Claude Skill

skf-create-skill

Compile a skill from a brief. Supports --batch for multiple briefs. Use when the user requests to "create a skill" or "compile a skill."

LLM Mart · 0 points · 3 views 0 listing impressions 0 install-command copies
Download armelhbobdad-bmad-module-skill-forge-src_skf-create-skill-484edd0.zip · 170 KB

Install

skills CLI npx skills add https://github.com/armelhbobdad/bmad-module-skill-forge/tree/main/src/skf-create-skill
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

Create Skill

Overview

Compiles a verified agent skill from a skill-brief.yaml and the source code or documentation it names: an agentskills.io-compliant SKILL.md with its provenance map, evidence report and references/. The run is mostly autonomous: the Gates row of references/invocation-contract.md lists every stop. Steps adapt to the forge tier (Quick, Forge, Forge+ or Deep). A single run is not resumable: an interrupted run starts again from the brief (only --batch checkpoints progress across briefs).

Conventions

  • Bare paths (e.g. references/<name>.md) resolve from the skill root, inside a references/ file too: only a stage's frontmatter nextStepFile, healthCheckStepFile, componentExtractionStepFile and returnToStep name a file relative to the stage file, and a file the text calls "beside this file" sits beside the file that says so.
  • 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.
  • 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.
  • 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.

Role

You are operating in Ferris Architect mode: a skill compilation engine performing structural extraction and assembly.

Workflow Rules

These rules apply to every step in this workflow:

  • Never include content in SKILL.md without a provenance citation: [AST:] or [SRC:] for code (T1 and T1-low), [QMD:] for T2 context or [EXT:] for T3 documentation, in the forms assets/skill-sections.md gives
  • Never write into a skill folder SKF did not generate — generate-artifacts §1 runs the inventory's write check before creating any directory; without the helper it writes only into a skill folder that does not exist yet
  • Only load one step file at a time — never preload future steps
  • 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.
  • Once step 3 §2a has bound {source_tree} (the private tree a remote source is read from), every HALT after it first runs uv run {sourceTreeHelper} close --tree "{source_tree}" from {project-root} and goes on whatever it prints. Step 7 removes the tree on a run that finishes, and a later run removes one a stopped run left behind, seven days on
  • Every HARD HALT in steps 1 to 7 emits the result envelope before it stops, in every mode. Each HALT names its exit code, halt_reason, phase, path and message where it fires, and its stage file's Rules give the emit command. Stage {"phase": "<phase>", "halt_reason": "<halt_reason>", "reason": "<the halt message, one line>", "summary": {"halt_reason": "<halt_reason>", "evidence_report": null}} as {run_dir}/halt.json (add "path" when the halt names a file or folder; once step 7 has promoted the package, add "skill_package" and "outputs" and set summary.evidence_report to {forge_version}/evidence-report.md), then run uv run {emitEnvelopeHelper} emit-halt --workflow skf-create-skill --run-dir "{run_dir}" --target stderr < "{run_dir}/halt.json", adding --result-dir "{forge_version}" once step 7 has created {forge_version}, so the emitter also writes the halt's create-skill-result-*.json and its -latest.json copy there. Display the line it prints, then stop with the exit code; under --batch the halt ends only its brief: go to references/batch-mode.md §3, which records it and takes the next brief. If {emitEnvelopeHelper} resolved no path, display the halt message alone. The schema, shared/scripts/schemas/skf-create-skill-result-envelope.v1.json, lists every halt_reason with its exit code
  • Always communicate in {communication_language}
  • If {headless_mode} is true, auto-proceed through confirmation gates with their default action
  • Every decision the run takes without asking (each gate a headless run resolves by its default, step 1's tier override and its pick of the only brief, and Gate 2 when a --batch run passes a clean extraction) is recorded the moment it is taken: stage {"step": "<step>", "gate": "<gate>", "decision": "<action>", "rationale": "<why>"}, plus "value" or "fallback" where the gate names one, as {run_dir}/decision.json and run uv run {emitEnvelopeHelper} record --workflow skf-create-skill --run-dir "{run_dir}" --decision < "{run_dir}/decision.json", which stamps the decision's timestamp from the clock. The run sink it appends to, {run_dir}/headless-decisions.jsonl, is the brief's one decision trail: it survives context compaction, step 5 §7 renders the evidence report's ## Auto-Decisions table from it, and the result envelope and contract carry it

Stages

# Step File Auto-proceed
1 Load Brief references/load-brief.md Conditional
2b CCC Discover references/ccc-discover.md Yes
3 Extract references/extract.md Conditional
3b Fetch Temporal references/fetch-temporal.md Yes
3c Fetch Docs references/fetch-docs.md Conditional
3d Component Extraction references/component-extraction.md Conditional
4 Enrich references/enrich.md Yes
5 Compile references/compile.md Yes
5a Doc Sources references/step-doc-sources.md Yes
5b Auto-Shard references/step-auto-shard.md Yes
5c Doc-Rot references/step-doc-rot.md Yes
6 Validate references/validate.md Yes
7 Generate Artifacts references/generate-artifacts.md Yes
8 Report references/report.md Yes
9 Workflow Health Check references/health-check.md Yes

Step 3d (Component Extraction) is a branch inside step 3 for a component-library brief: extract §2c loads it in place of §4 to §4c and resumes at its §5, before Gate 2.

