skf-refine-architecture
Skill7 starsChanged 8 days agoApache-2.0View on GitHub
Refines an architecture document against generated skills and a Verify Stack report. Use when the user requests to "refine the architecture against generated skills" or "refine an architecture doc with a VS report.
In this repository38 other files it gives its agents.
- _skf-learn/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- bmad-advanced-elicitationSkill
- bmad-brainstormingSkill
- bmad-cis-agent-brainstorming-coachSkill
- bmad-cis-agent-creative-problem-solverSkill
- bmad-cis-agent-design-thinking-coachSkill
- bmad-cis-agent-innovation-strategistSkill
- bmad-cis-agent-presentation-masterSkill
- bmad-cis-agent-storytellerSkill
- bmad-cis-design-thinkingSkill
- bmad-cis-innovation-strategySkill
- bmad-cis-problem-solvingSkill
- bmad-cis-storytellingSkill
- bmad-distillatorSkill
- bmad-editorial-review-proseSkill
- bmad-editorial-review-structureSkill
- bmad-helpSkill
- bmad-index-docsSkill
- bmad-party-modeSkill
- bmad-review-adversarial-generalSkill
- bmad-review-edge-case-hunterSkill
- bmad-shard-docSkill
- skf-analyze-sourceSkill
- skf-audit-skillSkill
- skf-brief-skillSkill
- skf-campaignSkill
- skf-create-skillSkill
- skf-create-stack-skillSkill
- skf-drop-skillSkill
- skf-export-skillSkill
- skf-forgerSkill
- skf-quick-skillSkill
- skf-rename-skillSkill
- skf-setupSkill
- skf-test-skillSkill
- skf-update-skillSkill
- skf-verify-stackSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 3 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
Never speculate — every gap, issue, or improvement must cite specific APIs, types, or function signatures from the generated skills
- Distinctive: line 28
Only load one step file at a time — never preload future steps
- Very specific: line 30
Always communicate in {communication_language}
- Very specific: line 32
If {headless_mode} is true, auto-proceed through confirmation gates with their default action.
- Very specific: line 33
Every HARD HALT names its exit code, halt_reason and phase, and in headless mode prints the envelope the Result Contract below describes
- Very specific: line 34
Run state lives in {run_dir}, not in context.
- Very specific: line 60
When {headless_mode} is true, step 6 prints one SKF_REFINE_ARCHITECTURE_RESULT_JSON: {...} line on stdout, and every HARD HALT one on …
- Very specific: line 102
Config-completeness (exit 3): If {outputFolderPath} is empty: HALT (exit code 3, halt_reason: "output-folder-unconfigured") at phase …
- Distinctive: line 104
Write probe (exit 4): Check that both paths are writable before any prompt:
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Refine Architecture
Overview
Produces a refined architecture document: gaps filled, issues flagged and improvements suggested from the generated skills and an optional VS feasibility report. It never deletes original content, only adds annotations, subsections and suggestions between <!-- RA:BEGIN ... --> and <!-- RA:END --> marker lines; run again on a refined document, it sets its earlier annotations aside and writes one current set.
Conventions
- Bare paths (e.g.
references/<name>.md) resolve from the skill root. - 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. - 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 an architecture refinement analyst in Ferris Architect mode; the user brings the architecture vision and the generated skills.
Workflow Rules
- Never speculate — every gap, issue, or improvement must cite specific APIs, types, or function signatures from the generated skills
- Only load one step file at a time — never preload future steps
- 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. - Always communicate in
{communication_language} - At any interactive prompt, the inputs
cancel,exit,[X],q, or:qexit cleanly with exit code 6 (halt_reason: "user-cancelled") - If
{headless_mode}is true, auto-proceed through confirmation gates with their default action; a gate that picks its default records that decision in the run sink the moment it decides - Every HARD HALT names its exit code,
halt_reasonand phase, and in headless mode prints the envelope the Result Contract below describes - Run state lives in
{run_dir}, not in context; step 6 deletes it when the run finishes, a HALT keeps it
Stages
| # | Step | File | Auto-proceed |
| 1 | Initialize & Load Inputs | references/init.md | No (input gate) |
| 2 | Gap Analysis | references/gap-analysis.md | Conditional (confirm a derived scope) |
| 3 | Issue Detection | references/issue-detection.md | Yes |
| 4 | Improvements | references/improvements.md | Yes |
| 5 | Compile Refined Architecture | references/compile.md | No (review) |
| 6 | Report | references/report.md | Yes |
| 7 | Workflow Health Check | references/health-check.md | Yes |
Invocation Contract
| Aspect | Detail | ||
| Inputs | architecture_doc_path [required], vs_report_path [optional] | ||
| Flags | --headless / -H; --architecture-doc <path> and --vs-report-path <path> answer the step 1 prompts (--vs-report-path none refines without a report and skips the search for one); --scope-skills <names> (comma-separated skill names that replace the derived scope, so step 2 asks no scope confirmation) | ||
| Gates | step 1: Input Gate [use args] | step 2: Scope Confirm Gate [C] continue / [X] cancel (only when a derived scope drops skills or keeps an ambiguous one) | step 5: Review Gate [R] review each refinement / [C] approve and replace the refined document / [X] cancel |
| Outputs | refined-architecture-{arch_project_name}.md at {outputFolderPath} (the document's frontmatter project_name, else config's), promoted from a draft once the step 5 review approves it; an earlier one is first renamed to refined-architecture-{arch_project_name}-{timestamp}.md. Also refine-architecture-result-{YYYYMMDD-HHmmss}.json, its -latest.json copy and, once an approved review drops a finding, .ra-dismissed-{arch_project_name}.json | ||
| Headless | Every gate takes its default when {headless_mode} is true: --scope-skills skips the step 2 scope confirmation, and without --vs-report-path step 1 uses the [VS] report it finds. A caller reads the run's own SKF_REFINE_ARCHITECTURE_RESULT_JSON line. A run that printed no envelope line has no result to read, whatever the process exit code: it was cut off, or could not write its result, and refine-architecture-result-latest.json may then describe an earlier run, so it is never read in its place. |
Result Contract (Headless)
When {headless_mode} is true, step 6 prints one SKF_REFINE_ARCHITECTURE_RESULT_JSON: {...} line on stdout, and every HARD HALT one on stderr, built by the shared emitter: references/exit-codes.md gives its fields, the halt_reason values and the halt command.
