Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Lesson Learned · softaworks | DecimalAI

code reviewby softaworks

Lesson Learned

softaworks/lesson-learned

Source softaworks/agent-toolkit ↗License MIT

Analyze recent code changes via git history and extract software engineering lessons.

SkillScore61Maintained

Automatic

Coding pack

Last verified 8/14/2026

What it changes

Passed 12 of 19 test cases with the skill, and 8 of 19 without it.

Without skill43%

With skill61%

Checks it passed that the model alone missed

Includes the Takeaway for next time section label.
Applies a default scope of 5 commits when on the main branch.
Restricts code analysis strictly to files present in the diff.

and 6 more in the full report

8 fixed6 passed either way5 still failing4 broke

Pass-rate lift: +17 pp
Tokens: +31%
Agent turns: 0%
Response time: -17%

Model gemini-3.6-flashMeasured 8/14/2026v114 of 23 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/softaworks-lesson-learned/SKILL.md https://app.decimal.ai/s/softaworks-lesson-learned/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add softaworks-lesson-learned, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/softaworks-lesson-learned/ and pins it in .decimal/skills.lock

decimalai skills add softaworks-lesson-learned

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/softaworks-lesson-learned/SKILL.md https://app.decimal.ai/s/softaworks-lesson-learned/SKILL.md

Raw file: /s/softaworks-lesson-learned/SKILL.md ↗ · machine-readable summary at /s/softaworks-lesson-learned.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

I am ready to analyze a git commit for software engineering principles. What reference document must be loaded before performing the analysis phase?

What was checked, without and with the skill
Checked	Without skill	With skill
Loads references/se-principles.md before initiating code analysis.	Missed	Passed

case-12 · gemini-3.6-flash · 8/14/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md100 lines3 files

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.

Read references/se-principles.md to have the principle catalog available
Optionally read references/anti-patterns.md if you suspect the changes include areas for improvement
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.

Scope	Git Commands	When to Use
Feature branch	`git log main..HEAD --oneline` + `git diff main...HEAD`	User is on a non-main branch (default)
Last N commits	`git log --oneline -N` + `git diff HEAD~N..HEAD`	User specifies a range, or on main (default N=5)
Specific commit	`git show <sha>`	User references a specific commit
Working changes	`git diff` + `git diff --cached`	User 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

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

Phase 3: Analyze

Track record

Benchmark

12 / 19

test cases passed, vs 8 / 19 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

softaworks / agent-toolkit

skills/lesson-learned/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 2 files

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Lesson Learned

Before You Begin

Phase 1: Determine Scope

Phase 2: Gather Changes

Phase 3: Analyze

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills