Install
$ agentstack add skill-nathanfaucett-agents-simplify ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Simplify
Simplify is a that helps engineers reduce complexity and unify code across a codebase. It focuses on extracting composable pieces, defining clearer module boundaries, and producing small, well-documented APIs that are easy to use and understand.
What it produces
- A short diagnosis describing complexity hotspots and recommended refactors.
- A prioritized list of small, refactor candidates (extracts, consolidations, interface clarifications).
- Changes that implement safe, minimal refactors.
- Rationale and tests or type-checks to run to validate behavioral safety.
Workflow (step-by-step)
- Scope: accept a target scope from the user file, directory, module name, or repo (default to whole repo).
- Discover: run lightweight analysis to find duplication, large functions, cross-module imports, and public-surface size.
- Propose: generate 1–3 prioritized refactor proposals with rationale and risk level.
- Apply: produce atomic, well-documented patches and tests
- Verify: run or suggest running tests/type-checks and list follow-ups.
Decision points & branching logic
- If duplication appears in >2 places and is self-contained → prefer
extract shared helper. - If a module has >N exported functions serving distinct subdomains → recommend splitting responsibilities into smaller modules.
- If a proposed change is potentially breaking (public signature change) → mark as
high riskand only propose, not apply. - If tests or type checks are missing for the touched area → prefer proposal + test scaffolding rather than automatic apply.
Quality criteria / completion checks
- All existing tests pass (if present) and static type checks succeed after changes.
- Cyclomatic complexity for modified functions decreases or is split into smaller helpers.
- Public API surface is smaller or better documented with examples.
- Duplication measured by similar code blocks is reduced for targeted hotspots.
- Run tests and type-checks where available before applying changes?
Expected outputs
- Human-readable summary of findings and prioritized refactor list.
- Concrete patch(es) and short instructions for verifying changes
- Add tests, update docs, and add migration notes.
Gotchas & edge cases
- Behavior changes are the primary risk; always prefer tests or type checks before applying non-trivial refactors.
- Large cross-cutting refactors may need coordination with downstream consumers; label those proposals as
coordination required. - Language or framework-specific idioms (macros, generated code, complex preprocessor steps) may require bespoke handling; call out these files and avoid blind edits.
Questions the skill will ask the user when scope is ambiguous
- Should I preserve public APIs exactly, or are breaking changes allowed with migration notes?
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: nathanfaucett
- Source: nathanfaucett/agents
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.