stages, chained by frontmatter nextStepFile; the rules file a stage loads (integrations.md loads integration-verification-rules.md); the halt reference the stages point to (exit-codes.md); and the caller contract (invocation-contract.md). scripts/ holds this skill's deterministic helpers and assets/ the report template.
  • {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.
  • 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. shared/references/output-contract-schema.md and shared/health-check.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.

Role

You are a stack feasibility analyst and integration verifier operating in Ferris Audit mode. You bring expertise in API surface analysis, cross-library compatibility assessment, and architecture validation, while the user brings their architecture vision and generated skills.

Workflow Rules

These rules apply to every step in this workflow:

  • Read-only — never modify skills, architecture docs, or PRD files
  • Every verdict must cite evidence from the generated skills
  • 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
  • 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.
  • Always communicate in {communication_language}
  • At any interactive prompt, the inputs cancel, exit, [X], q, or :q exit cleanly with exit code 6 (halt_reason: "user-cancelled")
  • If {headless_mode} is true, auto-proceed through confirmation gates with their default action and log each auto-decision; a gate that picks its default for the user (step 1's default of the newest earlier report) also records that decision in the run sink the moment it decides
  • Every helper a stage runs (a scripts/ file, or a shared helper from the stage's probe order) is required: if the probe order resolves to no path, or the helper cannot start, HALT (exit code 3, halt_reason: "resolution-failure") at the stage's phase, through the stage's halt envelope. Never recompute a helper's result by hand: the main-thread rule above covers subagent work, not helpers.
  • Every HARD HALT names its exit code, halt_reason and phase, and in headless mode prints its envelope through the shared emitter, with the command each stage file shows (references/exit-codes.md describes the envelope).
  • Stages 1 to 5 write only the timestamped report {outputFile}, and each write that fails halts (exit code 4, halt_reason: "write-failed"). Step 6 copies the report to {outputFileLatest} only after it passes the feasibility-report check, so a run that halts before then leaves the previous finished copy, the one consumers read, in place.
  • Run state lives in {run_dir}, not in context; step 6 deletes it, a HALT keeps it.

Stages

# Step File Auto-proceed
1 Initialize & Load Inputs references/init.md Conditional (asks only for inputs no flag gave, or whose path was not found)
2 Coverage Analysis references/coverage.md Yes
3 Integration Verification references/integrations.md Yes
4 Requirements Mapping references/requirements.md Yes
5 Synthesize Verdict references/synthesize.md Yes
6 Report references/report.md Yes
7 Workflow Health Check references/health-check.md Yes

Invocation Contract

references/invocation-contract.md holds the inputs, flags, gates, outputs and headless rules, and the SKF_VERIFY_STACK_RESULT_JSON result contract; references/exit-codes.md the exit codes.

On Activation

  1. Load config from {project-root}/_bmad/skf/config.yaml and resolve:

    • project_name, user_name, communication_language, document_output_language
    • skills_output_folder, forge_data_folder, sidecar_path
  2. Fix the run-scoped variables so no stage derives them again:

    • timestamp ← UTC YYYYMMDD-HHmmss captured at activation time
    • project_slug is bound by init.md before its §1, from the shared feasibility-report helper, which holds the one slug rule the consumers of this report also apply; never slugify project_name by hand
    • The two combine in init.md §4 into {outputFile} and {outputFileLatest} per the stage frontmatter template, and stay fixed for the whole run, so every later reference to either file resolves to the same path.
    • run_dir ← {project-root}/_bmad-output/.skf-run/skf-verify-stack-{timestamp}, the run folder init.md creates first
  3. Resolve {headless_mode}: true if --headless or -H was passed as an argument, or if headless_mode: true in {sidecar_path}/preferences.yaml. Default: false.

    Bind the inputs in every mode: {architecture_doc_path} ← the --architecture-doc value, {prd_path} ← --prd and {previous_report_path} ← --previous-report, each null when its flag is absent. init.md §1 asks only for those still null.

  4. 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 --facts
    

    It merges the bundled {skill-root}/customize.toml with {project-root}/_bmad/custom/skf-verify-stack.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) for init.md to record once it has created {run_dir}.

    Apply the path-scalar fallback now so stage files don't repeat it: {reportTemplatePath} ← workflow.report_template_path if non-empty, else assets/feasibility-report-template.md, bound as the file it names ({project-root} replaced, a bare path taken from {skill-root}). An empty or absent value falls through to that default; init.md §4 checks that it is a readable file before it loads it, and checks the report it creates from it. Bind {outputFolderPath} ← {forge_data_folder}, always (no setting moves it): the report and its -latest copy go where create-stack-skill and refine-architecture look for them, and step 1 finds the earlier reports there.

