oliver-kriska/claude-elixir-phoenix / .claude/skills/cc-changelog
cc-changelog
VerifiedCONTRIBUTOR TOOL - Track CC changelog, extract new versions since last check, analyze impact on plugin (breaking changes, opportunities, deprecations). Run periodically or before releases. NOT part of the distributed plugin.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.4 KB |
| references/analysis-rules.md | markdown | 5.6 KB |
references/analysis-rules.md
View on GitHub# CC Changelog Analysis Rules
## Plugin Component Mapping
When analyzing CC changelog entries, map them to specific plugin components:
### Hooks System
| CC Change Pattern | Plugin Files to Check |
|-------------------|-----------------------|
| Hook events (new/changed/removed) | `plugins/elixir-phoenix/hooks/hooks.json` |
| Hook `if` conditions | All hooks with `"if":` patterns |
| Hook output behavior | `plugins/elixir-phoenix/hooks/scripts/*.sh` |
| `asyncRewake`, `once`, `timeout` | hooks.json hook definitions |
| `additionalContext` changes | SubagentStart, PostToolUseFailure hooks |
| `hookSpecificOutput` changes | All hooks using exit 2 + stderr |
| New hook types (agent, prompt, http) | Consider new hook opportunities |
### Agent Frontmatter
| CC Change Pattern | Plugin Files to Check |
|-------------------|-----------------------|
| New frontmatter fields | All 26 agents in `plugins/elixir-phoenix/agents/*.md` |
| `model:` value changes | Agents using specific model values |
| `permissionMode:` changes | None of our plugin agents set it (ignored on plugin agents); `.claude/agents/` contributor agents use `bypassPermissions` |
| `effort:` level changes | All agents with effort levels |
| `tools:` / `disallowedTools:` | Review agents (read-only enforcement) |
| `omitClaudeMd:` behavior | Agents with `omitClaudeMd: true` |
| `skills:` preloading | Agents with preloaded skills |
| `isolation:` / `background:` | Orchestrator agents |
| `maxTurns:` behavior | All agents with maxTurns set |
### Skill System
| CC Change Pattern | Plugin Files to Check |
|-------------------|-----------------------|
| Skill format changes | All 38 skills in `plugins/elixir-phoenix/skills/` |
| `description` length limits | All SKILL.md frontmatter (CC cap 1,536 since v2.1.105; plugin targets 250) |
| `paths:` field behavior | Skills with `paths:` for auto-loading |
| Skill listing/truncation | Skill descriptions and ordering |
| Lazy loading behavior | Skills with large references |
| `argument-hint:` | Command skills with argument hints |
### Plugin Config
| CC Change Pattern | Plugin Files to Check |
|-------------------|-----------------------|
| `plugin.json` schema | `plugins/elixir-phoenix/.claude-plugin/plugin.json` |
| `marketplace.json` schema | `.claude-plugin/marketplace.json` |
| `${CLAUDE_PLUGIN_DATA}` | `hooks/scripts/setup-dirs.sh`, `log-progress.sh` |
| `${CLAUDE_PLUGIN_ROOT}` | All hooks.json paths |
| `userConfig` / `sensitive` | plugin.json (if we use settings) |
| Plugin validation (`claude plugin validate`) | CI workflow |
### Tool System
| CC Change Pattern | Plugin Files to Check |
|-------------------|-----------------------|
| Tool parameter changes | Hooks checking tool inputs |
| New tools added | Agent `tools:` lists |
| Tool deprecation | Agent `tools:` lists, skill instructions |
| Permission mode changes | Agent `permissionMode:` |
| `SendMessage` / `TaskCreate` / etc. | Orchestrator agents using these tools |
### Compaction & Memory
| CC Change Pattern | Plugin Files to Check |
|-------------------|-----------------------|
| Compaction behavior | `PreCompact` / `PostCompact` hooks |
| Context window changes | Agent token budgets, skill sizes |
| Memory system changes | Agents with `memory: project` |
## Impact Classification Rules
### BREAKING — Requires Immediate Action
Flag as BREAKING when CC changelog says:
- "Breaking change" explicitly
- "Removed" a feature/parameter we use
- "Changed" behavior of a hook event we rely on
- "Renamed" an API/tool/parameter we reference
- Tool parameter schema changed (affects hook `if` patterns)
**Verification**: grep the plugin for the affected term/pattern.
### OPPORTUNITY — New Feature We Could Use
Flag as OPPORTUNITY when:
- New hook event added (check "Available but NOT used" list in memory)
- New agent frontmatter field that could improve our agents
- New plugin capability (`userConfig`, new `${}` variables)
- New tool that agents could benefit from
- Performance improvement that changes best practices
**Prioritization**: Score 1-3 based on how many plugin components benefit.
### RELEVANT FIX — CC Fixed Something We Workaround
Flag as RELEVANT FIX when:
- CC fixed a bug we documented in memory or CLAUDE.md
- CC fixed a behavior our hooks explicitly handle
- Error mentioned in our compound solutions
**Verification**: search memory file and hooks for the bug pattern.
### DEPRECATION — Migration Needed
Flag as DEPRECATION when:
- CC deprecated a tool/parameter we use
- CC will remove something in a future version
- CC recommends migrating from X to Y (and we use X)
**Urgency**: immediate if removal announced, low if just deprecated.
### INFO — Log Only
Everything else: performance improvements, unrelated bug fixes, new features
for capabilities we don't use (e.g., Codex CLI, Windows-specific).
## Cross-Reference Checklist
For each BREAKING or DEPRECATION item, always:
1. `grep -r "PATTERN" plugins/elixir-phoenix/` — find all usages
2. Check `hooks/hooks.json` — any hook referencing the feature
3. Check memory file — any documented behavior about this
4. Check CLAUDE.md — any instructions referencing this
## Memory Update Template
After analysis, update `reference_cc_source_internals.md` with:
```markdown
**Last changelog audit: CC v{LATEST} (checked {DATE}, down to v{PREVIOUS})**
```
Add new sections for:
- New hook events → "Available but NOT used" list
- New agent frontmatter → Agent Frontmatter section
- New plugin capabilities → Plugin Capabilities section
- Breaking changes → Breaking Changes section
- Bug fixes affecting plugin → Bug Fixes section
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |