Skip to content

bg-szy/TOP-SKILLS / skills/agent-skills/avoid-ai-writing

avoid-ai-writing

Verified

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Supports detect-only audits, edit-in-place file cleanup, voice and context profiles, and an iterate-to-convergence pass.

FileKindSize
CHANGELOG.mdmarkdown9.2 KB
CONTRIBUTING.mdmarkdown4.4 KB
GLOSSARY.mdmarkdown3.5 KB
LICENSEother1.0 KB
LICENSE.txtmarkdown1.0 KB
PROOF.mdmarkdown7.2 KB
README.mdmarkdown35.7 KB
SKILL.full.mdmarkdown151.4 KB
SKILL.mdskill md34.8 KB
package.jsonmanifest1.5 KB

CHANGELOG.md

View on GitHub
# Changelog

All notable changes to the `avoid-ai-writing` skill will be documented in this file.

## [2026-11-16] - Catalog Freshness And Source Sync

### Added

- Refreshed the catalog metadata and retained-client portability baseline.
- Added the current upstream glossary input, HTML named-reference table, and focused preservation fixture required by the shipped self-scan, style/quote helpers, and detector tests.

### Changed

- Updated the catalog metadata and last-updated state for the 2026-11-16 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.
- Scoped the default test command to catalog-shipped suites; upstream monorepo packaging, GitHub Action, and retained-evaluation suites are excluded from this cross-client copy.
- Linked the omitted upstream issue template, corpus intake drafts, and dated
  calibration report at the pinned source revision instead of leaving broken
  local references in the catalog copy.

### Fixed

- Preserved explicit no-MCP fallbacks and the catalog's safety, approval, and source-boundary guidance.

## [2026-10-19] - Detector And Catalog Test Compatibility

### Added

- Declined Chinese and Japanese documents when unsegmented script characters dominate, matching the standalone detector workflow and avoiding a false clean score from whitespace-based word counts.

### Changed

- Marked the supported-contrast editorial card as judgment-only because the detector exposes no dedicated type for that frame.
- Adapted helper tests to the curated catalog layout and optional upstream evaluation archives without importing bulky evaluation artifacts.
- Aligned the root CLI's accepted context values with the shared detector API.

### Fixed

- Kept the root CLI and standalone detector aligned on shared scoring output while retaining standalone diagnostic counters.

## [2026-10-19] - Catalog Freshness And Source Sync

### Added

- Refreshed the catalog metadata and retained-client portability baseline.

### Changed

- Updated the catalog metadata and last-updated state for the 2026-10-19 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.

### Fixed

- Preserved explicit no-MCP fallbacks and the catalog's safety, approval, and source-boundary guidance.

## [2026-09-14] - Avoid AI Writing v3.35.0 Source Refresh

### Added

- Refreshed the catalog's mapped Avoid AI Writing core, detector, corpus, and measurement helpers from the upstream v3.35.0 source while retaining the cross-client catalog tail and safety boundaries.

### Changed

- Kept the catalog copy focused on runtime and verification support; upstream marketplace metadata, CI, and package-publishing metadata remain outside this skill while the current runtime CLI and gate entry points are retained.

### Fixed

- Updated detector-facing fixtures and corpus guidance, including the current false-positive preprocessing/comparison and bounded local regression checks, so supported local checks follow the upstream behavior.

## [2026-09-08] - Catalog Freshness And Source Sync

### Added

- Refreshed the catalog metadata and retained-client portability baseline.

### Changed

- Updated the catalog metadata and last-updated state for the 2026-09-08 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.

### Fixed

- Preserved explicit no-MCP fallbacks and the catalog's safety, approval, and source-boundary guidance.

## [2026-09-05] - Catalog Freshness And Source Sync

### Added

- Refreshed the catalog metadata and retained-client portability baseline.

### Changed

- Updated the catalog metadata and last-updated state for the 2026-09-05 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.

### Fixed

- Preserved explicit no-MCP fallbacks and the catalog's safety, approval, and source-boundary guidance.

## [2026-08-31] - Catalog Freshness And Source Sync

### Added

- Refreshed the catalog metadata and retained-client portability baseline.

### Changed

- Updated the catalog metadata and last-updated state for the 2026-08-31 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.

