Skip to main content
skill CX Codex

project-retrospective — Claude Code skill: generates LESSONS.md

project-retrospective creates LESSONS.md files that capture project knowledge and failures. Use when closing a project or investigation to record what worked, what didn't, and specific action items before the team moves on.

MIT 189 installs ★ 458 updated 2026-10-24

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add jamditis/claude-skills-journalism --skill project-retrospective -a claude-code
Open on GitHub

What project-retrospective does

This skill structures meaningful project retrospectives by rejecting blameless theater. Instead of hunting for a single root cause, it maps the system: what signals existed, how people interpreted them, what they were trying to accomplish, what they did. It separates the system layer from human action within that system.

The skill provides sections for what worked and what didn't, a critical "The real problem" section (what we thought we were building vs. what was actually needed), and an action-item table with owners and deadlines. It works for live-event retros (election night, breaking news—written within 48 hours) and project-close retrospectives (typically within a month). Draws on Google SRE practice, US Army After Action Review structure, and current incident-analysis approaches.

What it helps with

  • Capture lessons before the team disperses and details fade
  • Surface systemic issues instead of blaming individuals
  • Identify the gap between what you planned to build and what was actually needed
  • Write concrete action items with owners and deadlines, not vague recommendations
  • Debrief a live event while details are still fresh

Example prompts for the agent

  • Write a retrospective of the project with architectural mistakes we made
  • Create a LESSONS.md file for our live-blog's after-action review during election night
  • Analyze why we spent three months building a feature no one ended up using

How to install project-retrospective

1Skills CLI (Vercel)

npx skills add jamditis/claude-skills-journalism --skill project-retrospective -a claude-code

2Manually: put the files in place

~/.claude/skills/project-retrospective/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/project-retrospective/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about project-retrospective

How do I install project-retrospective in Claude Code?

Run npx skills add jamditis/claude-skills-journalism --skill project-retrospective -a claude-code, then edit ~/.claude/skills/project-retrospective/SKILL.md.

What does project-retrospective do?

It helps write LESSONS.md files by structuring retrospectives to separate system problems from human actions, uncover the real gap between what you planned and what was needed, and generate concrete action items with owners and deadlines.

When should I run a retrospective?

Pre-define triggers before incidents happen: live-event failure (downtime during breaking news), editorial process failure (missed correction), tool failures affecting readers, or explicit stakeholder request. Write within one week while memory is fresh.

Source text

SKILL.md · MIT
---
name: project-retrospective
description: Generates LESSONS.md files capturing institutional knowledge and failures. Use when closing out projects or investigations.
---

# Project retrospective writer

Create LESSONS.md files that capture institutional knowledge, especially failures. Think like a journalist writing about your own project, be specific, be honest, name the actual mistakes.

## Frame the retrospective: blame-aware, not pure-blameless

The 2024–2026 consensus in incident-analysis writing (PagerDuty, J. Paul Reed, Lorin Hochstein) is that pure blamelessness is neurobiologically unrealistic, humans default to blame. Healthier framing: acknowledge the blame bias exists and counter it deliberately. Source: https://postmortems.pagerduty.com/culture/blameless/

Cognitive biases to counter explicitly:
- **Fundamental attribution error**, blaming individuals for failures the system permitted
- **Confirmation bias**, looking for evidence that confirms a pre-formed narrative
- **Hindsight bias**, judging past decisions by knowledge that wasn't available at the time
- **Negativity bias**, over-weighting what went wrong vs. what worked

The voice rule isn't "no blame", it's "name the system that permitted the human action, not just the action."

## Drop the single-root-cause framing

Allspaw's canonical critique (still the dominant view in 2024–2026) calls Five Whys / single-root-cause analysis "seductively satisfying and compellingly simple, but false." It locks analysts into a linear causal chain that terminates in individual blame. Source: https://www.kitchensoap.com/2014/11/14/the-infinite-hows-or-the-dangers-of-the-five-whys/

Use "how" narratives instead, gathering on four prompts:
- **Cues**, what signals were available, who saw them when?
- **Interpretation**, how did people make sense of those signals?
- **Goals**, what were people trying to accomplish?
- **Taking action**, what did they do, and what did they expect to happen?

The retrospective's job is to surface contributing factors, not declare a root cause.

## When to run a retrospective

Pre-define triggers before incidents happen, not after. Google SRE specifies criteria: user-visible downtime past a threshold, any data loss, on-call rollbacks, monitoring failures requiring manual discovery, stakeholder request. Source: https://sre.google/sre-book/postmortem-culture/

Translated to journalism:

| Trigger | Examples |
|---|---|
| Live-event failure | Live-blog downtime during election night, breaking-news embed breakage, paywall regression mid-investigation |
| Editorial process failure | Missed correction window, source-management breach, fact-check process bypass |
| Tool failure affecting subscribers | CMS migration regression, paywall logic affecting >X% of readers |
| Stakeholder request | Editor / publisher / source explicitly asking "what happened?" |

Pre-defined triggers prevent retrospective theater on routine work and ensure they happen on real failures.

