Skip to content
Skills Library
Programming · Learning & explanation

engineering-core

/engineering-core

Universal engineering workflow, understand-before-modifying protocol, balanced autonomy, and non-destructive modification standards. Use when starting tasks on existing repos.

Repository
TES-SKILLS ↗
Licence
Apache-2.0
Last repository change
01.11.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
6
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 01.11.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Universal engineering workflow, understand-before-modifying protocol, balanced autonomy, and non-destructive modification standards. Use when starting tasks on existing repos.

Original author description

Universal engineering workflow, understand-before-modifying protocol, balanced autonomy, and non-destructive modification standards. Use when starting tasks on existing repos.

How it works

  1. Purpose & Activation
  2. 1. Understand Before Modifying
  3. 2. Balanced Autonomy Guardrails
  4. 3. Standard Execution Workflow
  5. 4. Expected Deliverables
  6. 5. Progressive Disclosure (Reference Documents)
Original SKILL.md headings · 71 lines, 508 words
SKILL.md preview
---
name: engineering-core
description: Universal engineering workflow, understand-before-modifying protocol, balanced autonomy, and non-destructive modification standards. Use when starting tasks on existing repos.
compatibility:
  - hermes
  - opencode
  - codex
  - claude-code
  - gemini-cli
  - generic
---

# Engineering Core

## Purpose & Activation
`engineering-core` establishes universal engineering discipline for autonomous coding agents. It governs pre-modification inspection, calibrated autonomy, minimal invasiveness, and verification standards.

- **Primary Skill For:** General repository maintenance, bug investigations, and engineering tasks requiring balanced autonomy.
- **Composition:** Pair with `software-engineering` for new feature development, or `project-onboarding` when first encountering an unfamiliar codebase.
- **Do Not Activate If:** The task is purely domain-specific (e.g., UI styling alone) where specialized skills suffice.

---

## 1. Understand Before Modifying
Before proposing or applying any code or configuration change:

1. **Repository Structure:** Map top-level directories, source trees, and documentation roots.
2. **Runtime & Languages:** Identify primary languages, compiler/interpreter versions, and package managers (`pyproject.toml`, `package.json`, `go.mod`, `Cargo.toml`).
3. **Dependencies & Frameworks:** Review direct dependencies, lockfiles, and active framework patterns.
4. **Conventions & Style:** Respect existing naming schemes, linter configs, formatting rules, and idioms.
5. **Test & Build Tooling:** Locate test harnesses, test commands, and CI workflow configurations.
6. **Security Seams:** Identify auth boundaries, cryptographic keys, database connections, and inputs.
7. **Production Context:** Check container definitions, environment configs, and deployment targets.

> **Rule:** Never introduce an unrequested framework, library, or architectural rewrite. Preserve working code.

---

## 2. Balanced Autonomy Guardrails

| Operation Class | Action | Permitted Autonomy |
|---|---|---|
| **Inspection & Analysis** | Reading repo files, searching symbols, profiling | **Automatic** (No confirmation needed) |
| **Local Verification** | Running tests, linters, static analyzers | **Automatic** (No confirmation needed) |
| **In-Scope Edits** | Editing source files in task scope, updating docs | **Autonomous within task** |
| **Local Commits** | Creating local git commits or local branches | **Follow project convention** |
| **Network Mutations** | Git push, PR creation, external API mutation | **Requires Explicit User Approval** |
| **Infrastructure / Release** | Production deployment, cloud provisioning | **Requires Explicit User Approval** |
| **Data Destruction** | Database drops, volume deletions, truncations | **Requires Explicit User Approval** |

---

## 3. Standard Execution Workflow

```
[Inspect & Understand] -> [Plan Minimal Seam] -> [Verify Baseline] -> [Execute Edit] -> [Verify Tests] -> [Report Evidence]
```

1. **Exploration:** Read relevant docs (`README.md`, `.engineering/`) and recent commits (`git log -n 5 --oneline`).
2. **Minimal Invasiveness:** Plan edits at the exact interface seam. Keep diffs minimal and atomic.
3. **Verification:** Run existing tests before editing. Add regression tests for touched code. Confirm linters pass.

---

## 4. Expected Deliverables
Every completed task must provide:
1. **Summary of Change:** High-level description of what was changed and the technical rationale.
2. **Files Touched:** Complete list of modified, added, or removed file paths.
3. **Verification Evidence:** Terminal output demonstrating passing tests, linting runs, or validation checks.
4. **Residual Risks:** Document any remaining edge cases, performance considerations, or migration requirements.

---

## 5. Progressive Disclosure (Reference Documents)
Consult these bundled documents only when specific deep guidance is needed:

- **Detailed exploration patterns:** Consult [understand-before-modifying.md](references/understand-before-modifying.md).
- **Autonomy boundaries & permissions:** Consult [balanced-autonomy.md](references/balanced-autonomy.md).
- **Pre-change verification:** Consult [pre-modification-checklist.md](checklists/pre-modification-checklist.md).
- **Task completion verification:** Consult [task-completion-checklist.md](checklists/task-completion-checklist.md).
- **Complex debugging log format:** Consult [investigation-log.md](templates/investigation-log.md).
Files in this package (6)
  • SKILL.md 4 KB
  • checklists/pre-modification-checklist.md 1 KB
  • checklists/task-completion-checklist.md 1 KB
  • references/balanced-autonomy.md 1 KB
  • references/understand-before-modifying.md 1 KB
  • templates/investigation-log.md 1 KB

Versions

The database has no other skills named engineering-core.

Database snapshot: 13.11.2026 · package version 3ba44d4336bf (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100p8-engine
    Engineering methodology skill for all tasks. Core behaviors: clarify before assuming, investigate before asking, verify before delivering, review full dependency chains, match existing code style. Trigger on: any task start, code development, debugging, multi-step work. Do NOT…
  • 100software-engineering
    For use only in threads for this proactive personal assistant. Investigate software issues; inspect, write, review, or test code; work on a repository or local engineering file; or create, fix, or monitor a pull request or CI run. Use for actual engineering or product QA work,…
  • 100engineering-workflow
    The spine of all engineering work — the non-negotiable rules that hold across analysis, planning, implementation, debugging, testing, optimisation, documentation and deployment, plus which specialised skill owns each stage. Use at the start of any non-trivial change,…
  • 90frontend-ui-engineering
    Component architecture, design systems, state management, responsive design, WCAG 2.1 AA accessibility. Use when building or modifying user-facing interfaces.
  • 90feature-flow
    My default workflow for non-trivial features at work — understand read-only → plan mode + grill me on six fork categories → implement per approved plan → verify honestly. Use when starting any feature or non-trivial change in one of my work repos, when a prompt contains a…
  • 100windsurf-core-workflow-a
    Execute Windsurf primary workflow: Core Workflow A. Use when implementing primary use case, building main features, or core integration tasks. Trigger with phrases like "windsurf main workflow", "primary task with windsurf".

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.