Invocation Contract

Headless callers and pipelines: the inputs, gates, outputs, exit codes and the SKF_CREATE_SKILL_RESULT_JSON and batch reading rules live in references/invocation-contract.md. Interactive runs do not need it.

On Activation

  1. Resolve {emitEnvelopeHelper} ← the first existing path of {project-root}/_bmad/skf/shared/scripts/skf-emit-result-envelope.py and {project-root}/src/shared/scripts/skf-emit-result-envelope.py, the shared emitter every result envelope, result contract and recorded decision goes through.

  2. Check the runtime. Every helper, the customization resolver and every envelope run through uv run, and the Extract, Validate and Generate Artifacts stages also call python3 directly, so confirm that python3 and uv are both on $PATH (command -v python3 and command -v uv). If either is missing, HARD HALT (exit code 3, helper-missing, phase on-activation:runtime): "Create Skill needs {the missing tool}, which is not on your PATH. Install it (uv from https://docs.astral.sh/uv/getting-started/installation/, python3 from https://www.python.org/downloads/), then re-run." Nothing is written, and the halt ends the run, under --batch too. The emitter needs only the standard library, so when only uv is missing, emit in every mode with python3 in place of uv run and display the line it prints; with python3 missing, or no {emitEnvelopeHelper} path, display the message alone:

    python3 "{emitEnvelopeHelper}" emit-halt --workflow skf-create-skill --target stderr <<'SKF_JSON'
    {"phase": "on-activation:runtime", "halt_reason": "helper-missing", "reason": "Create Skill needs uv, which is not on your PATH. Install it from https://docs.astral.sh/uv/getting-started/installation/, then re-run.", "summary": {"halt_reason": "helper-missing", "evidence_report": null}}
    SKF_JSON
    
  3. Load config from {project-root}/_bmad/skf/config.yaml and resolve:

    • output_folder, user_name, communication_language, document_output_language, sidecar_path, skills_output_folder, forge_data_folder
  4. 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.

  5. 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-create-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) for step 1 §0 to record in each brief's run folder.

    Apply the resolved values so the surface is not a silent no-op: 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); and stash {onCompleteCommand} ← workflow.on_complete (empty string = no-op) for step 8 to invoke once each brief's result contract is written. Then, before step 6 loads load-brief.md or batch-mode.md, execute each entry in workflow.activation_steps_append in order; a --batch run executes them once, not per brief.

  6. If --batch was given, load, read the full file, and then execute references/batch-mode.md: it validates every brief first, runs steps 1 to 8 for each one and the health check once. Otherwise load, read the full file, and then execute references/load-brief.md to begin the workflow.

Files (bmad-module-skill-forge)
  • assets
    • compile-assembly-rules.md 12.7 KB
      Loading…
    • skill-sections.md 17.2 KB
      Loading…
  • references
    • assembly-component-library.md 3.2 KB
      Loading…
    • assembly-reference-app.md 5.6 KB
      Loading…
    • assembly-whole-language.md 3.5 KB
      Loading…
    • authoritative-files-protocol.md 10.6 KB
      Loading…
    • batch-mode.md 10.2 KB
      Loading…
    • ccc-discover.md 7.1 KB
      Loading…
    • ccc-index-check.md 5.4 KB
      Loading…
    • compile.md 27.9 KB
      Loading…
    • component-extraction.md 25.4 KB
      Loading…
    • enrich.md 8.6 KB
      Loading…
    • entry-points-by-hand.md 4.6 KB
      Loading…
    • extract.md 38.6 KB
      Loading…
    • extraction-patterns-by-hand.md 25.6 KB
      Loading…
    • extraction-patterns-tracing.md 7.9 KB
      Loading…
    • extraction-patterns.md 34.3 KB
      Loading…
    • fetch-docs.md 18.6 KB
      Loading…
    • fetch-temporal.md 8.3 KB
      Loading…
    • generate-artifacts.md 24.3 KB
      Loading…
    • health-check.md 976 B
      Loading…
    • invocation-contract.md 4 KB
      Loading…
    • load-brief.md 10.7 KB
      Loading…
    • relabel-rule.md 2 KB
      Loading…
    • remote-source-access.md 8.9 KB
      Loading…
    • report.md 14.2 KB
      Loading…
    • source-resolution-protocols.md 12.6 KB
      Loading…
    • step-auto-shard.md 4.3 KB
      Loading…
    • step-doc-rot.md 14.9 KB
      Loading…
    • step-doc-sources.md 8 KB
      Loading…
    • tessl-review-collect.md 4 KB
      Loading…
    • tier-degradation-rules.md 4.8 KB
      Loading…
    • validate.md 35.8 KB
      Loading…
  • scripts
    • scan-doc-rot.py 25.1 KB
      Loading…
  • customize.toml 2.9 KB
    Loading…
  • SKILL.md 11.2 KB
    ---
    name: skf-create-skill
    description: Compile a skill from a brief. Supports --batch for multiple briefs. Use when the user requests to "create a skill" or "compile a skill."
    ---
    
