Skip to content
Agentmart
Submit a tool

dev

Writing and changing code: Ponytail simplicity, grounded style rules, local and feature-wide systematic debugging, completion verification, architecture…

Skill by youlianvr

IndexedCC-BY-4.0★ 14
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/youlianvr-dev

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Writing and changing code: Ponytail simplicity, grounded style rules, local and feature-wide systematic debugging, completion verification, architecture improvements, defensive bash, API/database design, money-path safety, hardening and observability, RAG pipelines. One contract; the parts under parts/ carry the rules — open the ones the task needs.

Use cases: documents, design, backend, ml

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/dev
  • ~/threads/thread-manager
  • ~/threads/types

What's inside

Skill name
dev
Description
Writing and changing code: Ponytail simplicity, grounded style rules, local and feature-wide systematic debugging, completion verification, architecture improvements, defensive bash, API/database design, money-path safety, hardening and observability, RAG pipelines. One contract; the parts under parts/ carry the rules — open the ones the task needs.
License
CC-BY-4.0
Instructions
76 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (100)

  • SKILL.md
  • SKILL.md · parts/agent-refactor-safety/
  • eval_queries.json · parts/agent-refactor-safety/evals/
  • evals.json · parts/agent-refactor-safety/evals/
  • SKILL.md · parts/api-design-reviewer/
  • api_antipatterns.md · parts/api-design-reviewer/references/
  • rest_design_rules.md · parts/api-design-reviewer/references/
  • api_linter.py · parts/api-design-reviewer/scripts/
  • api_scorecard.py · parts/api-design-reviewer/scripts/
  • breaking_change_detector.py · parts/api-design-reviewer/scripts/
  • SKILL.md · parts/api-test-suite-builder/
  • example-test-files.md · parts/api-test-suite-builder/references/
  • SKILL.md · parts/architecture-simplicity/
  • SKILL.md · parts/bash-defensive-patterns/
  • SKILL.md · parts/changelog-discipline/
  • 01-antipatterns.md · parts/changelog-discipline/references/
  • 02-examples.md · parts/changelog-discipline/references/
  • SKILL.md · parts/coding-style/
  • assumption_linter.json · parts/coding-style/expected_outputs/
  • complexity_checker.json · parts/coding-style/expected_outputs/
  • diff_surgeon.json · parts/coding-style/expected_outputs/
  • goal_verifier.json · parts/coding-style/expected_outputs/
  • anti-patterns.md · parts/coding-style/references/
  • enforcement-patterns.md · parts/coding-style/references/
  • karpathy-principles.md · parts/coding-style/references/
  • ponytail-source.md · parts/coding-style/references/
  • assumption_linter.py · parts/coding-style/scripts/
  • complexity_checker.py · parts/coding-style/scripts/
  • diff_surgeon.py · parts/coding-style/scripts/
  • goal_verifier.py · parts/coding-style/scripts/
  • SKILL.md · parts/cross-platform-gotchas/
  • README.md · parts/database-designer/
  • SKILL.md · parts/database-designer/
  • sample_query_patterns.json · parts/database-designer/assets/
  • sample_schema.json · parts/database-designer/assets/
  • sample_schema.sql · parts/database-designer/assets/
  • index_optimization_sample.txt · parts/database-designer/expected_outputs/
  • migration_sample.txt · parts/database-designer/expected_outputs/
  • schema_analysis_sample.txt · parts/database-designer/expected_outputs/
  • index_optimizer.py · parts/database-designer/
  • migration_generator.py · parts/database-designer/
  • database-design-reference.md · parts/database-designer/references/
  • database_selection_decision_tree.md · parts/database-designer/references/
  • index_strategy_patterns.md · parts/database-designer/references/
  • normalization_guide.md · parts/database-designer/references/
  • schema_analyzer.py · parts/database-designer/
  • SKILL.md · parts/debug-incident-protocol/
  • eval_queries.json · parts/debug-incident-protocol/evals/
  • evals.json · parts/debug-incident-protocol/evals/
  • LICENSE.txt · parts/fastapi/
  • SKILL.md · parts/fastapi/
  • dependencies.md · parts/fastapi/references/
  • frontend-and-telemetry.md · parts/fastapi/references/
  • other-tools.md · parts/fastapi/references/
  • path-operations.md · parts/fastapi/references/
  • pydantic.md · parts/fastapi/references/
  • responses.md · parts/fastapi/references/
  • streaming.md · parts/fastapi/references/
  • SKILL.md · parts/hardening-observability/
  • HTML-REPORT.md · parts/improve-codebase-architecture/
  • …and 40 more

SKILL.md (first lines)

# dev — writing and changing code

> Home branch in Memora: `root/skill/dev`. Every part is a method, not a mode:
> read the section you need, never a large file end to end.