On Activation
- Load config from
{project-root}/_bmad/skf/config.yamland resolve:project_name,user_name,communication_language,document_output_languageskills_output_folder,forge_data_folder,output_folder,sidecar_path
- Compute run-scoped variables:
timestamp← the output ofdate -u +%Y%m%d-%H%M%S, run once now.run_dir←{project-root}/_bmad-output/.skf-run/skf-refine-architecture-{timestamp}
- Resolve
{headless_mode}: true if--headlessor-Hwas passed as an argument, or ifheadless_mode: truein{sidecar_path}/preferences.yaml. Default: false. 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 workflowIt merges the bundled
{skill-root}/customize.tomlwith{project-root}/_bmad/custom/skf-refine-architecture.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}for §5 to record.Bind each path scalar, taking the bundled default when the merged value is empty or absent:
{refinementRulesPath}←workflow.refinement_rules_pathif non-empty, elsereferences/refinement-rules.md(house style only: the file's first section names what a copy can change){outputFolderPath}←workflow.output_folder_pathif non-empty, else{output_folder}{onCompleteCommand}←workflow.on_completeif non-empty, else empty
Then run
workflow.activation_steps_prependnow, treatworkflow.persistent_factsas standing context for the run (file:entries load their files or globs as facts: the bundled default loads everyproject-context.mdunder{project-root}; an entry prefixed!drops each earlier entry it names and loads nothing itself, so an override's"!file:{project-root}/**/project-context.md"turns that default off), then runworkflow.activation_steps_appendonce §5's pre-flight has passed, before §6 loads the first stage.Pre-flight: the emitter, config, write probe and run folder. In that order, so every halt can print its envelope and an empty path halts as missing config (exit 3), not as a write failure.
The emitter. 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 phaseon-activation:emitterand display only: "Refine Architecture cannot run withoutskf-emit-result-envelope.py, which is not installed. Re-install SKF."The halts below come before the run folder, so in headless mode each passes its payload on stdin, with
"customization_resolver_unavailable": "<reason>"added when step 4 kept one:uv run {emitEnvelopeHelper} emit-halt --workflow skf-refine-architecture --target stderr <<'SKF_RA_HALT' {"phase": "<phase>", "reason": "<the halt message>", "halt_reason": "<halt_reason>"} SKF_RA_HALTConfig-completeness (exit 3). If
{outputFolderPath}is empty: HALT (exit code 3,halt_reason: "output-folder-unconfigured") at phaseon-activation:config: "Setoutput_folderin config.yaml, then re-run [RA]." If{forge_data_folder}is empty: HALT (exit code 3,halt_reason: "forge-folder-unconfigured") at phaseon-activation:config: "Setforge_data_folderin config.yaml, then re-run [RA]."Write probe (exit 4). Check that both paths are writable before any prompt:
for dir in "{outputFolderPath}" "{forge_data_folder}"; do mkdir -p "$dir" && \ printf 'probe' > "$dir/.skf-write-probe" && \ rm "$dir/.skf-write-probe" doneOn any non-zero exit: HALT (exit code 4,
halt_reason: "write-failed") at phaseon-activation:write-probe, with"path"set to the folder that failed.Run folder (exit 4).
mkdir -p "{project-root}/_bmad-output/.skf-run" && mkdir "{run_dir}"If the command fails, HALT (exit code 4,
halt_reason: "write-failed") at phaseon-activation:run-folder: "Cannot create the run folder{run_dir}: {the first stderr line}." Once it exists and{customization_resolver_unavailable}is set, record the reason in the run sink: writecustomization_resolver_unavailable: {customization_resolver_unavailable}to{run_dir}/resolver-warning.txtwith a file write, neverecho, then runuv run {emitEnvelopeHelper} record --run-dir "{run_dir}" --warning "$(cat "{run_dir}/resolver-warning.txt")".- Load, read the full file, and then execute
references/init.mdto begin the workflow.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

