63-campaign-retrospective-global
Skill644 starsChanged 6 months agoMITView on GitHub
Use when a campaign has ENDED and the team needs a structured retrospective — a scorecard against target, what worked, what did not, and why with evidence, surprises, process review, lessons written back into the playbook and Brand Hub, and action items with owners. Trigger on 'campaign retrospective', 'campaign retro', 'post-mortem', 'campaign debrief', 'what worked and what did not', 'the campaign is over, what did we learn'. Also use when a campaign underdelivered and the team is arguing about why. Not for — a periodic performance report, see `07-marketing-report-global`; diagnosing live numbers mid-flight, see `03-performance-eval-global`; the next period ads plan, see `57-next-ads-plan-global`.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- minhnv0807/ai-business-skillsword for word, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 1
- minhnv0807/ai-business-skills★ 644100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository134 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- 00-marketing-plan-globalSkill
- 01-content-calendar-globalSkill
- 02-campaign-brief-globalSkill
- 03-performance-eval-globalSkill
- 04-script-video-globalSkill
- 05-ad-copy-globalSkill
- 06-ugc-egc-brief-globalSkill
- 07-marketing-report-globalSkill
- 08-competitor-research-globalSkill
- 09-customer-insight-globalSkill
- 10-reverse-kpi-globalSkill
- 11-channel-setup-globalSkill
- 12-landing-page-brief-globalSkill
- 13-data-analysis-globalSkill
- 14-email-marketing-globalSkill
- 15-social-listening-globalSkill
- 16-marketing-psychology-globalSkill
- 17-pricing-strategy-globalSkill
- 18-referral-program-globalSkill
- 19-ab-test-setup-globalSkill
- 20-client-intake-brief-globalSkill
- 21-ads-audit-globalSkill
- 30-design-master-globalSkill
- 31-offer-design-globalSkill
- 32-seo-growth-globalSkill
- 33-b2b-lead-gen-globalSkill
- 34-ai-marketing-os-globalSkill
- 35-brand-voice-globalSkill
- 36-content-brief-globalSkill
- 37-social-caption-globalSkill
- 38-community-seeding-globalSkill
- 39-content-audit-globalSkill
- 40-next-content-plan-globalSkill
- 41-campaign-asset-list-globalSkill
- 42-image-brief-globalSkill
- 43-carousel-brief-globalSkill
- 44-video-editor-brief-globalSkill
- 45-design-tool-brief-globalSkill
- 46-brand-guideline-globalSkill
- 47-design-review-globalSkill
- 48-quick-visual-brief-globalSkill
- 49-html-email-template-globalSkill
- 50-asset-resize-globalSkill
- 51-audience-research-globalSkill
- 52-account-structure-globalSkill
- 53-tracking-setup-globalSkill
- 54-media-plan-globalSkill
- 55-scaling-ads-globalSkill
- 56-retargeting-plan-globalSkill
- 57-next-ads-plan-globalSkill
- 58-positioning-globalSkill
- 59-go-to-market-globalSkill
- 60-launch-playbook-globalSkill
- 61-budget-planning-globalSkill
- 62-marketing-review-globalSkill
- 64-team-brief-globalSkill
- 65-team-performance-review-globalSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Ask up to 4 questions:
- Distinctive: line 36
How long ago did the campaign end?: Run the retro within 5 days of the end, while memory is fresh.
- Distinctive: line 40
Mandatory after every major campaign: No skipping because the team is busy.
- Very specific: line 68
When comparing against category benchmarks, use the right region and industry row in references/benchmarks-global.md — and adjust for …
- Distinctive: line 127
Every action item needs an owner and a deadline — never "the whole team will handle it."
- Distinctive: line 139
Ground rules: no individual blame, systems and process only.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Campaign Retrospective (Global)
A retrospective is not for assigning blame — it is how the team and the system get better after every campaign. The best insight comes from failure, but only if it is safe to speak honestly. A retro with no action is wasted time: every lesson must become one concrete change in the playbook, the Brand Hub, or the process.
Information gathering
Ask up to 4 questions:
- Which campaign, and over what dates? Name, start and end dates, original objective.
- Final data: revenue, leads, CPA, ROAS, spend — final numbers versus target. (If a report already exists from
07-marketing-report-global, use it as the input.) - Who attends the retro? Content, performance, design, sales, leader?
- How long ago did the campaign end? Run the retro within 5 days of the end, while memory is fresh.
Principles
- Mandatory after every major campaign. No skipping because the team is busy. No retro means paying tuition without learning the lesson.
- Record only claims backed by data. "Creative A felt strong" is not an insight; "creative A hit $18 CPA against a $28 account average" is.
- No individual blame. Talk about systems and process. Everyone has the floor.
- Every lesson becomes one concrete change — to the playbook, a template, the Brand Hub, or a process — with an owner and a deadline.
- Document so it still makes sense in 6 months — and link the retro into the next campaign's brief.
Workflow
1. Prepare (before the session)
- Pull final data: revenue, leads, CPA, ROAS, spend, timeline adherence, budget variance.
- Send the data to the team before the meeting — the meeting is for discussion, not for reading numbers.
- Book 60 minutes with a named facilitator (usually the leader). For distributed teams, pick a time that works across the relevant timezones and require written pre-reads from anyone who cannot attend live.
2. Campaign scorecard
| KPI | Target | Actual | % achieved | vs previous campaign |
| Revenue | ||||
| Leads | ||||
| CPA | ||||
| ROAS | ||||
| Spend | ||||
| Timeline (on schedule?) | ||||
| Budget (within plan?) |
Overall verdict: Success (>90% of KPIs) / Mixed (60-90%) / Miss (<60%).
When comparing against category benchmarks, use the right region and industry row in references/benchmarks-global.md — and adjust for seasonality before declaring a CPA increase a failure, since Q4 media costs run materially above Q1.
3. What worked (repeat next time)
| # | What worked | Evidence (numbers) | Why it worked | How to apply next time |
| 1 | ||||
| 2 | ||||
| 3 |
Name the winning patterns explicitly:
- Content angle: which angle converted best
- Creative format: video / image / carousel — which performed
- Audience: which segment responded
- Timing: which day or hour performed best
- Channel: best CPA and ROAS
4. What did not work (avoid next time)
| # | What failed | Evidence | Root cause | Decision: stop / fix / retest |
| 1 | ||||
| 2 |
Root cause must go past the symptom. "The ads were bad" is not a root cause; "audience overlapped with the previous campaign > frequency rose above 4 > CTR fell below 1%" is.
5. Surprises
- Positive surprises: what beat expectations, by how much, why — what do you take from it?
- Negative surprises: what came in worse, by how much, why — how do you prevent it?
6. Process and execution review
| Item | Assessment | Problems hit | Improvement |
| Brief quality | |||
| Timeline adherence | |||
| Team communication | |||
| Review and approval process | |||
| Launch-day execution | |||
| Data and tracking setup |
Biggest process bottleneck: the single thing most worth fixing next time.
7. Team callouts
Record specific contributions: [Name] — [the specific contribution and its positive impact on the result]. Recognize publicly, correct privately.
8. Playbook and Brand Hub updates plus action items
| Document to update | What changes | Owner | Deadline |
Launch playbook (60-launch-playbook-global) | Add or amend step: [X] | Leader | |
| Campaign brief template | Adjust section: [Y] | Leader | |
| Brand Hub — customer insight | Add new insight from this campaign: [Z] | ||
| Brand Hub — KPI framework / internal benchmarks | Update the benchmarks you actually achieved (CPA, CVR) | ||
| Winning creative library | Store the winners plus the reason they won |
Every action item needs an owner and a deadline — never "the whole team will handle it."
9. Input for the next campaign
- 3 things to definitely repeat: 1... 2... 3...
- 3 things to definitely do differently: 1... 2... 3...
- Hypothesis to test next campaign: [hypothesis + how it will be measured]
Facilitation guide
- Timing: within 5 days of campaign end.
- Format: 60 minutes, full team, facilitator (leader): 10 min scorecard > 15 min what worked > 15 min what did not > 10 min process > 10 min action items and owners.
- Ground rules: no individual blame, systems and process only; everyone speaks; constructive, not a venting session.
- After: the leader publishes the document within 24 hours, shares it with the team and leadership, and links it into the next campaign brief.
Output structure
File name: campaign-retro-[campaign-name]-[YYYYMMDD].md — the 9 sections above: scorecard > what worked > what did not > surprises > process review > team callouts > playbook and Brand Hub updates > input for the next campaign > action items with owners.
Related skills
07-marketing-report-global: the final report supplies the scorecard data.60-launch-playbook-global: execution lessons are written directly back into the playbook.02-campaign-brief-global: the "lessons from the previous campaign" section of a new brief comes from this retro.34-ai-marketing-os-global: new insights and real benchmarks are written into the Brand Hub.65-team-performance-review-global: team callouts and observations feed individual reviews at period end — keep the two documents separate.
Quality checklist
- Retro run within 5 days of campaign end
- Scorecard covers all KPIs against target with a Success/Mixed/Miss verdict
- Every "what worked" and "what did not" entry has numeric evidence — no impressions
- Failures trace to a real root cause, not a symptom
- Benchmark comparisons adjusted for region, industry, and season
- At least one playbook update and one Brand Hub update
- Every action item has an owner and a deadline
- 3 things to repeat, 3 things to change, and a hypothesis for next time
- No individual blame anywhere in the document
- Document shared within 24 hours and linked into the next campaign brief
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

