/learn — Skill Extraction Workflow

Extract non-obvious discoveries into reusable skills that persist across sessions.

When to Use This Skill

Invoke /learn when you encounter:

• Non-obvious debugging — Investigation that took significant effort, not in docs
• Misleading errors — Error message was wrong, found the real cause
• Workarounds — Found a limitation with a creative solution
• Tool integration — Undocumented API usage or configuration
• Trial-and-error — Multiple attempts before success
• Repeatable workflows — Multi-step task you'd do again
• User-facing automation — Reports, checks, or processes users will request

Workflow Phases

PHASE 1: Evaluate (Self-Assessment)

Before creating a skill, answer these questions:

1. "What did I just learn that wasn't obvious before starting?"
2. "Would future-me benefit from this being documented?"
3. "Was the solution non-obvious from documentation alone?"
4. "Is this a multi-step workflow I'd repeat?"

Continue only if YES to at least one question.

PHASE 2: Check Existing Skills

Search for related skills to avoid duplication:

bash
1# Check project skills
2ls .claude/skills/ 2>/dev/null
3
4# Search for keywords
5grep -r -i "KEYWORD" .claude/skills/ 2>/dev/null

Outcomes:

• Nothing related → Create new skill (continue to Phase 3)
• Same trigger & fix → Update existing skill (bump version)
• Partial overlap → Update with new variant

PHASE 3: Create Skill

Create the skill file at .claude/skills/[skill-name]/SKILL.md:

yaml
1---
2name: descriptive-kebab-case-name
3description: |
4  [CRITICAL: Include specific triggers in the description]
5  - What the skill does
6  - Specific trigger conditions (exact error messages, symptoms)
7  - When to use it (contexts, scenarios)
8author: Claude Code Academic Workflow
9version: 1.0.0
10argument-hint: "[expected arguments]"  # Optional
11---
12
13# Skill Name
14
15## Problem
16[Clear problem description — what situation triggers this skill]
17
18## Context / Trigger Conditions
19[When to use — exact error messages, symptoms, scenarios]
20[Be specific enough that you'd recognize it again]
21
22## Solution
23[Step-by-step solution]
24[Include commands, code snippets, or workflows]
25
26## Verification
27[How to verify it worked]
28[Expected output or state]
29
30## Example
31[Concrete example of the skill in action]
32
33## References
34[Documentation links, related files, or prior discussions]

PHASE 4: Quality Gates

Before finalizing, verify:

• Description has specific trigger conditions (not vague)
• Solution was verified to work (tested)
• Content is specific enough to be actionable
• Content is general enough to be reusable
• No sensitive information (credentials, personal data)
• Skill name is descriptive and uses kebab-case

Output

After creating the skill, report:

✓ Skill created: .claude/skills/[name]/SKILL.md
  Trigger: [when to use]
  Problem: [what it solves]

Example: Creating a Skill

User discovers that a specific R package silently drops observations:

markdown
1---
2name: fixest-missing-covariate-handling
3description: |
4  Handle silent observation dropping in fixest when covariates have missing values.
5  results between packages.
6author: Claude Code Academic Workflow
7version: 1.0.0
8---
9
10# fixest Missing Covariate Handling
11
12## Problem
13The fixest package silently drops observations when covariates have NA values,
14which can produce unexpected results when comparing to other packages.
15
16## Context / Trigger Conditions
17- Sample size in fixest is smaller than expected
18- Results differ from Stata or other R packages
19- Model has covariates with potential missing values
20
21## Solution
221. Check for NA patterns before regression:
23   ```r
24   summary(complete.cases(data[, covariates]))

2. Explicitly handle NA values or use na.action parameter
3. Document the expected sample size in comments

Verification

Compare nobs(model) with nrow(data) — difference indicates dropped obs.

References

• fixest documentation on missing values
• [LEARN:r-code] entry in MEMORY.md