## Timing: aim for under one week

Google's good-vs-bad postmortem comparison cites a "four months later" example as a quality failure because contributors' memories had decayed. Source: https://sre.google/workbook/postmortem-culture/

Recommended cadence:

| Project type | Target window |
|---|---|
| Live-event retro (election night, breaking news) | Same-day debrief, written within 48h |
| Tool / CMS incident | Within one week |
| Investigation or publication launch | Within one month of project close |
| Annual review of ongoing initiative | Once per year, scoped to discrete decision points |

The empirical floor is "fresh in contributors' minds." Past one week and the narrative gets reconstructed rather than remembered.

## For event-type retros, use AAR structure

The US Army's After Action Review (FM 7-0 Appendix K) was designed for facilitated post-event debriefs and fits live-news realities better than a project-close template. Source: https://www.first.army.mil/Portals/102/FM%207-0%20Appendix%20K.pdf

Four prompts:
1. **What was supposed to happen?**
2. **What did happen?**
3. **What was right or wrong about the difference?**
4. **How do we perform to standard next time?**

Run AAR immediately after the event with all participants, election night newsroom team, live-blog runners, breaking-news desk. Use `event.md` template for this; project-close templates are wrong for live-event retros.

## The critical section: "The real problem"

This is the most valuable part of any retrospective. It answers:

> "What did we THINK we were building vs. what was ACTUALLY needed?"

**Strong example:**
> We built an admin dashboard for editors when they actually needed a Slack bot. They live in Slack, forcing them to open a web app was friction they'd never accept. The dashboard has 2 monthly active users; the Slack bot prototype we built in a day has 47.

**Weak example:**
> We learned the importance of user research.

## Template structure

```markdown
# LESSONS.md

## Project
- **Name:** [Project name]
- **Dates:** [Start - End]
- **Status:** [Completed / Abandoned / Ongoing]
- **Author:** [Your name]
- **Retrospective written:** [Date, should be within timing window above]

## Summary
[One paragraph: what it did, what impact it had, why it matters]

## What worked

### Technical wins
- [Specific decision and WHY it worked]
- [Tool/pattern that saved time]

### Process wins
- [Methodology that helped]
- [Communication pattern that worked]

## What didn't work

For each item below, separate the system layer from the people layer.
"What did the system permit or require?" comes before "What did the
people inside that system do?"

### Critical failures
- **System:** [What the architecture / process / tooling permitted]
- **People:** [What humans did inside that constraint]
- **Cost:** [Quantified impact: hours, subscribers affected, money]

### Technical debt
- [Shortcut that hurt later, and why it was the rational choice at the time]
- [Complexity that wasn't needed]

### External factors
- [Things outside your control that impacted the project]

## The real problem

What we thought: [Initial assumption]
What was actually needed: [Reality]
The gap cost us: [Time / effort / money wasted]

## Action items

Each item must have an owner, a deadline, a tracker URL, and a priority.
"Postmortems without subsequent action are indistinguishable from no postmortem."
- Google SRE

| # | Action | Owner | Deadline | Tracker | Priority |
|---|--------|-------|----------|---------|----------|
| 1 | [Specific change] | [Name] | [Date] | [Issue URL] | P0 / P1 / P2 |
| 2 | [Specific change] | [Name] | [Date] | [Issue URL] | P0 / P1 / P2 |

Failure modes to avoid:
- Ambiguous wording ("make automation better")
- Equal priority across all items (defeats the purpose of priority)
- No tracker bug or issue URL (action items vanish)
- Fixes targeting human behavior instead of system redesign ("be more careful")

Add a 30/60/90-day check-in note: who reviews progress on these, and when.

## Reusable artifacts

| Component | Why it's valuable |
|-----------|-------------------|
| [Name] | [Specific reuse potential] |
| [Name] | [Why someone else should use this] |

## Questions for next time
- [Unanswered questions worth investigating]
- [Things you'd research before starting]
```

## Voice guidelines

- Honest, specific, slightly self-deprecating
- Like explaining to a friend why the project took twice as long
- Name what the system permitted, then what the people did inside it
- Specific mistakes, not vague "challenges"
- Active voice; avoid "mistakes were made" passives that hide who decided what

## Sourcing-decision retrospectives (journalism-native)

The canonical SRE / AAR / Allspaw frameworks don't cover the editorial-judgment retrospective an investigation needs. The `research-project.md` template adds a "Source decisions revisited" section:

- Which sources we trusted, and why?
- Which we declined, and why?
- What was the redaction logic? Did it hold up?
- What would we reconsider if we ran the investigation again?
- What patterns should we carry forward to the next investigation?

