Skip to content
Agentmart
Submit a tool

consistency-check

Finds and fixes internal inconsistencies in a software project — code vs configuration vs documentation drift, plus linter findings.

Skill by viktor-ferenczi

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying consistency-check?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/viktor-ferenczi-consistency-check

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Finds and fixes internal inconsistencies in a software project — code vs configuration vs documentation drift, plus linter findings. Use after a larger change or refactoring, before a release, or when the user asks to check/clean up the consistency of the project.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/consistency-check

What's inside

Skill name
consistency-check
Description
Finds and fixes internal inconsistencies in a software project — code vs configuration vs documentation drift, plus linter findings. Use after a larger change or refactoring, before a release, or when the user asks to check/clean up the consistency of the project.
License
MIT
Instructions
31 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Check the project for internal inconsistencies and fix what you find. Work through the passes below in order.
Cap each pass at **3 iterations**; if issues remain after that, stop fixing and list them in the final report instead.

1. **Code ↔ code.** Look for drift within the codebase:
   - References to renamed/removed symbols, files, endpoints, or CLI flags (grep for old names after renames).
   - The same constant, magic value, or default duplicated with different values in different places.
   - Inconsistent naming for the same concept across modules.
   - Dead exports/imports and commented-out code left behind by refactorings.
2. **Configuration ↔ code.** Compare configuration against what the code actually reads:
   - Config keys, environment variables, and feature flags that the code no longer reads, or reads but are missing from config templates/examples.
   - Mismatched defaults between code and config files.
   - Build/CI files referencing scripts, paths, or targets that no longer exist.
3. **Linters.** Discover the project's linters and formatters instead of assuming any:
   check config files (e.g. `pyproject.toml`, `.eslintrc*`, `.golangci.yml`, `.editorconfig`), `package.json` scripts,
   `Makefile`/`justfile` targets, and CI workflows. Run what you find and fix the findings.
   If the project defines no linters, skip this pass — do not introduce new tools.
4. **Documentation ↔ code and configuration.** Update docs to match reality:
   - README/setup instructions that no longer work (commands, paths, prerequisites, version numbers).
   - Documented APIs, options, or behavior that changed in code.
   - Doc comments/docstrings contradicting the code they describe.
5. **Final cross-check.** Re-scan anything you modified in passes 1–4 for new inconsistencies introduced by the fixes
   (one pass only, no loop).

Remarks:
- Fix inconsistencies; do not redesign. If the correct resolution is ambiguous (e.g. code and docs disagree and either could be intended), ask the user instead of guessing.
- Never delete or disable tests to make a pass "consistent".
- Prefer programmatic checks (grep, existing linters, link checkers) over reading whole files.

Once done, provide a concise report: fixes made per pass, issues left unresolved (with why), and anything that needs the user's decision.

From viktor-ferenczi/skills, MIT.

More from viktor-ferenczi/skills

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Jul 4, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from viktor-ferenczi

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get consistency-check running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying consistency-check?

CallGet help
Cite this page

consistency-check skill. Agent Mart. https://agentmart.dev/skills/viktor-ferenczi-consistency-check (last updated 2026-10-24)