agent-changelog
Compile an agent-optimized changelog by cross-referencing git history with plans and documentation. Use when asked to "update changelog", "compile history", "document project evolution", or proactively after major milestones, architectural changes, or when stale/deprecated information is detected that could confuse coding agents.
What this skill does
# Agent Changelog Compile a chronological record of key decisions, architectural changes, and project evolution optimized for coding agent context-building. ## Output Write to `AGENT_CHANGELOG.md` in the project root. This file helps agents: - Understand key decisions and their rationale - Identify deprecated patterns/approaches to avoid - Grasp the trajectory from past to present to likely future - Detect stale documentation that contradicts current reality ## Workflow ### 1. Gather Sources Collect information from these sources in parallel: **Git history:** ```bash git log --oneline --since="6 months ago" | head -100 git log --all --oneline --grep="BREAKING" --grep="deprecate" --grep="remove" --grep="migrate" -i git tag -l --sort=-creatordate | head -20 ``` **Documentation:** - `.claude/plans/` - implementation plans and decisions - `CLAUDE.md` - project instructions - `README.md` - project overview - `docs/` or similar documentation directories - `CHANGELOG.md` if exists (traditional changelog) **Code signals:** - `@deprecated` annotations - `TODO`, `FIXME`, `HACK` comments with dates - Migration files, upgrade scripts ### 2. Identify Key Events Extract events that matter for agent understanding: **Always include:** - Architectural decisions (new patterns, removed patterns) - Breaking changes and migrations - Deprecated features/approaches - Major dependency changes - Directory structure changes - API changes (internal or external) **Include if significant:** - New features that change how agents should work - Bug fixes that reveal incorrect assumptions - Performance changes that affect approach recommendations **Skip:** - Minor bug fixes - Cosmetic changes - Routine dependency updates - Individual feature additions (unless architectural) ### 3. Cross-Reference for Contradictions For each significant event, check if existing documentation contradicts it: ``` Event: "Migrated from Redux to Zustand" (commit abc123, 2024-03) Check: Does any documentation still reference Redux patterns? - README.md mentions Redux? → Flag as STALE - CLAUDE.md suggests Redux approach? → Flag as STALE - Old tutorials in docs/? → Flag as STALE ``` Track contradictions in a "Stale Information Detected" section. ### 4. Write the Changelog Structure the output file: ```markdown # Agent Changelog > This file helps coding agents understand project evolution, key decisions, > and deprecated patterns. Updated: [DATE] ## Current State Summary [2-3 sentences on where the project is NOW - the authoritative current architecture] ## Stale Information Detected [List any documentation that contradicts current reality - agents should ignore these until fixed] | Location | States | Reality | Since | |----------|--------|---------|-------| | docs/auth.md | "Uses JWT tokens" | Migrated to sessions | 2024-06 | ## Timeline ### [YEAR-MONTH] - [Brief Title] **What changed:** [Factual description] **Why:** [Decision rationale if known from plans/commits] **Agent impact:** [How this affects how agents should work in the codebase] **Deprecated:** [What approaches/patterns should agents avoid] --- [Repeat for each significant event, reverse chronological] ## Deprecated Patterns [Consolidated list of things agents should NOT do, with what to do instead] | Don't | Do Instead | Deprecated Since | |-------|------------|------------------| | Use `OldService` | Use `NewService` | 2024-08 | ## Trajectory [Brief note on where the project appears to be heading based on recent changes and plans] ``` ### 5. Validate and Update After writing: - Read existing `AGENT_CHANGELOG.md` if present and merge, don't duplicate - Verify dates against git history - Ensure "Stale Information Detected" section is actionable ## When to Proactively Run Suggest running this skill when: - A major refactor or migration just completed - Plans in `.claude/plans/` were recently executed - Multiple architectural decisions happened in quick succession - Detected documentation that seems to contradict code reality - Starting work on a codebase after a long gap - Onboarding to an unfamiliar codebase ## Guidelines - Prioritize accuracy over completeness—wrong history is worse than incomplete - Include rationale when available (commit messages, plan docs) - Be specific about what agents should avoid, not just what changed - Keep entries concise—this is reference material, not storytelling - Date everything to help agents judge relevance
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.