atlas-agent-developer
Implementation and troubleshooting agent - builds features and fixes bugs
npx skills add majiayu000/claude-skill-registry --skill atlas-agent-developer --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The Atlas Agent: Developer is tasked with implementing features and fixing bugs in strict alignment with project standards. It emphasizes auditing dependencies before changes, verifying outcomes with grep-like checks, and eliminating unnecessary complexity. It uses store-specific methods and canonical field names, and requires debugging statements to be removed or wrapped in DEV.
How it works
- It follows a 5-step workflow: Understand, Implement, Self-Validate, Document, and (implied) Review. The agent reads requirements, audits the codebase with grep-like commands to locate usages and patterns, identifies affected areas, and checks documentation.
- In implementation, it mirrors StackMap conventions: use store.getState().setXxx or similar store-specific methods instead of direct setState calls; canonical field names text and icon; provide fallbacks when reading fields; wrap or remove debug logs; add comments for non-obvious logic; handle null/undefined and error conditions.
- It provides concrete code examples for store updates and field naming, including correct vs. incorrect patterns:
- Correct: useUserStore.getState().setUsers(newUsers);
- Correct: activity.text and activity.icon with fallbacks; reading via const text = activity.text || activity.name || activity.title;
- Typography and color usage via Typography component and accessible colors specified.
- Validation steps include typechecking, tests, linting, and grep-based checks to ensure no forbidden patterns remain (e.g., useAppStore.setState, direct console logs, legacy field names).
When to use it
- Manual Invocation: commands like "Implement [feature description]", "Fix bug: [bug description]", "Refactor [component name] to follow new pattern", and "Troubleshoot [issue description]".
- Automatic Triggers: issues labeled ready for development, stories created by product manager, or triaged bug reports.
- Workflow phases: Standard (Research, Plan, Implement), Full (Research, Plan, Implement), Iterative (all iterations).
What it can touch
- It prescribes using store-specific update methods (e.g., useXStore.getState().setX) and canonical fields (text, icon).
- It requires validation commands and grep-based checks as part of validation steps.
- It references tools like grep for auditing imports and usage; specific commands are shown in the SKILL’s guidance.
Caveats
- The approach relies on adhering to StackMap conventions and measurable validation; outcomes must be verifiable via grep and tests.
- Debug logs must be wrapped or removed in production as prescribed.
- All changes should pass typecheck, tests, and linting before submission.
# Atlas Agent: Developer ## Core Responsibility To implement features and fix bugs in precise alignment with the project's architectural standards and quality gates. To provide verifiable evidence of correctness for all work submitted. **Philosophy**: The developer is the first line of defense for quality. The goal is to submit work that passes peer review on the first attempt. ## When to Invoke This Agent **Workflow Integration:** - **Standard Workflow**: Phase 1 (Research), Phase 2 (Plan), Phase 3 (Implement) - **Full Workflow**: Phase 1 (Research), Phase 3 (Plan), Phase 5 (Implement) - **Iterative Workflow**: All implementation iterations **Manual Invocation:** ``` "Implement [feature description]" "Fix bug: [bug description]" "Refactor [component name] to follow new pattern" "Troubleshoot [issue description]" ``` **Automatic Triggers** (if configured): - Issue labeled "ready for development" - Story created by product manager - Bug report triaged ## Core Principles ### 1. Verify, Then Act **Principle**: Before modifying any code, audit its usage and dependencies. Never assume. Use tools like `grep` to trace imports and component usage. **In practice:** ```bash # Before changing
- Core Responsibility
- When to Invoke This Agent
- Core Principles
- 1. Verify, Then Act
- 2. Measure Everything (The "Grep Test")
- 3. Eliminate, Don't Add
- 4. Production Code is Silent & Safe
- 5. Own Your Quality
- Standard Workflow
- 1. Understand
- 2. Implement
- 3. Self-Validate
- 4. Document
- 5. Submit for Review
Before changing a function: grep -r "functionName" src/ Before renaming a component: grep -r "import.*ComponentName" src/ Before changing a prop: grep -r "propName" src/ Before modifying store: grep -r "useAppStore\|useUserStore\|useSettingsStore" src/ Find all callers grep -rn "resolveConflict" src/
What does the atlas-agent-developer skill do?
Implementation and troubleshooting agent - builds features and fixes bugs
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill atlas-agent-developer --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.