Newsroom engineering blogs (NYT Open, ProPublica News Apps, WaPo Engineering) publish project descriptions but rarely retrospective methodologies, so this is treated as a journalism-native extension to the system rather than borrowed from precedent.

## What to include vs exclude

| Include | Exclude |
|---------|---------|
| Specific failures with quantified context | Vague "learnings" |
| Actual time / cost of mistakes | Blame for individuals |
| What the system permitted (then what humans did) | "Mistakes were made" passives |
| Tools that helped or hurt, by name | Generic best practices |
| Decisions you'd reverse, and why now, not then | Obvious statements |
| Surprising discoveries | Information already in other docs |

## The specificity test

For each item in "What didn't work," ask:
- Can I name the specific decision?
- Can I quantify the impact?
- Did I separate what the system permitted from what the people did?
- Would this help someone avoid the same mistake?

If no to any → be more specific.

## Red flags in your writing

If you find yourself writing these, stop and be more specific:
- "Communication is key"
- "We learned the importance of..."
- "Going forward, we should..."
- "Challenges included..."
- "There were some issues with..."
- "Mistakes were made" (who made them? in what system?)

These are placeholders for real insights. Replace them.

## Examples of good vs bad entries

**Bad, too vague:**
> - Communication could have been better
> - We underestimated the complexity
> - Testing was insufficient

**Good, specific and actionable:**
> - The schema validation step was disabled in CI for the data-import script (system) and the freelance reporter who imported new entries didn't know it had been disabled (people). Cost: 3 hours debugging a typo that caused silent failures across 12 published stories.
> - We built a custom date picker when the browser native input would have worked. Tracker: ENG-1247. Owner: K. Park. 2 days wasted.

## Journalism-specific templates

Templates are in the `templates/` directory:

| Template | Use for |
|----------|---------|
| `research-project.md` | Investigations, data journalism projects (includes sourcing-decision retro) |
| `event.md` | Conferences, workshops, campaigns (uses AAR structure) |
| `publication.md` | Newsletters, podcasts, ongoing content |
| `editorial-tool.md` | Newsroom software, AI tools |

### Template selection

```
What kind of project?
├── Investigation/analysis → research-project.md
├── Conference/workshop/election night → event.md (use AAR)
├── Newsletter/podcast → publication.md
└── Newsroom tool → editorial-tool.md
```

## Last currency sweep

2026-05-09. Sources verified: kitchensoap.com (Allspaw "Infinite Hows"), postmortems.pagerduty.com, sre.google/sre-book and /workbook, first.army.mil FM 7-0 Appendix K, adaptivecapacitylabs.com.

---

*The best retrospectives are written by people who got burned and want to save others from the same fate.*

© jamditis · MIT · jamditis/claude-skills-journalism

Similar skills

All skills for Writing and docs →

From the same set35

The whole set →
content-access content-access is a Claude Code skill that describes ethical and legal workflows for journalists and researchers to access paywalled publications and research papers through open access APIs. CX Codex +1 201installs digital-archive Design a digital archive that brings material from different sources into one schema, adds AI-assisted classification, and connects referenced entities. CX Codex +1 198installs zero-build-frontend zero-build-frontend — a skill for building frontend code that runs directly in the browser without a build step. Covers static sites, browser extensions, maps, and lightweight data-backed interfaces. CX Codex +1 198installs free-apis-catalog free-apis-catalog is a Claude Code skill listing free APIs and verified free-tier limits for news, weather, US public records, and social platforms. It helps agents choose a data source instead of inventing an endpoint. CX Codex +1 191installs python-pipeline python-pipeline is a Claude Code skill for modular Python data pipelines, batch jobs, content routing, and Google Sheets or Drive integrations. CX Codex +1 189installs api-hardening api-hardening is a Claude Code skill for hardening APIs built with Express, FastAPI, or serverless. It activates for work on rate limits, CORS, input checks, API keys, and OWASP API risks. CX Codex +1 186installs project-memory project-memory generates project instruction files like AGENTS.md or CLAUDE.md to pass institutional knowledge to AI agents without generic clutter. CX Codex +1 180installs mobile-debugging mobile-debugging hands the agent a method for opening a JS console on a phone or tablet and debugging pages without desktop DevTools: Eruda, vConsole, USB inspection. CX Codex +1 176installs

Project sponsors

Companies that keep this analytics open