Skf Export Skill

Export Skill

Overview

Packages a completed skill as an agentskills.io-compliant package, generates context snippets, and updates the managed section in CLAUDE.md/.cursorrules/AGENTS.md for platform-aware context injection. It is the sole publishing gate — create-skill/update-skill produce drafts; only export writes platform context files and distribution packages.

Conventions

• Bare paths (e.g. references/<name>.md) resolve from the skill root.
• Module-level path exception: bare knowledge/ and shared/ paths resolve from the SKF module root ({project-root}/_bmad/skf/ installed, src/ in dev), not the skill root (e.g. knowledge/version-paths.md, shared/health-check.md).
• references/ holds prompt content carved out of SKILL.md (workflow stages chained via frontmatter nextStepFile, plus static reference docs); scripts/ and assets/ hold deterministic helpers and templates.
• {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.
• Cross-skill data coupling: assets/managed-section-format.md (loaded by drop-skill and rename-skill's execute.md) and references/update-context.md §4a (v2 manifest schema enforced by skf-manifest-ops.py) are the source of truth for those contracts — schema-breaking changes here need coordinated updates across those skills.

Role

You are a delivery and packaging specialist collaborating with a skill developer, pairing your skill-packaging, ecosystem-compliance, and context-injection expertise with their completed skill and distribution requirements.

Workflow Rules

These rules apply to every step in this workflow:

• Only load one step file at a time — never preload future steps
• 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

Stages

Invocation Contract

Exit Codes

Every HARD HALT in this workflow exits with a stable code so headless automators can branch on the failure class without grepping message text:

Result Contract (Headless)

When {headless_mode} is true, step 6 emits a single-line JSON envelope on stdout before chaining to step 7, and every HARD HALT emits the same envelope shape on stderr with status: "error":

SKF_EXPORT_RESULT_JSON: {"status":"success|error|dry-run","skills":[],"context_files_updated":[],"manifest_path":"…|null","headless_decisions":[],"exit_code":0,"halt_reason":null}

references/result-envelope.md is the single source for the full field semantics and the halt_reason enum — halting stages load it directly, so the enum lives in exactly one place. exit_code matches the Exit Codes table above.

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
   • snippet_skill_root_override (optional string) — when set, overrides the IDE-derived skill_root for snippet root: paths. Authoring repos that keep all skills under a single on-disk folder (e.g. skills/) set this once so exported snippets reference the real layout instead of a per-IDE directory that does not exist. Consuming projects omit it.

2. Compute run-scoped variables:

   • timestamp ← UTC YYYYMMDD-HHmmss captured at activation time. Fixed for the entire workflow run; summary.md reuses this when writing the result contract.

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.

4. Resolve workflow customization. Run:

   python3 {project-root}/_bmad/scripts/resolve_customization.py \
       --skill {skill-root} --key workflow
   

   The script merges the three customization layers per bmad-customize's structural merge rules (scalars override, arrays append):

   • {skill-root}/customize.toml — bundled defaults
   • _bmad/custom/<skill-name>.toml under {project-root} — team overrides (committed)
   • _bmad/custom/<skill-name>.user.toml under {project-root} — personal overrides (gitignored)

   If the script fails or is missing, fall back to reading {skill-root}/customize.toml directly — the bundled defaults are an empty string for each path scalar.

   Apply the fallback now so stage files don't have to repeat the conditional logic. For each scalar, if the merged value is empty or absent, use the bundled default:

   • {managedSectionFormatPath} ← workflow.managed_section_format_path if non-empty, else assets/managed-section-format.md
   • {snippetFormatPath} ← workflow.snippet_format_path if non-empty, else assets/snippet-format.md
   • {onCompleteCommand} ← workflow.on_complete if non-empty, else empty string (no-op — step 6 skips the hook invocation)

   Stash all three as workflow-context variables. Stage files reference them directly — no conditional at the usage site.

   Apply the array surfaces so they are not silent no-ops: execute each entry in workflow.activation_steps_prepend in order now (org-wide pre-flight such as auth, network, or compliance); treat every entry in workflow.persistent_facts as standing context for the whole run (file:-prefixed entries are paths or globs whose contents load as facts — the bundled default loads any project-context.md); then, after activation completes and before the first stage runs, execute each entry in workflow.activation_steps_append in order.

5. Pre-flight write probe. Verify {skills_output_folder} is writable. A read-only mount, full disk, or permissions-denied path otherwise only surfaces at step 4's managed-section rewrite — by then the user has already confirmed the batch:

   mkdir -p "{skills_output_folder}" && \
     printf 'probe' > "{skills_output_folder}/.skf-write-probe" && \
     rm "{skills_output_folder}/.skf-write-probe"
   

   On any non-zero exit: HALT (exit code 4, halt_reason: "write-failed"). In headless mode, emit the error envelope per references/result-envelope.md with skills: [], context_files_updated: [], manifest_path: null.

6. Load, read the full file, and then execute references/load-skill.md to begin the workflow.