skf-campaign

Name: skf-campaign
Author: armelhbobdad

88stars9forks

How to install skf-campaign?

armelhbobdad/bmad-module-skill-forge/skf-campaign

$npx -y skills add armelhbobdad/bmad-module-skill-forge --skill skf-campaign

Installs into the current project.

Summary

Campaign orchestration — multi-library skill production with dependency tracking, file-based state, and resume. Use when the user asks to "run a campaign" or "orchestrate skills.

Files · 1

View on GitHub

SKILL.md

1	# Campaign
2
3	## Overview
4
5	Orchestrates the production of 15+ skills across multiple sessions by driving them through the full SKF pipeline (brief, generate, compile, test, export) in dependency order. Campaign sits atop the pipeline ladder: it sequences the workflows that produce skills rather than producing artifacts itself. File-based state (`_campaign-state.yaml`) survives context death, enabling resume from any point.
6
7	## Conventions
8
9	- Bare paths (e.g. `references/step-01-setup.md`) resolve from the skill root.
10	- `references/` holds the stage-chained step files plus reference specs (e.g. the `_campaign-directive.md` contract at `references/campaign-directive-spec.md`); `templates/`, `scripts/`, and `assets/` hold templates, deterministic helpers, and the state schema.
11	- `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).
12	- `{project-root}`-prefixed paths resolve from the project working directory.
13	- `{skill-name}` resolves to the skill directory's basename.
14
15	## Role
16
17	You are a campaign orchestrator operating in Ferris's Management mode. You sequence workflows, track per-skill state, enforce quality gates, and ensure every skill reaches its target tier — while the individual pipeline workflows handle the actual artifact production.
18
19	## On Activation
20
21	Run these steps once, in order, before dispatching to Mode Routing.
22
23	1. Load config. Read `{project-root}/_bmad/skf/config.yaml` and `{sidecar_path}/preferences.yaml` in one batched message (independent files). From config resolve `project_name`, `user_name`, `communication_language`, `document_output_language`, `skills_output_folder`, `forge_data_folder`, `sidecar_path`. From preferences resolve `headless_mode` (default false). If the config file is missing, fall back to `forge_data_folder = forge-data`.
24
25	2. Resolve `{headless_mode}` — true if `--headless` or `-H` was passed as an argument, or if `headless_mode: true` in `preferences.yaml`. Default: false.
26
27	3. Resolve workflow customization. Run:
28
29	```bash
30	python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow
31	```
32
33	The script merges three layers (scalars override, arrays append):
34
35	- `{skill-root}/customize.toml` — bundled defaults
36	- `_bmad/custom/<skill-name>.toml` under `{project-root}` — team overrides (committed)
37	- `_bmad/custom/<skill-name>.user.toml` under `{project-root}` — personal overrides (gitignored)
38
39	If it fails or is missing, fall back to `{skill-root}/customize.toml` directly. Resolve each scalar now (so step files never repeat the conditional) and stash as workflow-context variables:
40
41	- `{campaignWorkspacePath}` ← `workflow.campaign_workspace_path` if non-empty, else `{forge_data_folder}/_campaign`
42	- `{qualityGateHard}` / `{qualityGateSoftTarget}` / `{qualityGateSoftFallback}` ← the `quality_gate_*` scalars (defaults `zero-critical-high` / `90` / `80`)
43	- `{reportTemplatePath}` ← `workflow.report_template_path` if non-empty, else `templates/campaign-report-template.md`
44	- `{kickoffTemplatePath}` ← `workflow.kickoff_template_path` if non-empty, else `templates/kickoff-template.md`
45	- `{briefTemplatePath}` ← `workflow.brief_template_path` if non-empty, else `templates/campaign-brief-template.yaml`
46	- `{onComplete}` ← `workflow.on_complete` (empty = no-op)
47
48	Load `workflow.persistent_facts` (literal sentences and `file:` references, globs expanded) and keep them in mind for the whole campaign — they are injected into every per-skill kickoff. Run any `activation_steps_prepend` before step 1 and any `activation_steps_append` after this step.
49
50	4. Parse CLI overrides into the workflow context:
51
52	\| Flag \| Effect \|
53	\| --- \| --- \|
54	\| `--headless` / `-H` \| Force `{headless_mode} = true` (see step 2). \|
55	\| `--brief <file>` \| Seed step-01 targets from a `campaign-brief.yaml` instead of interactive prompts. Implies `--headless`. \|
56	\| `--manifest <file>` \| Seed step-01 targets from a plain-text `name,repo_url,tier,pin` manifest. Implies `--headless`. \|
57	\| `--from <skill>` \| Resume override — see Mode Routing. \|
58
59	If `--brief` or `--manifest` is set, force `{headless_mode} = true` (log "headless: coerced by --brief/--manifest" if it was false).
60
61	`--manifest` format: one `name,repo_url,tier,pin` target per line (empty `pin` = latest); a trailing `;dep1,dep2` segment sets `depends_on`; blank and `#` lines are skipped. A malformed line HALTs step-01 with the offending line numbers — never a partial target set.
62
63	5. Dispatch per Mode Routing below.
64
65	## Workflow Rules
66
67	These rules apply to every step in this workflow:
68
69	- State-first — write state to disk before chaining to the next step or workflow
70	- Read-backup-modify-write for all stat

People who liked this also viewed

6 picks

Type

skf-campaign

88stars9forks

View on GitHub

How to install skf-campaign?

armelhbobdad/bmad-module-skill-forge/skf-campaign

$npx -y skills add armelhbobdad/bmad-module-skill-forge --skill skf-campaign

Installs into the current project.