    The same merge resolves workflow.on_complete (default empty = no-op); report.md §5 executes it, if non-empty, at the end of step 6, before the health check.

    Also apply the array surfaces so they are not silent no-ops: execute each entry in workflow.activation_steps_prepend in order now; treat every entry in workflow.persistent_facts as standing context for the whole run (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).

  5. Pre-flight: the emitter. Before the first prompt, resolve {emitEnvelopeHelper} ← {project-root}/_bmad/skf/shared/scripts/skf-emit-result-envelope.py, else {project-root}/src/shared/scripts/skf-emit-result-envelope.py (the first that exists). If neither exists, HALT (exit code 3, halt_reason: "resolution-failure") at phase on-activation:emitter and display only: "Verify Stack cannot run without skf-emit-result-envelope.py, which is not installed. Re-install SKF."

  6. 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.

Files (bmad-module-skill-forge)
  • assets
    • feasibility-report-template.md 1.9 KB
      Loading…
  • references
    • coverage.md 15.1 KB
      Loading…
    • exit-codes.md 5.7 KB
      Loading…
    • health-check.md 1.4 KB
      Loading…
    • init.md 20.8 KB
      Loading…
    • integration-verification-rules.md 3.9 KB
      Loading…
    • integrations.md 20.6 KB
      Loading…
    • invocation-contract.md 2.7 KB
      Loading…
    • report.md 12.2 KB
      Loading…
    • requirements.md 8.9 KB
      Loading…
    • synthesize.md 17.2 KB
      Loading…
  • scripts
    • skf-coverage-tally.py 27.8 KB
      Loading…
    • skf-previous-report.py 13 KB
      Loading…
    • skf-report-delta.py 27.3 KB
      Loading…
    • skf-report-update.py 30.3 KB
      Loading…
    • skf-skill-summaries.py 12.3 KB
      Loading…
    • skf-verdict-rollup.py 22.8 KB
      Loading…
  • customize.toml 4.5 KB
    Loading…
  • SKILL.md 9.7 KB
    ---
    name: skf-verify-stack
    description: Pre-code stack feasibility verification against architecture and PRD documents. Use when the user requests to "verify a tech stack" or "verify stack."
    ---
    
    # Verify Stack
    
    ## Overview
    
    Cross-references generated skills against architecture and PRD documents to produce a feasibility report with evidence-backed integration verdicts, coverage analysis, and requirements mapping. Read-only: it reads skills and input documents and writes only the feasibility report, its result files and a scratch run folder (see Workflow Rules).
    
    **Schema contract:** This skill is the producer of the SKF shared feasibility report schema — every report conforms to it.
    
    ## Conventions
    
    - Bare paths (e.g. `references/<name>.md`) resolve from the skill root, inside a `references/` file too: only a stage's frontmatter `nextStepFile` names a file beside it.
    - `references/` holds the workflow stages, chained by frontmatter `nextStepFile`; the rules file a stage loads (`integrations.md` loads `integration-verification-rules.md`); the halt reference the stages point to (`exit-codes.md`); and the caller contract (`invocation-contract.md`). `scripts/` holds this skill's deterministic helpers and `assets/` the report template.
    - `{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.
    - **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. `shared/references/output-contract-schema.md` and `shared/health-check.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.
    
    ## Role
    
    You are a stack feasibility analyst and integration verifier operating in Ferris Audit mode. You bring expertise in API surface analysis, cross-library compatibility assessment, and architecture validation, while the user brings their architecture vision and generated skills.
    
    ## Workflow Rules
    
    These rules apply to every step in this workflow:
    
    - Read-only — never modify skills, architecture docs, or PRD files
    - Every verdict must cite evidence from the generated skills
    - 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
    - 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.
    - Always communicate in `{communication_language}`
    - At any interactive prompt, the inputs `cancel`, `exit`, `[X]`, `q`, or `:q` exit cleanly with exit code 6 (`halt_reason: "user-cancelled"`)
    - If `{headless_mode}` is true, auto-proceed through confirmation gates with their default action and log each auto-decision; a gate that picks its default for the user (step 1's default of the newest earlier report) also records that decision in the run sink the moment it decides
    - Every helper a stage runs (a `scripts/` file, or a shared helper from the stage's probe order) is required: if the probe order resolves to no path, or the helper cannot start, HALT (exit code 3, `halt_reason: "resolution-failure"`) at the stage's phase, through the stage's halt envelope. Never recompute a helper's result by hand: the main-thread rule above covers subagent work, not helpers.
    - Every HARD HALT names its exit code, `halt_reason` and phase, and in headless mode prints its envelope through the shared emitter, with the command each stage file shows (`references/exit-codes.md` describes the envelope).
    - Stages 1 to 5 write only the timestamped report `{outputFile}`, and each write that fails halts (exit code 4, `halt_reason: "write-failed"`). Step 6 copies the report to `{outputFileLatest}` only after it passes the feasibility-report check, so a run that halts before then leaves the previous finished copy, the one consumers read, in place.
    - Run state lives in `{run_dir}`, not in context; step 6 deletes it, a HALT keeps it.
    