## Choosing a part

**Everyday quality**

| Part | What it covers |
|---|---|
| `parts/ponytail/` | Main route: simplest clear complete solution; existing tools and code first, no silent scope cuts or weaker checks |
| `parts/coding-style/` | Grounded APIs and versions, project conventions, coherent changes, optional complexity diagnostics |
| `parts/simplify/` | Reduce needless complexity once behavior is understood; cleanup stays separate from correctness fixes |
| `parts/systematic-debugging/` | Reproduce and repair a local bug or a whole feature journey; trace dependencies and affected consumers |
| `parts/debug-incident-protocol/` | Hung, regressed or silently failing runtime, stale code, duplicate consumers, a restart that must be verified |
| `parts/testing-discipline/` | Writing and reviewing tests, test sensitivity, isolation of storage and external effects, what verification a change needs |
| `parts/architecture-simplicity/` | Module and layer design, library versus own code, god-files, "an abstraction for growth", schema evolution without data loss |
| `parts/improve-codebase-architecture/` | Structural improvement passes on an existing codebase |
| `parts/agent-refactor-safety/` | Extracting modules, splitting a monolith, moving symbols, repairing behavior lost after an edit |
| `parts/bash-defensive-patterns/` | Defensive bash: quoting, `set -euo pipefail`, safe temp files, portability traps |
| `parts/changelog-discipline/` | Keep a CHANGELOG as a decision log: what changed, why, what was rejected |
| `parts/cross-platform-gotchas/` | Python/bash installers on Linux, macOS and Windows: paths, encodings, package managers, WSL stubs |

**API, data and service design**

| Part | What it covers |
|---|---|
| `parts/api-design-reviewer/` | Review API designs for consistency, ergonomics and contract quality |
| `parts/api-test-suite-builder/` | Build API test suites from contracts or specs |
| `parts/database-designer/` | Schema design: normalization, indexes, constraints, migrations |
| `parts/sql-database-assistant/` | Working SQL for Postgres, MySQL and SQLite — queries, tuning, schema changes |
| `parts/jsonc-surgical-edit/` | Edit JSON/JSONC configs by offsets without losing comments, ordering or manual entries |
| `parts/money-path-safety/` | Anything that debits, credits or grants: idempotency, atomicity, buckets, hard gates, charge after success |
| `parts/hardening-observability/` | Rate limits, metrics, log tiers, "database is locked", why metrics lie, a security pass |

**AI and retrieval plumbing**

| Part | What it covers |
|---|---|
| `parts/rag-architect/` | Design RAG pipelines: chunking, embeddings, retrieval evaluation |
| `parts/langchain-rag/` | LangChain-specific RAG implementation patterns |
| `parts/llm-cost-optimizer/` | Reduce LLM cost: model tiering, caching, prompt compression |

**Deciding and routing**

| Part | What it covers |
|---|---|
| `parts/production-first-decisions/` | A consequential tool or design choice with unresolved evidence: compare, research the gap, spike the load-bearing claim |
| `parts/using-superpowers/` | Choose and compose task-relevant skills when the route is unclear |
| `parts/fastapi/` | FastAPI and Pydantic conventions: `Annotated`, return types, routers, async versus sync, SSE and byte streaming, frontend serving, OpenTelemetry |

## Rules

- **Main route** → understand the task and the code → `ponytail` + `coding-style` → verification
  through the real usage path. A method, not an approval ceremony.
- **Bug** → `systematic-debugging` for cause and consumer-wide repair; a hung process or a
  suspicious restart → `debug-incident-protocol`. Verification stays a completed act, not a
  separate gate: BOOT §5 already forbids reporting unexercised claims.
- **Refactor versus cleanup** → behavior-preserving cleanup is `simplify`; structural redesign is
  `improve-codebase-architecture`; a risky mechanical sweep is `agent-refactor-safety`.
- **Tests** → `testing-discipline`. Implementation order is not a completion gate; the mandatory
  TDD package was retired by the owner on 2026-10-04.
- **Forks worth `ask_questions`**: a change of public contract, a schema migration that can lose
  data, a new dependency or service, money or quota semantics, an irreversible data operation.
  Ordinary implementation detail is decided here and stated in one line.
- **Findings that outlive the task** become Memora nodes under `root/skill/dev` (or the project
  branch); `_memory/reports/` keeps only large tables and dated evidence.
- **Shipping the change** → the `ship` router.

## Related

`ship` (release, dependencies, git), `discipline` methods now living in the parts above,
`review` (`verify`, `diagnosing-bugs`), `loops` for repeated work.

From youlianvr/oper-share, CC-BY-4.0.

More from youlianvr/oper-share

Signals

Stars
14
Forks
4
Open issues
0
Last commit (this folder)
Oct 20, 2026 (8 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
CC-BY-4.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from youlianvr

Cite this page

dev skill. Agent Mart. https://agentmart.dev/skills/youlianvr-dev (last updated 2026-10-24)