Summary

Campaign orchestration — multi-library skill production with dependency tracking, file-based state, and resume. Use when the user asks to "run a campaign" or "orchestrate skills.

Files · 1

View on GitHub

SKILL.md

1	# Campaign
2
3	## Overview
4
5	Orchestrates the production of 15+ skills across multiple sessions by driving them through the full SKF pipeline (brief, generate, compile, test, export) in dependency order. Campaign sits atop the pipeline ladder: it sequences the workflows that produce skills rather than producing artifacts itself. File-based state (`_campaign-state.yaml`) survives context death, enabling resume from any point.
6
7	## Conventions
8
9	- Bare paths (e.g. `references/step-01-setup.md`) resolve from the skill root.
10	- `references/` holds the stage-chained step files plus reference specs (e.g. the `_campaign-directive.md` contract at `references/campaign-directive-spec.md`); `templates/`, `scripts/`, and `assets/` hold templates, deterministic helpers, and the state schema.
11	- `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).
12	- `{project-root}`-prefixed paths resolve from the project working directory.
13	- `{skill-name}` resolves to the skill directory's basename.
14
15	## Role
16
17	You are a campaign orchestrator operating in Ferris's Management mode. You sequence workflows, track per-skill state, enforce quality gates, and ensure every skill reaches its target tier — while the individual pipeline workflows handle the actual artifact production.
18
19	## On Activation
20
21	Run these steps once, in order, before dispatching to Mode Routing.
22
23	1. Load config. Read `{project-root}/_bmad/skf/config.yaml` and `{sidecar_path}/preferences.yaml` in one batched message (independent files). From config resolve `project_name`, `user_name`, `communication_language`, `document_output_language`, `skills_output_folder`, `forge_data_folder`, `sidecar_path`. From preferences resolve `headless_mode` (default false). If the config file is missing, fall back to `forge_data_folder = forge-data`.
24
25	2. Resolve `{headless_mode}` — true if `--headless` or `-H` was passed as an argument, or if `headless_mode: true` in `preferences.yaml`. Default: false.
26
27	3. Resolve workflow customization. Run:
28
29	```bash
30	python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow
31	```
32
33	The script merges three layers (scalars override, arrays append):
34
35	- `{skill-root}/customize.toml` — bundled defaults
36	- `_bmad/custom/<skill-name>.toml` under `{project-root}` — team overrides (committed)
37	- `_bmad/custom/<skill-name>.user.toml` under `{project-root}` — personal overrides (gitignored)
38
39	If it fails or is missing, fall back to `{skill-root}/customize.toml` directly. Resolve each scalar now (so step files never repeat the conditional) and stash as workflow-context variables:
40
41	- `{campaignWorkspacePath}` ← `workflow.campaign_workspace_path` if non-empty, else `{forge_data_folder}/_campaign`
42	- `{qualityGateHard}` / `{qualityGateSoftTarget}` / `{qualityGateSoftFallback}` ← the `quality_gate_*` scalars (defaults `zero-critical-high` / `90` / `80`)
43	- `{reportTemplatePath}` ← `workflow.report_template_path` if non-empty, else `templates/campaign-report-template.md`
44	- `{kickoffTemplatePath}` ← `workflow.kickoff_template_path` if non-empty, else `templates/kickoff-template.md`
45	- `{briefTemplatePath}` ← `workflow.brief_template_path` if non-empty, else `templates/campaign-brief-template.yaml`
46	- `{onComplete}` ← `workflow.on_complete` (empty = no-op)
47
48	Load `workflow.persistent_facts` (literal sentences and `file:` references, globs expanded) and keep them in mind for the whole campaign — they are injected into every per-skill kickoff. Run any `activation_steps_prepend` before step 1 and any `activation_steps_append` after this step.
49
50	4. Parse CLI overrides into the workflow context:
51
52	\| Flag \| Effect \|
53	\| --- \| --- \|
54	\| `--headless` / `-H` \| Force `{headless_mode} = true` (see step 2). \|
55	\| `--brief <file>` \| Seed step-01 targets from a `campaign-brief.yaml` instead of interactive prompts. Implies `--headless`. \|
56	\| `--manifest <file>` \| Seed step-01 targets from a plain-text `name,repo_url,tier,pin` manifest. Implies `--headless`. \|
57	\| `--from <skill>` \| Resume override — see Mode Routing. \|
58
59	If `--brief` or `--manifest` is set, force `{headless_mode} = true` (log "headless: coerced by --brief/--manifest" if it was false).
60
61	`--manifest` format: one `name,repo_url,tier,pin` target per line (empty `pin` = latest); a trailing `;dep1,dep2` segment sets `depends_on`; blank and `#` lines are skipped. A malformed line HALTs step-01 with the offending line numbers — never a partial target set.
62
63	5. Dispatch per Mode Routing below.
64
65	## Workflow Rules
66
67	These rules apply to every step in this workflow:
68
69	- State-first — write state to disk before chaining to the next step or workflow
70	- Read-backup-modify-write for all stat

People who liked this also viewed

6 picks

Type