PluginBench
Skill
Review
Audit score 70

lesson-learned

softaworks/agent-toolkit

Extract software engineering lessons from your recent code changes via git history.

What is lesson-learned?

Analyzes actual code diffs and commit messages to identify specific, grounded software engineering principles at work in your recent changes. Use when you want to reflect on what you've learned from your own code—not a lecture, but a mirror showing what your changes already demonstrate.

  • Examines git history (feature branches, commit ranges, or working changes) to identify dominant patterns
  • Maps code changes to concrete software engineering principles from a reference catalog
  • Identifies structural decisions, trade-offs, and problems solved in your recent work
  • Suggests improvements gently as "next time, consider..." rather than criticism
  • Grounds every lesson in specific files, commits, and code references

How to install lesson-learned

npx skills add https://github.com/softaworks/agent-toolkit --skill lesson-learned
Prerequisites
  • Git repository with commit history
  • Access to references/se-principles.md (loaded automatically by the skill)
  • Optional: references/anti-patterns.md for identifying areas for improvement
Claude Code
Cursor
Windsurf
Cline

How to use lesson-learned

  1. 1.Invoke the skill with a scope: feature branch, last N commits, specific commit, or working changes
  2. 2.The skill loads the principles reference and determines scope (defaults to feature branch vs. main, or last 5 commits on main)
  3. 3.Provide git history and diffs; the skill reads commit messages and changed files
  4. 4.The skill identifies the dominant pattern and maps it to one or two key principles
  5. 5.Review the lesson output, which includes what happened, the principle at work, why it matters, and a concrete takeaway

Use cases

Good for
  • Reflect on a completed feature branch to understand what engineering principles guided your design
  • Extract lessons from the last 5 commits on main to reinforce good patterns you're already using
  • Analyze a specific commit to understand the trade-offs you made (readability vs. performance, DRY vs. clarity)
  • Review working changes before committing to identify structural decisions worth documenting
  • Identify missed opportunities in recent refactoring work
Who it's for
  • Software engineers wanting to reflect on and reinforce their own coding practices
  • Teams conducting lightweight code reviews focused on learning rather than approval
  • Developers seeking to articulate the principles behind their recent decisions
  • Anyone looking to extract actionable takeaways from their own work

lesson-learned FAQ

What if my recent changes are trivial (typo fix, config tweak)?

The skill will say so honestly rather than forcing a lesson. Not every change yields a deep insight—sometimes good housekeeping is just good housekeeping.

Can I analyze a specific commit instead of a branch or range?

Yes. Provide the commit SHA and the skill will analyze that single commit using `git show <sha>`.

What if the diff is very large?

The skill uses `git diff --stat` first to identify the most-changed files, then reads only the top 3-5 files to keep analysis focused and actionable.

Does the skill criticize my code?

No. It leads with what works and frames suggestions as "next time, consider..." rather than "you should have..." The goal is reflection, not judgment.

Can I get more than one lesson from a single analysis?

Yes, but the skill limits output to a maximum of 2–3 lessons. One well-grounded lesson beats seven vague ones.

Full instructions (SKILL.md)

Source of truth, from softaworks/agent-toolkit.


name: lesson-learned description: "Analyze recent code changes via git history and extract software engineering lessons. Use when the user asks 'what is the lesson here?', 'what can I learn from this?', 'engineering takeaway', 'what did I just learn?', 'reflect on this code', or wants to extract principles from recent work."

Lesson Learned

Extract specific, grounded software engineering lessons from actual code changes. Not a lecture -- a mirror. Show the user what their code already demonstrates.

Before You Begin

Load the principles reference first.

  1. Read references/se-principles.md to have the principle catalog available
  2. Optionally read references/anti-patterns.md if you suspect the changes include areas for improvement
  3. Determine the scope of analysis (see Phase 1)

Do not proceed until you've loaded at least se-principles.md.

Phase 1: Determine Scope

Ask the user or infer from context what to analyze.

ScopeGit CommandsWhen to Use
Feature branchgit log main..HEAD --oneline + git diff main...HEADUser is on a non-main branch (default)
Last N commitsgit log --oneline -N + git diff HEAD~N..HEADUser specifies a range, or on main (default N=5)
Specific commitgit show <sha>User references a specific commit
Working changesgit diff + git diff --cachedUser says "what about these changes?" before committing

Default behavior:

  • If on a feature branch: analyze branch commits vs main
  • If on main: analyze the last 5 commits
  • If the user provides a different scope, use that

Phase 2: Gather Changes

  1. Run git log with the determined scope to get the commit list and messages
  2. Run git diff for the full diff of the scope
  3. If the diff is large (>500 lines), use git diff --stat first, then selectively read the top 3-5 most-changed files
  4. Read commit messages carefully -- they contain intent that raw diffs miss
  5. Only read changed files. Do not read the entire repo.

Phase 3: Analyze

Identify the dominant pattern -- the single most instructive thing about these changes.

Look for:

  • Structural decisions -- How was the code organized? Why those boundaries?
  • Trade-offs made -- What was gained vs. sacrificed? (readability vs. performance, DRY vs. clarity, speed vs. correctness)
  • Problems solved -- What was the before/after? What made the "after" better?
  • Missed opportunities -- Where could the code improve? (present gently as "next time, consider...")

Map findings to specific principles from references/se-principles.md. Be specific -- quote actual code, reference actual file names and line changes.

Phase 4: Present the Lesson

Use this template:

## Lesson: [Principle Name]

**What happened in the code:**
[2-3 sentences describing the specific change, referencing files and commits]

**The principle at work:**
[1-2 sentences explaining the SE principle]

**Why it matters:**
[1-2 sentences on the practical consequence -- what would go wrong without this, or what goes right because of it]

**Takeaway for next time:**
[One concrete, actionable sentence the user can apply to future work]

If there is a second lesson worth noting (maximum 2 additional):

---

### Also worth noting: [Principle Name]

**In the code:** [1 sentence]
**The principle:** [1 sentence]
**Takeaway:** [1 sentence]

What NOT to Do

AvoidWhyInstead
Listing every principle that vaguely appliesOverwhelming and genericPick the 1-2 most relevant
Analyzing files that were not changedScope creepStick to the diff
Ignoring commit messagesThey contain intent that diffs missRead them as primary context
Abstract advice disconnected from the codeNot actionableAlways reference specific files/lines
Negative-only feedbackDemoralizingLead with what works, then suggest improvements
More than 3 lessonsDilutes the insightOne well-grounded lesson beats seven vague ones

Conversation Style

  • Reflective, not prescriptive. Use the user's own code as primary evidence.
  • Never say "you should have..." -- instead use "the approach here shows..." or "next time you face this, consider..."
  • If the code is good, say so. Not every lesson is about what went wrong. Recognizing good patterns reinforces them.
  • If the changes are trivial (a single config tweak, a typo fix), say so honestly rather than forcing a lesson. "These changes are straightforward -- no deep lesson here, just good housekeeping."
  • Be specific. Generic advice is worthless. Every claim must point to a concrete code change.