Retrospective

After completing a significant task or experiment, documents what worked, what failed, and key learnings. Activates when a multi-step task finishes or when user says "done", "finished", "that worked", or asks for a summary. Failed attempts get documented first - they're read more than successes.

62 stars 2 forksProductivity & Notes

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ElliotJLT/Claude-Skill-Potions --skill retrospective
Manual install
git clone --depth 1 https://github.com/ElliotJLT/Claude-Skill-Potions.git /tmp/Claude-Skill-Potions
mkdir -p ~/.claude/skills
cp -r /tmp/Claude-Skill-Potions/skills/retrospective ~/.claude/skills/retrospective

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Retrospective

<purpose>
Knowledge capture at task completion. The Sionic AI insight: "Failed Attempts"
tables get read more than any other documentation section. Success paths are
nice. Failure paths save real time. This skill ensures both get documented
before context is lost.
</purpose>

## When To Activate

<triggers>
After completing significant work:

- Multi-step implementations (3+ distinct phases)
- Debugging sessions that found the root cause
- Experiments or spikes that reached a conclusion
- Tasks where you tried multiple approaches

User signals completion:
- "That worked"
- "Done" / "Finished" / "Ship it"
- "Can you summarize what we did?"
- Explicit request for retrospective
</triggers>

## Instructions

### Step 1: Capture Failed Attempts First

Document what DIDN'T work before it fades from memory:

```markdown
## Failed Attempts

| Approach | Why It Failed | Time Spent |
|----------|---------------|------------|
| [First thing tried] | [Specific reason] | [Estimate] |
| [Second thing tried] | [Specific reason] | [Estimate] |
```

Be specific about WHY it failed. "Didn't work" is useless. "Race condition
between auth callback and state update" is useful.

### Step 2: Document The Working Solution

```markdown
## What Worked

**Final approach:** [One sentence summary]

**Key insight:** [The "aha" moment that unlocked the solution]

**Implementation:**
1. [Step 1]
2. [Step 2]
3. [Step 3]
```

### Step 3: Extract Learnings
Read the full skill on GitHub

Details

Skill name
retrospective
Path
skills/retrospective/SKILL.md
License
MIT
Repo updated
12 February 2026

FAQ

What does the Retrospective skill do?

After completing a significant task or experiment, documents what worked, what failed, and key learnings. Activates when a multi-step task finishes or when user says "done", "finished", "that worked", or asks for a summary. Failed attempts get documented first - they're read more than successes.

How do I install the Retrospective skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ElliotJLT/Claude-Skill-Potions --skill retrospective. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Retrospective popular?

It lives in ElliotJLT/Claude-Skill-Potions, which has 62 GitHub stars and 2 forks.

Related skills

Agent Audit

62

ElliotJLT/Claude-Skill-Potions

When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, and strips the agent to minimum viable form. Answers: "What can we remove without degrading quality?" The goal is the leanest agent that still works.

AI, LLMs & Agents

Battle Plan

62

ElliotJLT/Claude-Skill-Potions

Before ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in sequence: rubber-duck (clarify scope) -> pre-mortem (assess risks) -> eta (estimate time) -> final confirmation. Do not start coding until the battle plan is approved.

Software Development

Breadcrumbs

62

ElliotJLT/Claude-Skill-Potions

Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records what was tried, what worked, what failed, and context for next time. On session start, reads breadcrumbs to understand history. Session-to-session memory without manual updates.

Productivity & Notes

Skill Gate

62

ElliotJLT/Claude-Skill-Potions

Before starting any significant task, force explicit evaluation of available skills. For each potentially relevant skill, state YES/NO with reasoning. Only proceed to implementation after skills have been consciously evaluated and activated. Prevents the ~50% "coin flip" activation rate that occurs when skills are passively available but not deliberately considered.

Productivity & Notes

Obsidian Vault Search

62

ElliotJLT/Claude-Skill-Potions

Searches an Obsidian vault intelligently — combines CLI search, frontmatter filtering, content grep, and wikilink traversal. Goes beyond keyword search to find notes by property, by link, by folder, and by content. Activates on "find in vault", "search vault", "which note has", "where did I write about", or when looking for specific notes in Obsidian.

Productivity & Notes

External Comms

45

Azure-Samples/agent-skills-dotnet-demo

PAO workflow for scanning, drafting, and presenting community responses with human review gate

Productivity & Notes11

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.