From 04e296013539009019832a8344aa46fc17516530 Mon Sep 17 00:00:00 2001 From: Safi Date: Sun, 12 Apr 2026 21:18:20 +0100 Subject: [PATCH] Remove Claude-specific language from platform skill files (0.4.8) Co-Authored-By: Claude Sonnet 4.6 --- CHANGELOG.md | 4 ++++ graphify/skill-aider.md | 6 +++--- graphify/skill-claw.md | 6 +++--- graphify/skill-codex.md | 6 +++--- graphify/skill-copilot.md | 6 +++--- graphify/skill-droid.md | 6 +++--- graphify/skill-opencode.md | 6 +++--- graphify/skill-windows.md | 6 +++--- pyproject.toml | 2 +- 9 files changed, 26 insertions(+), 22 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 9b5fd6d1b..feb7cbfa5 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,6 +2,10 @@ Full release notes with details on each version: [GitHub Releases](https://github.com/safishamsi/graphify/releases) +## 0.4.8 (2026-04-12) + +- Fix: platform skill files (aider, codex, opencode, claw, droid, copilot, windows) no longer contain Claude-specific language — references to "Claude" as the AI model replaced with platform-agnostic wording (#272) + ## 0.4.7 (2026-04-12) - Fix: `watch` semantic edge preservation was always empty — `graph.json` uses `links` key but code read `edges` (#269) diff --git a/graphify/skill-aider.md b/graphify/skill-aider.md index 520aea6bb..f70136f1a 100644 --- a/graphify/skill-aider.md +++ b/graphify/skill-aider.md @@ -38,7 +38,7 @@ Turn any folder of files into a navigable knowledge graph with community detecti graphify is built around Andrej Karpathy's /raw folder workflow: drop anything into a folder - papers, tweets, screenshots, code, notes - and get a structured knowledge graph that shows you what you didn't know was connected. -Three things it does that Claude alone cannot: +Three things it does that your AI assistant alone cannot: 1. **Persistent graph** - relationships are stored in `graphify-out/graph.json` and survive across sessions. Ask questions weeks later without re-reading everything. 2. **Honest audit trail** - every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS. You know what was found vs invented. 3. **Cross-document surprise** - community detection finds connections between concepts in different files that you would never think to ask about directly. @@ -157,7 +157,7 @@ After transcription: **Before starting:** note whether `--mode deep` was given. You must pass `DEEP_MODE=true` to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it. -This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (Claude, costs tokens). +This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (your AI model, costs tokens). **Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.** @@ -1117,7 +1117,7 @@ Supported URL types (auto-detected): - Twitter/X → fetched via oEmbed, saved as `.md` with tweet text and author - arXiv → abstract + metadata saved as `.md` - PDF → downloaded as `.pdf` -- Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run +- Images (.png/.jpg/.webp) → downloaded, vision extraction runs on next build - Any webpage → converted to markdown via html2text --- diff --git a/graphify/skill-claw.md b/graphify/skill-claw.md index 9b653752f..eefa5782d 100644 --- a/graphify/skill-claw.md +++ b/graphify/skill-claw.md @@ -38,7 +38,7 @@ Turn any folder of files into a navigable knowledge graph with community detecti graphify is built around Andrej Karpathy's /raw folder workflow: drop anything into a folder - papers, tweets, screenshots, code, notes - and get a structured knowledge graph that shows you what you didn't know was connected. -Three things it does that Claude alone cannot: +Three things it does that your AI assistant alone cannot: 1. **Persistent graph** - relationships are stored in `graphify-out/graph.json` and survive across sessions. Ask questions weeks later without re-reading everything. 2. **Honest audit trail** - every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS. You know what was found vs invented. 3. **Cross-document surprise** - community detection finds connections between concepts in different files that you would never think to ask about directly. @@ -157,7 +157,7 @@ After transcription: **Before starting:** note whether `--mode deep` was given. You must pass `DEEP_MODE=true` to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it. -This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (Claude, costs tokens). +This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (your AI model, costs tokens). **Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.** @@ -1117,7 +1117,7 @@ Supported URL types (auto-detected): - Twitter/X → fetched via oEmbed, saved as `.md` with tweet text and author - arXiv → abstract + metadata saved as `.md` - PDF → downloaded as `.pdf` -- Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run +- Images (.png/.jpg/.webp) → downloaded, vision extraction runs on next build - Any webpage → converted to markdown via html2text --- diff --git a/graphify/skill-codex.md b/graphify/skill-codex.md index c75a407ec..dec6c7b12 100644 --- a/graphify/skill-codex.md +++ b/graphify/skill-codex.md @@ -38,7 +38,7 @@ Turn any folder of files into a navigable knowledge graph with community detecti graphify is built around Andrej Karpathy's /raw folder workflow: drop anything into a folder - papers, tweets, screenshots, code, notes - and get a structured knowledge graph that shows you what you didn't know was connected. -Three things it does that Claude alone cannot: +Three things it does that your AI assistant alone cannot: 1. **Persistent graph** - relationships are stored in `graphify-out/graph.json` and survive across sessions. Ask questions weeks later without re-reading everything. 2. **Honest audit trail** - every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS. You know what was found vs invented. 3. **Cross-document surprise** - community detection finds connections between concepts in different files that you would never think to ask about directly. @@ -156,7 +156,7 @@ After transcription: **Before starting:** note whether `--mode deep` was given. You must pass `DEEP_MODE=true` to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it. -This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (Claude, costs tokens). +This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (your AI model, costs tokens). **Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.** @@ -1175,7 +1175,7 @@ Supported URL types (auto-detected): - Twitter/X → fetched via oEmbed, saved as `.md` with tweet text and author - arXiv → abstract + metadata saved as `.md` - PDF → downloaded as `.pdf` -- Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run +- Images (.png/.jpg/.webp) → downloaded, vision extraction runs on next build - Any webpage → converted to markdown via html2text --- diff --git a/graphify/skill-copilot.md b/graphify/skill-copilot.md index 1bd26f0aa..f6572a171 100644 --- a/graphify/skill-copilot.md +++ b/graphify/skill-copilot.md @@ -40,7 +40,7 @@ Turn any folder of files into a navigable knowledge graph with community detecti graphify is built around Andrej Karpathy's /raw folder workflow: drop anything into a folder - papers, tweets, screenshots, code, notes - and get a structured knowledge graph that shows you what you didn't know was connected. -Three things it does that Claude alone cannot: +Three things it does that your AI assistant alone cannot: 1. **Persistent graph** - relationships are stored in `graphify-out/graph.json` and survive across sessions. Ask questions weeks later without re-reading everything. 2. **Honest audit trail** - every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS. You know what was found vs invented. 3. **Cross-document surprise** - community detection finds connections between concepts in different files that you would never think to ask about directly. @@ -159,7 +159,7 @@ After transcription: **Before starting:** note whether `--mode deep` was given. You must pass `DEEP_MODE=true` to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it. -This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (Claude, costs tokens). +This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (your AI model, costs tokens). **Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.** @@ -1201,7 +1201,7 @@ Supported URL types (auto-detected): - Twitter/X → fetched via oEmbed, saved as `.md` with tweet text and author - arXiv → abstract + metadata saved as `.md` - PDF → downloaded as `.pdf` -- Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run +- Images (.png/.jpg/.webp) → downloaded, vision extraction runs on next build - Any webpage → converted to markdown via html2text --- diff --git a/graphify/skill-droid.md b/graphify/skill-droid.md index 979972017..e5ac74054 100644 --- a/graphify/skill-droid.md +++ b/graphify/skill-droid.md @@ -38,7 +38,7 @@ Turn any folder of files into a navigable knowledge graph with community detecti graphify is built around Andrej Karpathy's /raw folder workflow: drop anything into a folder - papers, tweets, screenshots, code, notes - and get a structured knowledge graph that shows you what you didn't know was connected. -Three things it does that Claude alone cannot: +Three things it does that your AI assistant alone cannot: 1. **Persistent graph** - relationships are stored in `graphify-out/graph.json` and survive across sessions. Ask questions weeks later without re-reading everything. 2. **Honest audit trail** - every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS. You know what was found vs invented. 3. **Cross-document surprise** - community detection finds connections between concepts in different files that you would never think to ask about directly. @@ -157,7 +157,7 @@ After transcription: **Before starting:** note whether `--mode deep` was given. You must pass `DEEP_MODE=true` to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it. -This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (Claude, costs tokens). +This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (your AI model, costs tokens). **Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.** @@ -1172,7 +1172,7 @@ Supported URL types (auto-detected): - Twitter/X → fetched via oEmbed, saved as `.md` with tweet text and author - arXiv → abstract + metadata saved as `.md` - PDF → downloaded as `.pdf` -- Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run +- Images (.png/.jpg/.webp) → downloaded, vision extraction runs on next build - Any webpage → converted to markdown via html2text --- diff --git a/graphify/skill-opencode.md b/graphify/skill-opencode.md index d2200f640..b1a8da6eb 100644 --- a/graphify/skill-opencode.md +++ b/graphify/skill-opencode.md @@ -38,7 +38,7 @@ Turn any folder of files into a navigable knowledge graph with community detecti graphify is built around Andrej Karpathy's /raw folder workflow: drop anything into a folder - papers, tweets, screenshots, code, notes - and get a structured knowledge graph that shows you what you didn't know was connected. -Three things it does that Claude alone cannot: +Three things it does that your AI assistant alone cannot: 1. **Persistent graph** - relationships are stored in `graphify-out/graph.json` and survive across sessions. Ask questions weeks later without re-reading everything. 2. **Honest audit trail** - every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS. You know what was found vs invented. 3. **Cross-document surprise** - community detection finds connections between concepts in different files that you would never think to ask about directly. @@ -157,7 +157,7 @@ After transcription: **Before starting:** note whether `--mode deep` was given. You must pass `DEEP_MODE=true` to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it. -This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (Claude, costs tokens). +This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (your AI model, costs tokens). **Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.** @@ -1171,7 +1171,7 @@ Supported URL types (auto-detected): - Twitter/X → fetched via oEmbed, saved as `.md` with tweet text and author - arXiv → abstract + metadata saved as `.md` - PDF → downloaded as `.pdf` -- Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run +- Images (.png/.jpg/.webp) → downloaded, vision extraction runs on next build - Any webpage → converted to markdown via html2text --- diff --git a/graphify/skill-windows.md b/graphify/skill-windows.md index 2016f8d2b..8aa048238 100644 --- a/graphify/skill-windows.md +++ b/graphify/skill-windows.md @@ -41,7 +41,7 @@ Turn any folder of files into a navigable knowledge graph with community detecti graphify is built around Andrej Karpathy's /raw folder workflow: drop anything into a folder - papers, tweets, screenshots, code, notes - and get a structured knowledge graph that shows you what you didn't know was connected. -Three things it does that Claude alone cannot: +Three things it does that your AI assistant alone cannot: 1. **Persistent graph** - relationships are stored in `graphify-out/graph.json` and survive across sessions. Ask questions weeks later without re-reading everything. 2. **Honest audit trail** - every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS. You know what was found vs invented. 3. **Cross-document surprise** - community detection finds connections between concepts in different files that you would never think to ask about directly. @@ -149,7 +149,7 @@ After transcription: **Before starting:** note whether `--mode deep` was given. You must pass `DEEP_MODE=true` to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it. -This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (Claude, costs tokens). +This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (your AI model, costs tokens). **Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.** @@ -1165,7 +1165,7 @@ Supported URL types (auto-detected): - Twitter/X → fetched via oEmbed, saved as `.md` with tweet text and author - arXiv → abstract + metadata saved as `.md` - PDF → downloaded as `.pdf` -- Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run +- Images (.png/.jpg/.webp) → downloaded, vision extraction runs on next build - Any webpage → converted to markdown via html2text --- diff --git a/pyproject.toml b/pyproject.toml index f3621ac89..f9d4e20a6 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta" [project] name = "graphifyy" -version = "0.4.7" +version = "0.4.8" description = "AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, OpenClaw, Factory Droid, Trae) - turn any folder of code, docs, papers, images, or videos into a queryable knowledge graph" readme = "README.md" license = { file = "LICENSE" }