engagement-workflow
Run a full marketing engagement using the 12-Part methodology. Use when starting a new engagement, advancing parts, applying the Decision Matrix, or showing engagement status.
npx skills add indranilbanerjee/digital-marketing-pro --skill engagement-workflow --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
This skill orchestrates a full marketing engagement using a fixed 12-Part methodology. It serves as the central controller for the engagement lifecycle, checkpointing, and per-part production contracts. It produces a canonical set of files at each stage and handles persistence via engagement-state.py. It supports starting new engagements, advancing parts, applying the decision matrix, and showing engagement status.
How it works
- It is invoked through the /digital-marketing-pro:engagement command family, acting as the slim router and single source of truth for lifecycle actions.
- It uses a checkpointing protocol: init a run, save each completed part, finalize, and publish to a visible output folder. It persists run IDs and part completion via scripts like checkpoint-manager.py and engagement-state.py.
- For each part completion, it saves the part deliverable with the appropriate path and extension using checkpoint-manager.py save, ensuring Part 5 and Part 8 pass a full quality check before checkpointing.
- It validates outputs against PART_DEFINITIONS, supports repair of partial states, and limits v2 re-run rounds per part to 2 unless overridden.
- It offers a wide set of subcommands to start, advance, check status, show trees, validate parts, apply re-runs via the Decision Matrix, perform update-back operations, and generate per-part production targets.
When to use it
- Start a new engagement with Part 1 intake.
- Advance from the current part to the next not-yet-completed part.
- Show current engagement status, file-tree, or detailed life-cycle state.
- Apply or re-run the Decision Matrix to compute re-run plans after client validation.
- Validate Part 5 (Client Validation) and Part 8 deliverables before checkpointing.
What it can touch
- It interacts with: engagement-state.py for persistence, checkpoint-manager.py for save/init/finalize, and various scripts for validation, publishing, and versioning as described in the steps.
- It references and uses the brand workspace under ~/.claude-marketing/brands/{slug}/ and CLAUDE_PLUGIN_ROOT for script paths.
Caveats
- The flow is strict: never edit _engagement.json directly; always use engagement-state.py.
- A maximum of 2 v2 re-run rounds per part are allowed unless overridden; excessive re-runs require explicit approval.
- Part 5 and Part 8 require a full quality gate before checkpointing; BLOCKED results must be fixed before proceeding.
# /digital-marketing-pro:engagement-workflow — 12-Part Engagement Orchestrator This skill orchestrates the full marketing engagement using the 12-Part sequential methodology. Every brand engagement runs through the same 12 parts in sequence, producing a canonical set of files at each stage. ## Context efficiency Heavy skill. **Grep before Read** any referenced file, then `Read` only matched ranges with `offset` + `limit`. List the brand's workspace at `~/.claude-marketing/brands/{slug}/` (or `$CLAUDE_PLUGIN_DATA/digital-marketing-pro/brands/{slug}/` when that env var is set) before opening files. On re-invocation mid-session, skip files already in context. Read these references before producing output: - [engagement-flow-methodology.md](../context-engine/engagement-flow-methodology.md) — the full 12-Part flow - [two-views-model.md](../context-engine/two-views-model.md) — v1 / v2 architecture - [stone-vs-opinion.md](../context-engine/stone-vs-opinion.md) — confidence tagging - [decision-matrix-rerun.md](../context-engine/decision-matrix-rerun.md) — when to re-run what - [update-back-rule.md](../context-engine/update-back-rule.md) — versioning protocol - [living-instruction-file-spec
- Context efficiency
- Operating Mode
- Checkpointing & Resume (single source of truth)
- State validation & rework caps
- Subcommands
- /digital-marketing-pro:engagement start <brand-slug> <engagement-id>
- /digital-marketing-pro:engagement next [brand] [id]
- /digital-marketing-pro:engagement status [brand] [id]
- /digital-marketing-pro:engagement file-tree [brand] [id]
- /digital-marketing-pro:engagement validate [brand] [id]
- /digital-marketing-pro:engagement re-run-decision [brand] [id]
- /digital-marketing-pro:engagement lif-show [brand] [id]
- /digital-marketing-pro:engagement list-engagements [brand]
- Production shorthands
python "${CLAUDE_PLUGIN_ROOT}/scripts/checkpoint-manager.py" init \
Record the returned run_id into _engagement.json so resume can find it:
python "${CLAUDE_PLUGIN_ROOT}/scripts/engagement-state.py" set-checkpoint-run \
python "${CLAUDE_PLUGIN_ROOT}/scripts/checkpoint-manager.py" save \
BLOCKING gate — Part 5 and Part 8 deliverables cannot be checkpointed until this passes
python "${CLAUDE_PLUGIN_ROOT}/scripts/output-publisher.py" publish-run \
python "${CLAUDE_PLUGIN_ROOT}/scripts/checkpoint-manager.py" finalize \
python "${CLAUDE_PLUGIN_ROOT}/scripts/engagement-state.py" validate-part \
python "${CLAUDE_PLUGIN_ROOT}/scripts/engagement-state.py" init --repair \What does the engagement-workflow skill do?
Run a full marketing engagement using the 12-Part methodology. Use when starting a new engagement, advancing parts, applying the Decision Matrix, or showing engagement status.
How do I install it?
Run `npx skills add indranilbanerjee/digital-marketing-pro --skill engagement-workflow --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From indranilbanerjee/digital-marketing-pro, a repository with 700 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.