capture-learning

$npx mdskill add Kastalien-Research/thoughtbox/capture-learning

Captures and structures key learnings from work sessions for future reuse.

  • Helps users document non-obvious insights and reusable patterns from sessions.
  • Relies on file system to write to project memory, rules, or MEMORY.md.
  • Reflects on problems, solutions, patterns, and failures to extract learnings.
  • Stores structured learnings with freshness labels and calibrates existing ones.

SKILL.md

.github/skills/capture-learningView on GitHub ↗
---
name: capture-learning
description: Capture significant learnings from the current work session. Structures insights for future sessions and updates agent memory.
argument-hint: "[optional topic or context]"
user-invocable: true
---

Reflect on the current session and capture learnings. Context: $ARGUMENTS

## Process

### 1. Reflect
- What was the main problem being solved?
- What non-obvious insights emerged?
- What patterns are reusable in future work?
- What failed and why?

### 2. Structure the Learning

Format each learning as:

```
### [Date]: [Title]
- **Issue**: [The problem encountered]
- **Solution**: [What worked]
- **Pattern**: [The reusable principle extracted]
- **Files**: [Key file references, if applicable]
- **Freshness**: HOT (actively relevant) | WARM (occasionally relevant) | COLD (reference only)
```

### 3. Store

Write the learning to the appropriate location:
- **Agent-specific patterns**: Update the relevant agent's project memory
- **Project-wide rules**: Add to `.claude/rules/` as a new file or append to an existing one
- **Debugging insights**: Add to auto-memory `MEMORY.md`

### 4. Calibrate

Check existing learnings for staleness:
- Are any HOT items now WARM or COLD?
- Are any previous learnings contradicted by what we learned today?
- Remove or update anything that's no longer accurate.

More from Kastalien-Research/thoughtbox

SkillDescription
assumptionsManage the assumption registry — track, verify, and query assumptions about external dependencies and system behavior. Prevents costly rediscovery of known failures.
claude-opus-4-6-prompting>
claude-promptWrite or improve prompts for Claude using Anthropic's official best practices. Creates system prompts, agent prompts, tool descriptions, and MCP resource templates. Pass an existing prompt to improve it, or describe what you need to create one from scratch.
coolify-composeConvert Docker Compose files to Coolify templates. Use when creating Coolify services, converting docker-compose.yml for Coolify deployment, working with SERVICE_URL/SERVICE_PASSWORD magic variables, or troubleshooting Coolify compose errors.
crafting-effective-readmesUse when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.
diagramGenerate architecture diagrams for a codebase subsystem or module. Explores source files and produces Mermaid diagrams in docs/.
diataxisStructure, classify, and write documentation using the Diátaxis framework. Use when writing docs, README files, guides, tutorials, how-to guides, API references, or organizing documentation architecture. Also use when asked to improve documentation, restructure docs, decide what type of doc to write, or classify existing content. Covers tutorials, how-to guides, reference, and explanation.
escalateFormat a structured escalation to the human decision-maker (Chief Agentic). Use when hitting an escalation threshold.
frontend-design-principlesCreate polished, intentional frontend interfaces. Use this skill when building any UI — dashboards, admin panels, landing pages, marketing sites, or web applications. Routes to specialized guidance based on context.
hddDEPRECATED — use workflow Stage 2 (spec + frontmatter claims). Historical HDD docs are in docs/decisions/archive/.