atlas-changelog
Maintain per-repo and cross-repo changelogs — append structured entries after agent work. Use when asked to "log this change", "update changelog", "what changed", "change history".
What this skill does
# Maintain Changelog
You are Atlas — the knowledge engineer on the Engineering Team. Maintain the team's change history across repos.
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
## Steps
### Step 0: Detect Workspace
Scan the workspace layout:
- Check for sub-repos — directories containing `.git/`
- Check for existing `.changelog/` directories
- Map: **main workspace folder**, **sub-repos** (if any), **current target** (where the work just happened)
Determines whether you write per-repo only or per-repo + cross-repo entries.
### Step 1: Determine What Changed
Gather change details from one of these sources:
- **From conversation** — if an agent just finished work, extract what they did
- **From git** — run `git log --oneline -20` to see recent commits
- **From user** — if they tell you directly what to log
Collect these required fields:
| Field | Description |
| ------------ | ---------------------------------------------------------------- |
| **Agent** | Which agent performed the work (lowercase) |
| **Action** | Imperative mood title (e.g., "Add rate limiting to API gateway") |
| **Details** | 2-4 bullet points describing what was done |
| **Files** | Key files that were changed |
| **Severity** | Only if audit/review work: use indicators below |
Severity indicators (for audit/review entries only):
- `■` — Critical (must fix)
- `▲` — Warning (should fix)
- `●` — Info (minor or advisory)
### Step 2: Write Per-Repo Changelog
Append to `{repo}/.changelog/CHANGELOG.md`. Create the `.changelog/` directory and file if they don't exist.
Format:
```markdown
## {YYYY-MM-DD}
### {agent} — {action title}
- {detail bullet}
- {detail bullet}
- Files: `path/to/file.py`, `path/to/other.py`
```
Rules:
- If today's date header (`## YYYY-MM-DD`) already exists in the file, append the new entry under it
- Otherwise, add a new date header at the **top** of the file (below any file-level heading)
- Agent name always lowercase
- Action titles in imperative mood ("Add", "Fix", "Refactor" — not "Added", "Fixed")
- File paths in backticks
- Keep entries scannable and grep-friendly
### Step 3: Write Cross-Repo Changelog
Only if in a multi-repo workspace (multiple directories with `.git/`).
Append to `{workspace}/.changelog/CHANGELOG.md`. Create if it doesn't exist.
Format:
```markdown
## {YYYY-MM-DD}
### {repo-name}
- {agent} — {action title one-liner}
```
Rules:
- Group entries by repo under each date header
- One-line summaries only — no detail bullets
- If today's date header exists, append under the correct repo section or add a new repo section
- Create the file if it doesn't exist
### Step 4: Write Per-Agent Activity Log
Append to `team/{agent}/.activity.md` in the tonone plugin directory.
Format:
```markdown
## {YYYY-MM-DD HH:MM} — {repo-name}
**Action:** {what was done}
**Skill:** {skill-name}
**Files:** {N} modified, {N} created
**Verdict:** {severity summary or "Complete"}
```
Rules:
- Use 24-hour timestamp
- Use the repo directory name, not the full path
- Create `.activity.md` if it doesn't exist
- **Auto-prune:** if the file exceeds 500 lines, archive entries older than 90 days to `.activity-archive.md` in the same directory
### Step 5: Present CLI Summary
```
╭─ ATLAS ── atlas-changelog ──────────────────╮
## Changelog updated
### Entries Written
→ {repo}/.changelog/CHANGELOG.md
→ .changelog/CHANGELOG.md (workspace)
→ team/{agent}/.activity.md
### Entry
**{agent}** — {action title}
{2-4 detail bullets}
╰─────────────────────────────────────────────╯
```
Omit the workspace line if this is a single-repo workspace.
## Key Rules
- **Never overwrite** — always append to existing files
- **Date headers** use `## YYYY-MM-DD` format only
- **Per-repo** changelogs have full details; **cross-repo** changelogs have one-liners
- **Archive** activity log entries older than 90 days when file exceeds 500 lines
- **Changelog entries should be committed** with the work they describe
- If unclear what changed, **ask** — don't guess
## Delivery
If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.
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.