    # Create Skill
    
    ## Overview
    
    Compiles a verified agent skill from a skill-brief.yaml and the source code or documentation it names: an agentskills.io-compliant SKILL.md with its provenance map, evidence report and `references/`. The run is mostly autonomous: the Gates row of `references/invocation-contract.md` lists every stop. Steps adapt to the forge tier (Quick, Forge, Forge+ or Deep). A single run is not resumable: an interrupted run starts again from the brief (only `--batch` checkpoints progress across briefs).
    
    ## Conventions
    
    - Bare paths (e.g. `references/<name>.md`) resolve from the skill root, inside a `references/` file too: only a stage's frontmatter `nextStepFile`, `healthCheckStepFile`, `componentExtractionStepFile` and `returnToStep` name a file relative to the stage file, and a file the text calls "beside this file" sits beside the file that says so.
    - **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.
    - **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.
    - `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.
    
    ## Role
    
    You are operating in Ferris Architect mode: a skill compilation engine performing structural extraction and assembly.
    
    ## Workflow Rules
    
    These rules apply to every step in this workflow:
    
    - Never include content in SKILL.md without a provenance citation: `[AST:]` or `[SRC:]` for code (T1 and T1-low), `[QMD:]` for T2 context or `[EXT:]` for T3 documentation, in the forms `assets/skill-sections.md` gives
    - Never write into a skill folder SKF did not generate — generate-artifacts §1 runs the inventory's write check before creating any directory; without the helper it writes only into a skill folder that does not exist yet
    - Only load one step file at a time — never preload future steps
    - 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.
    - Once step 3 §2a has bound `{source_tree}` (the private tree a remote source is read from), every HALT after it first runs `uv run {sourceTreeHelper} close --tree "{source_tree}"` from `{project-root}` and goes on whatever it prints. Step 7 removes the tree on a run that finishes, and a later run removes one a stopped run left behind, seven days on
    - Every HARD HALT in steps 1 to 7 emits the result envelope before it stops, in every mode. Each HALT names its exit code, `halt_reason`, phase, path and message where it fires, and its stage file's Rules give the emit command. Stage `{"phase": "<phase>", "halt_reason": "<halt_reason>", "reason": "<the halt message, one line>", "summary": {"halt_reason": "<halt_reason>", "evidence_report": null}}` as `{run_dir}/halt.json` (add `"path"` when the halt names a file or folder; once step 7 has promoted the package, add `"skill_package"` and `"outputs"` and set `summary.evidence_report` to `{forge_version}/evidence-report.md`), then run `uv run {emitEnvelopeHelper} emit-halt --workflow skf-create-skill --run-dir "{run_dir}" --target stderr < "{run_dir}/halt.json"`, adding `--result-dir "{forge_version}"` once step 7 has created `{forge_version}`, so the emitter also writes the halt's `create-skill-result-*.json` and its `-latest.json` copy there. Display the line it prints, then stop with the exit code; under `--batch` the halt ends only its brief: go to `references/batch-mode.md` §3, which records it and takes the next brief. If `{emitEnvelopeHelper}` resolved no path, display the halt message alone. The schema, `shared/scripts/schemas/skf-create-skill-result-envelope.v1.json`, lists every `halt_reason` with its exit code
    - Always communicate in `{communication_language}`
    - If `{headless_mode}` is true, auto-proceed through confirmation gates with their default action
    - Every decision the run takes without asking (each gate a headless run resolves by its default, step 1's tier override and its pick of the only brief, and Gate 2 when a `--batch` run passes a clean extraction) is recorded the moment it is taken: stage `{"step": "<step>", "gate": "<gate>", "decision": "<action>", "rationale": "<why>"}`, plus `"value"` or `"fallback"` where the gate names one, as `{run_dir}/decision.json` and run `uv run {emitEnvelopeHelper} record --workflow skf-create-skill --run-dir "{run_dir}" --decision < "{run_dir}/decision.json"`, which stamps the decision's `timestamp` from the clock. The run sink it appends to, `{run_dir}/headless-decisions.jsonl`, is the brief's one decision trail: it survives context compaction, step 5 §7 renders the evidence report's `## Auto-Decisions` table from it, and the result envelope and contract carry it
    
    ## Stages
    
    | # | Step | File | Auto-proceed |
    |---|------|------|--------------|
    | 1 | Load Brief | references/load-brief.md | Conditional |
    | 2b | CCC Discover | references/ccc-discover.md | Yes |
    | 3 | Extract | references/extract.md | Conditional |
    | 3b | Fetch Temporal | references/fetch-temporal.md | Yes |
    | 3c | Fetch Docs | references/fetch-docs.md | Conditional |
    | 3d | Component Extraction | references/component-extraction.md | Conditional |
    | 4 | Enrich | references/enrich.md | Yes |
    | 5 | Compile | references/compile.md | Yes |
    | 5a | Doc Sources | references/step-doc-sources.md | Yes |
    | 5b | Auto-Shard | references/step-auto-shard.md | Yes |
    | 5c | Doc-Rot | references/step-doc-rot.md | Yes |
    | 6 | Validate | references/validate.md | Yes |
    | 7 | Generate Artifacts | references/generate-artifacts.md | Yes |
    | 8 | Report | references/report.md | Yes |
    | 9 | Workflow Health Check | references/health-check.md | Yes |
    
    *Step 3d (Component Extraction) is a branch inside step 3 for a `component-library` brief: extract §2c loads it in place of §4 to §4c and resumes at its §5, before Gate 2.*
    
    ## Invocation Contract
    
    Headless callers and pipelines: the inputs, gates, outputs, exit codes and the `SKF_CREATE_SKILL_RESULT_JSON` and batch reading rules live in `references/invocation-contract.md`. Interactive runs do not need it.
    
    ## On Activation
    
    1. Resolve `{emitEnvelopeHelper}` ← the first existing path of `{project-root}/_bmad/skf/shared/scripts/skf-emit-result-envelope.py` and `{project-root}/src/shared/scripts/skf-emit-result-envelope.py`, the shared emitter every result envelope, result contract and recorded decision goes through.
    
    2. **Check the runtime.** Every helper, the customization resolver and every envelope run through `uv run`, and the Extract, Validate and Generate Artifacts stages also call `python3` directly, so confirm that `python3` and `uv` are both on `$PATH` (`command -v python3` and `command -v uv`). If either is missing, **HARD HALT** (exit code 3, `helper-missing`, phase `on-activation:runtime`): "**Create Skill needs `{the missing tool}`, which is not on your PATH.** Install it (`uv` from <https://docs.astral.sh/uv/getting-started/installation/>, `python3` from <https://www.python.org/downloads/>), then re-run." Nothing is written, and the halt ends the run, under `--batch` too. The emitter needs only the standard library, so when only `uv` is missing, emit in every mode with `python3` in place of `uv run` and display the line it prints; with `python3` missing, or no `{emitEnvelopeHelper}` path, display the message alone:
    
       ```bash
       python3 "{emitEnvelopeHelper}" emit-halt --workflow skf-create-skill --target stderr <<'SKF_JSON'
       {"phase": "on-activation:runtime", "halt_reason": "helper-missing", "reason": "Create Skill needs uv, which is not on your PATH. Install it from https://docs.astral.sh/uv/getting-started/installation/, then re-run.", "summary": {"halt_reason": "helper-missing", "evidence_report": null}}
       SKF_JSON
       ```
    
    3. Load config from `{project-root}/_bmad/skf/config.yaml` and resolve:
       - `output_folder`, `user_name`, `communication_language`, `document_output_language`, `sidecar_path`, `skills_output_folder`, `forge_data_folder`
    
    4. **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.
    
    5. **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-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) for step 1 §0 to record in each brief's run folder.
    
       Apply the resolved values so the surface is not a silent no-op: 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); and stash `{onCompleteCommand}` ← `workflow.on_complete` (empty string = no-op) for step 8 to invoke once each brief's result contract is written. Then, before step 6 loads load-brief.md or batch-mode.md, execute each entry in `workflow.activation_steps_append` in order; a --batch run executes them once, not per brief.
    
    6. If `--batch` was given, load, read the full file, and then execute `references/batch-mode.md`: it validates every brief first, runs steps 1 to 8 for each one and the health check once. Otherwise load, read the full file, and then execute `references/load-brief.md` to begin the workflow.
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.