brycewang-stanford/techdebt
NewSkillScoreMaintainedFind and fix technical debt including duplicated code, dead code, outdated patterns, and code smells. Run at the end of sessions to clean up.
by brycewang-stanford
Links this skill to your agents and keeps it current with the author’s updates.
On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.
◆Coding pack
$decimalai skills pull brycewang-stanford-techdebt
Get this skill — curl · raw file
$curl -fsSL https://app.decimal.ai/s/brycewang-stanford-techdebt/SKILL.md
how this skill behaves on real traffic · last 30 days
No production data for this skill yet — usage numbers appear here once agents start running it.
Anonymized aggregate across every org using this skill — proof from real production use, not a demo.
Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents 22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago
—-19% tokens0% turns86% of whole cases pass with skill (19/22)
Showing 5 of 22 cases
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026
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
Importedbrycewang-stanford / Auto-Empirical-Research-Skills
skills/09-meleantonio-awesome-econ-ai-stuff/_skills/engineering/techdebt/SKILL.md
License NOASSERTIONImported 8/2/2026Version v1
Technical Debt Finder
Identify and fix technical debt in the codebase.
What to Look For
Code Duplication
- Functions with similar logic that could be consolidated
- Copy-pasted code blocks
- Repeated patterns that should be abstracted
Dead Code
- Unused imports
- Unused functions or classes
- Commented-out code blocks
- Unreachable code paths
Outdated Patterns
- Deprecated API usage
- Old-style string formatting (% or .format) vs f-strings
- Type hints using
typing.List instead of list - Missing type hints on public functions
Code Smells
- Functions longer than 50 lines
- Too many parameters (more than 5)
- Deep nesting (more than 3 levels)
- Magic numbers without constants
- Overly complex conditionals
Missing Best Practices
- Missing docstrings on public functions
- Missing error handling
- Hardcoded values that should be config
- Missing tests for critical paths
Workflow
- Scan the Codebase
- Look for patterns matching the issues above
- Prioritize by impact and ease of fix
- Report Findings
- List issues by category
- Include file paths and line numbers
- Estimate severity (high/medium/low)
- Fix Issues
- Start with high-severity, easy fixes
- Create atomic commits for each fix
- Run tests after each change
- Verify
- Run linter:
ruff check . - Run tests:
pytest - Ensure no new issues introduced
Arguments
Optionally specify a directory or file to focus on.
Usage:
/techdebt - Scan entire project/techdebt src/ - Scan specific directory/techdebt src/utils.py - Scan specific file
Output
Provide a summary of:
- Issues found (by category)
- Issues fixed
- Remaining items for future sessions
Want to see if brycewang-stanford/techdebt would activate on your phrasing? Try it before you install — no LLM call, no signup.