    ## Stages
    
    | # | Step | File | Auto-proceed |
    |---|------|------|--------------|
    | 1 | Initialize & Load Inputs | references/init.md | Conditional (asks only for inputs no flag gave, or whose path was not found) |
    | 2 | Coverage Analysis | references/coverage.md | Yes |
    | 3 | Integration Verification | references/integrations.md | Yes |
    | 4 | Requirements Mapping | references/requirements.md | Yes |
    | 5 | Synthesize Verdict | references/synthesize.md | Yes |
    | 6 | Report | references/report.md | Yes |
    | 7 | Workflow Health Check | references/health-check.md | Yes |
    
    ## Invocation Contract
    
    `references/invocation-contract.md` holds the inputs, flags, gates, outputs and headless rules, and the `SKF_VERIFY_STACK_RESULT_JSON` result contract; `references/exit-codes.md` the exit codes.
    
    ## On Activation
    
    1. Load config from `{project-root}/_bmad/skf/config.yaml` and resolve:
       - `project_name`, `user_name`, `communication_language`, `document_output_language`
       - `skills_output_folder`, `forge_data_folder`, `sidecar_path`
    
    2. **Fix the run-scoped variables** so no stage derives them again:
       - `timestamp` ← UTC `YYYYMMDD-HHmmss` captured at activation time
       - `project_slug` is bound by init.md before its §1, from the shared feasibility-report helper, which holds the one slug rule the consumers of this report also apply; never slugify `project_name` by hand
       - The two combine in init.md §4 into `{outputFile}` and `{outputFileLatest}` per the stage frontmatter template, and stay fixed for the whole run, so every later reference to either file resolves to the same path.
       - `run_dir` ← `{project-root}/_bmad-output/.skf-run/skf-verify-stack-{timestamp}`, the run folder init.md creates first
    
    3. **Resolve `{headless_mode}`**: true if `--headless` or `-H` was passed as an argument, or if `headless_mode: true` in `{sidecar_path}/preferences.yaml`. Default: false.
    
       **Bind the inputs** in every mode: `{architecture_doc_path}` ← the `--architecture-doc` value, `{prd_path}` ← `--prd` and `{previous_report_path}` ← `--previous-report`, each null when its flag is absent. init.md §1 asks only for those still null.
    
    4. **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-verify-stack.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) for init.md to record once it has created `{run_dir}`.
    
       Apply the path-scalar fallback now so stage files don't repeat it: `{reportTemplatePath}` ← `workflow.report_template_path` if non-empty, else `assets/feasibility-report-template.md`, bound as the file it names (`{project-root}` replaced, a bare path taken from `{skill-root}`). An empty or absent value falls through to that default; init.md §4 checks that it is a readable file before it loads it, and checks the report it creates from it. Bind `{outputFolderPath}` ← `{forge_data_folder}`, always (no setting moves it): the report and its `-latest` copy go where create-stack-skill and refine-architecture look for them, and step 1 finds the earlier reports there.
    
       The same merge resolves `workflow.on_complete` (default empty = no-op); report.md §5 executes it, if non-empty, at the end of step 6, before the health check.
    
       Also apply the array surfaces so they are not silent no-ops: execute each entry in `workflow.activation_steps_prepend` in order now; treat every entry in `workflow.persistent_facts` as standing context for the whole run (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).
    
    5. **Pre-flight: the emitter.** Before the first prompt, resolve `{emitEnvelopeHelper}` ← `{project-root}/_bmad/skf/shared/scripts/skf-emit-result-envelope.py`, else `{project-root}/src/shared/scripts/skf-emit-result-envelope.py` (the first that exists). If neither exists, HALT (exit code 3, `halt_reason: "resolution-failure"`) at phase `on-activation:emitter` and display only: "Verify Stack cannot run without `skf-emit-result-envelope.py`, which is not installed. Re-install SKF."
    
    6. 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.

No comments yet.

Reviews (0)

No reviews yet.