### Fixed

- Preserved explicit no-MCP fallbacks and the catalog's safety, approval, and source-boundary guidance.

## [2026-08-29] - Catalog Freshness And Source Sync

### Added

- Refreshed the catalog metadata and retained-client portability baseline.

### Changed

- Updated the catalog metadata and last-updated state for the 2026-08-29 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.

### Fixed

- Preserved explicit no-MCP fallbacks and the catalog's safety, approval, and source-boundary guidance.

## [2026-08-24] - Catalog Freshness And Source Sync

### Added

- Refreshed the catalog metadata and retained-client portability baseline.

### Changed

- Updated the catalog metadata and last-updated state for the 2026-08-24 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.

### Fixed

- Preserved explicit no-MCP fallbacks and the catalog's safety, approval, and source-boundary guidance.

## [2026-08-14] - Catalog Freshness And Source Sync

### Added

- Refreshed the catalog metadata and retained-client portability baseline.

### Changed

- Updated the catalog metadata and last-updated state for the 2026-08-14 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.

### Fixed

- Preserved explicit no-MCP fallbacks and the catalog's safety, approval, and source-boundary guidance.

## [2026-07-29] - Version 2.0 Client Support Reset

### Added

- Added the current GitHub Copilot, Claude Code, and Codex portability baseline.

### Changed

- **BREAKING:** Removed Gemini CLI and Antigravity as supported clients.
- Refreshed catalog metadata and last-updated state for the 2026-07-29 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.

### Fixed

- Prevented catalog modernization from reintroducing removed Gemini or Antigravity guidance.

## [2026-07-11] - Catalog Maintenance Refresh

### Added

- Added the current catalog verification baseline where it was missing.

### Changed

- Refreshed catalog metadata and last-updated state for the 2026-07-11 maintenance pass.
- Kept the cross-client, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.
- Reclassified historical `Tested` or `Verified` changelog headings under the allowed changelog vocabulary without dropping their evidence.

### Fixed

- Closed validator and documentation drift so the enforced schema matches the documented skill baseline.

## [2026-06-09] - Upstream Refresh and Catalog Validation Cleanup

### Added
- Brought in the latest upstream guidance for edit-in-place cleanup, voice and context profiles, and iterative rewrite convergence.
- Refreshed the bundled MIT license text from the upstream repository.

### Changed
- Updated the maintained `SKILL.md` from `https://github.com/conorbronsdon/avoid-ai-writing` to commit `4331560d02b2c86ffd1d889d4f688da699d360d9` while keeping the repo-standard verification, portability, and no-MCP sections.
- Refreshed the frontmatter description and `last_updated` date to match the expanded workflow.

### Fixed
- Removed the legacy `### Tested` changelog heading so repo validation rules stay satisfied.
- Replaced the older two-mode wording with the current upstream three-mode guidance.

## [2026-04-25] - Version 1.2 Verification Protocol Refresh

### Added
- Added a `Verification Protocol` section with skill-specific pass/fail checks, one pressure-test scenario, and a measurable success metric.
- Added guidance to leverage native parallel subagent dispatch and 200k+ context windows where available.

### Changed
- Updated `SKILL.md` frontmatter to `version: "1.2"` and `last_updated: 2026-04-25`.
- Reframed activation guidance toward symptom -> action triggers and standardized two-stage review wording where applicable.

### Fixed
- Preserved the earlier import cleanup while aligning the maintained copy with the v1.2 catalog structure.

## [2026-04-24] - Initial Import and Portability Upgrade

### Added
- Imported the skill from `https://github.com/conorbronsdon/avoid-ai-writing`.
- Added the upstream MIT license as `LICENSE.txt`.
- Added cross-client portability guidance for GitHub Copilot, Claude Code, Codex, and Gemini CLI.
- Added the repo-standard no-MCP fallback guidance for this skill.

### Changed
- Standardized the maintained copy into the shared catalog structure used in this repo.
- Pinned the initial vendored source commit to `cbf885e087e8ec1168bc58dc603606a6e4bfacbd`.

### Fixed
- Cleaned up imported mojibake or replacement-character separators so the maintained copy rendered cleanly.
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall