Skip to content

indranilbanerjee/digital-marketing-pro / skills/context-engine

context-engine

Verified

Load shared marketing context: brand profile, benchmarks, compliance rules, specs. "load my brand context"

FileKindSize
30-60-90-framework.mdmarkdown8.2 KB
SKILL.mdskill md12.9 KB
actionable-persona-format.mdmarkdown7.0 KB
advanced-reporting-guide.mdmarkdown21.1 KB
agency-operations-guide.mdmarkdown15.7 KB
ai-visibility-metrics.mdmarkdown2.9 KB
approval-framework.mdmarkdown13.0 KB
b2b-decision-making-unit.mdmarkdown9.1 KB
channel-families.mdmarkdown7.7 KB
competitive-monitoring-guide.mdmarkdown16.8 KB
competitor-3-question-output.mdmarkdown8.0 KB
compliance-rules.mdmarkdown87.2 KB
compound-intelligence-guide.mdmarkdown15.5 KB
creative-intelligence-guide.mdmarkdown13.9 KB
crm-integration-guide.mdmarkdown35.4 KB
custom-mcp-guide.mdmarkdown17.1 KB
decision-framework.mdmarkdown7.4 KB
decision-matrix-rerun.mdmarkdown4.9 KB
engagement-flow-methodology.mdmarkdown11.4 KB
eu-code-of-practice.mdmarkdown15.6 KB
eval-framework-guide.mdmarkdown27.5 KB
eval-rubrics.mdmarkdown16.8 KB
execution-workflows.mdmarkdown23.3 KB
five-digital-markets.mdmarkdown7.5 KB
fixed-vs-variable-budget.mdmarkdown6.8 KB
four-core-documents-spec.mdmarkdown14.2 KB
geo-execution-guide.mdmarkdown20.2 KB
google-seo-reference.mdmarkdown7.3 KB
growth-plan-template.mdmarkdown9.5 KB
guidelines-framework.mdmarkdown14.0 KB
in-market-out-market.mdmarkdown6.1 KB
india-market-context.mdmarkdown14.1 KB
industry-profiles.mdmarkdown65.0 KB
intelligence-layer.mdmarkdown3.9 KB
journey-growth-guide.mdmarkdown19.8 KB
living-instruction-file-spec.mdmarkdown7.2 KB
market-intelligence-guide.mdmarkdown13.7 KB
marketing-science-guide.mdmarkdown14.0 KB
memory-architecture.mdmarkdown12.5 KB
monthly-report-template.mdmarkdown7.0 KB
multilingual-execution-guide.mdmarkdown31.7 KB
narrative-warfare-guide.mdmarkdown17.9 KB
platform-publishing-specs.mdmarkdown19.5 KB
platform-specs.mdmarkdown34.7 KB
reporting-cadence.mdmarkdown8.5 KB
schema-templates.jsonconfig8.7 KB
scoring-rubrics.mdmarkdown10.9 KB
self-healing-ops-guide.mdmarkdown18.5 KB
seo-execution-guide.mdmarkdown14.8 KB
stone-vs-opinion.mdmarkdown7.7 KB
synthetic-audience-guide.mdmarkdown20.4 KB
team-roles-framework.mdmarkdown12.4 KB
three-scenario-forecasting.mdmarkdown7.4 KB
transcreation-framework.mdmarkdown24.2 KB
two-views-model.mdmarkdown5.5 KB
unit-economics-framework.mdmarkdown7.5 KB
update-back-rule.mdmarkdown7.0 KB
yearly-planner-template.mdmarkdown6.1 KB

decision-matrix-rerun.md

View on GitHub
# Decision Matrix for v2 Re-runs

After Part 5 Client Validation, the Decision Matrix governs exactly which Part 3 and Part 4 documents need to be re-run as v2 versions. The matrix prevents over-re-running (which wastes compute) and under-re-running (which leaves stale assumptions in the v2 layer).

## How it works

In Part 5, the client reviews the Client Validation Document and makes one of four decisions on each finding:

- **ACCEPT** — finding is correct as stated
- **REJECT** — finding is wrong; client provides correction
- **EDIT** — finding is partially correct; client provides amended version
- **DEFER** — needs further investigation; flag for follow-up

The Decision Matrix then triggers v2 re-runs based on which categories of findings were rejected or edited.

## The Matrix

| Category of change in Part 5 | Re-run these v2 documents |
|---|---|
| **Competitors changed** (added new competitors, removed competitors, changed competitive tier rankings) | All four Core Documents (3.1, 3.2, 3.3, 3.4) AND 4.1 Competitor Ad Analysis AND 4.2 Competitor Positioning |
| **Target market data changed** (geography, market sizing, addressable segments) | 4.3 Customer Analysis AND 4.4 Market Analysis |
| **Audiences changed** (TG priorities reshuffled, new persona added, persona attributes corrected) | Core Doc 3.2 (Segmentation) + Core Doc 3.3 (Brand Positioning) + Core Doc 3.4 (DMFlow) |
| **Positioning changed** (positioning statement amended, messaging pillars revised) | Core Doc 3.3 (Brand Positioning) only |
| **Budget / scope changed** (budget envelope changed, channel scope changed) | Core Doc 3.4 (DMFlow) only |
| **Pricing or offering changed** (pricing model amended, offering scope corrected) | Core Doc 3.1 (Business & SBU Analysis) — section 4 (Unit Economics) and section 7 (Pricing Architecture) |
| **Unit economics changed** (CAC range corrected, LTV range corrected, margin corrected) | Core Doc 3.1 — section 4 only (do not re-run full doc unless other changes warrant it) |
| **Minor corrections only** (typos, factual fixes, source updates that do not change the conclusion) | NO full re-run. Update inline in v1, tag the file as v1.1, log the change in the document's change log |

## Trigger detection

The `/digital-marketing-pro:engagement re-run-decision` command:

1. Reads the Client Validation Document responses
2. Categorises each REJECTED or EDITED finding by type (competitor / market / audience / positioning / budget / pricing / unit-economics / minor)
3. Computes the union of triggered re-runs
4. Outputs the re-run plan: which docs need v2, which can stay as v1
5. Returns the estimated compute cost (rough token estimate for each re-run)
6. Awaits user approval before running

## Rules

1. **Never auto-execute re-runs without showing the plan.** The user always sees and approves what will run.
2. **Re-runs always produce a "v1 → v2 changes" header** in the new document, listing what was modified and why.
3. **If a re-run produces a v2 that is structurally identical to v1**, do not save a redundant v2 — note this in the change log instead.
4. **Re-runs honour the original document's evidence discipline** — every change in v2 must cite a source (the client validation, in this case, with the specific finding ID).
5. **Re-runs do not delete v1.** Always two views.

## When the matrix says "no re-run" but the user wants one

The matrix is a guideline, not a hard rule. The user can override:

```
/digital-marketing-pro:engagement re-run-decision --override "rerun 3.3"
```

This forces a re-run even if the matrix didn't trigger it. Useful when the user has external context that justifies a refresh (e.g., a major industry event since v1 was produced).

## When the matrix triggers re-runs but the user wants to skip

```
/digital-marketing-pro:engagement re-run-decision --skip "rerun 4.4"
```

This skips a triggered re-run. Useful when the changed information is minor and the user judges v1 is still good enough. The skipped re-run is logged so future audits can understand why v1 wasn't refreshed.

## Audit trail

Every re-run decision (auto-triggered, override, skip) is logged to `_engagement.json` under the `rerun_decisions` array:

```json
{
  "rerun_decisions": [
    {
      "timestamp": "2026-05-03T12:00:00Z",
      "trigger": "competitors changed",
      "triggered_reruns": ["3.1", "3.2", "3.3", "3.4", "4.1", "4.2"],
      "user_decision": "approved",
      "executed_reruns": ["3.1", "3.2", "3.3", "3.4", "4.1", "4.2"],
      "skipped_reruns": [],
      "notes": "client added 2 new competitors and removed 1"
    }
  ]
}
```

This audit trail lets future engagement reviews understand what was re-run, when, and why.

## Related references

- [two-views-model.md](two-views-model.md) — the v1/v2 architecture
- [engagement-flow-methodology.md](engagement-flow-methodology.md) — the 12-Part flow context
- [update-back-rule.md](update-back-rule.md) — what happens for corrections AFTER Part 7
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall