Automated summary
Structures architect mentoring for senior engineers around a competency rubric, architecture katas, paired ADR authoring, and design-review shadowing.
Strengths
- Provides an end-to-end operating frame: rubric-based assessment, 90-day goals, weekly practice, and quarterly recalibration
- Ships concrete copyable artifacts such as the Markdown growth plan and a defined output format
- Names realistic mentoring pitfalls (mentor monologues, pattern memorization, missing artifacts) with practical fixes
Limitations
- Assumes a published competency rubric, access to live design work, and ~2-3 hours per week of mentor capacity already exist
- Leans heavily on external references (Larson, Hohpe, Neward, ATAM) without explaining their content
- Offers limited guidance on measuring program effectiveness beyond skill-matrix deltas
Use it when promoting a senior engineer toward staff/principal/architect roles or building an internal architect bench.
Skip it when no competency rubric or access to real design artifacts exists, or when the psychological safety needed for practice drills isn't in place.
Security analysis
SafeThe skill is purely instructional mentoring content. It declares no tools, executes no commands, accesses no secrets or network resources, and contains no destructive or exfiltration behavior. All referenced artifacts are documentation and meeting practices.
No concerns found
How this analysis is madeExamples
Draft a Q2 2026 growth plan to move our senior backend engineer toward staff architect, including 3-5 outcome-based goals, a weekly cadence, and the evidence links I should collect.Create a weekly architecture kata and ADR drill that forces trade-off reasoning on four quality attributes, plus the reflection questions to ask in the paired session.Our architect mentoring program produces no visible artifacts and the mentor does most of the talking — review this against the pitfalls table and propose fixes for the next quarter.name: technical-mentoring description: Mentor engineers on architecture skills with structured growth paths, deliberate practice, and design-review pairing. Use when developing senior/staff/principal engineers, building an internal architect bench, or coaching individuals through ADRs, trade-off analysis, and stakeholder communication.
Technical Mentoring for Architects
Architecture is a craft learned through reps, feedback, and reflection. Effective mentoring pairs explicit competency models with low-stakes practice (katas, shadowing) and high-stakes pairing (real ADRs, real reviews) so mentees internalize trade-off thinking, not just patterns.
Stack Baseline (2026)
| Concern | Recommended | | --- | --- | | Competency model | Staff Engineer Archetypes (Larson) + Hohpe Architect Elevator floors | | Growth framework | T-shaped depth + breadth across c4model.com layers | | Practice format | Architecture Kata (Ted Neward), ADR drills, brown-bag teardowns | | Feedback loop | Weekly 1:1 + paired ADR authoring + review shadowing | | Reference texts | Fundamentals of Software Architecture 2e, The Software Architect Elevator | | Tracking | Skill matrix in Markdown/Notion; quarterly calibration |
When to Use
- Promoting senior engineers toward staff/principal/architect roles.
- Onboarding a new architect to the org's domain and decision style.
- Closing gaps surfaced in architecture reviews (e.g., weak NFR analysis).
- Building a mentoring program inside a guild or chapter.
Prerequisites
- A published competency rubric (levels, behaviors, evidence).
- Access to live design work: ADRs, RFCs, review meetings.
- Mentor capacity (~2-3 hrs/week per mentee) and a 6-12 month horizon.
- Psychological safety: mistakes in drills must not affect performance reviews.
Instructions
flowchart LR
A[Assess: rubric + 360] --> B[Plan: 90-day growth goals]
B --> C[Practice: katas + ADR drills]
C --> D[Pair: real reviews + RFCs]
D --> E[Reflect: 1:1 + journal]
E --> F[Recalibrate quarterly]
F --> B
- Assess with a 2026 rubric covering: systems thinking, NFR reasoning, communication (Elevator floors), influence, and tech breadth.
- Plan three to five outcome-based goals per quarter (e.g., "Author 2 ADRs that survive review with <3 substantive comments").
- Practice weekly: one architecture kata, one anti-pattern teardown, or one capacity estimation drill.
- Pair on real artifacts: co-author an ADR, co-facilitate an ATAM-lite, shadow a vendor evaluation.
- Reflect in 30-min 1:1s using the prompt: what decision, what trade-off, what you'd change.
# Mentee Growth Plan — Q2 2026
Mentee: <name> Mentor: <name>
Target level: Staff Engineer (Architecture track)
## Goals
1. Lead 1 cross-team ADR end-to-end (draft -> review -> accepted).
2. Facilitate 2 architecture reviews using ATAM-lite checklist.
3. Publish 1 internal teardown of an anti-pattern from our codebase.
## Cadence
- Weekly 1:1 (Tue 30m), paired ADR session (Thu 60m)
- Monthly review with skip-level
## Evidence
Links to ADRs, review notes, recordings.
Common Pitfalls
| Pitfall | Why it hurts | Fix | | --- | --- | --- | | Pattern memorization over trade-offs | Produces Golden Hammer thinkers | Force "what would change your mind?" in every drill | | Mentor monologues | Mentee never practices the muscle | Mentor talks <30% of the time; ask, don't tell | | No artifacts | Growth is invisible at calibration | Require ADR/RFC outputs each cycle | | One-floor mentoring | Mentee can talk to peers but not execs | Rotate across Hohpe Elevator floors quarterly | | Skipping NFRs | Designs collapse under load/regulation | Every kata must score on 4+ quality attributes |
Output Format
- A growth plan (Markdown) with goals, cadence, and evidence links.
- A skill-matrix delta showing pre/post scores per competency.
- A portfolio folder of mentee-authored ADRs and review notes.
- A quarterly retro summarizing wins, gaps, and next-quarter focus.
Authoritative References
- Mark Richards & Neal Ford, Fundamentals of Software Architecture, 2e (O'Reilly, 2024).
- Gregor Hohpe, The Software Architect Elevator (O'Reilly).
- Will Larson, Staff Engineer — archetypes and growth paths.
- Ted Neward, Architecture Kata format — neward.net/architecturalkatas.
- ThoughtWorks Technology Radar (latest volume) — thoughtworks.com/radar.
- GitHub ADR community — github.com/joelparkerhenderson/architecture-decision-record.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/technical-mentoring-for-architects-mrwakd20/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/technical-mentoring-for-architects-mrwakd20' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/technical-mentoring-for-architects-mrwakd20/download' --output '.skill-downloads/technical-mentoring-for-architects-mrwakd20/SKILL.md.part' && mv '.skill-downloads/technical-mentoring-for-architects-mrwakd20/SKILL.md.part' '.skill-downloads/technical-mentoring-for-architects-mrwakd20/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Original excerpt: Prerequisites
- A published competency rubric (levels, behaviors, evidence).
- Access to live design work: ADRs, RFCs, review meetings.
- Mentor capacity (~2-3 hrs/week per mentee) and a 6-12 month horizon.
- Psychological safety: mistakes in drills must not affect performance reviews.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/technical-mentoring-for-architects-mrwakd20/SKILL.md' && test -s '.skill-downloads/technical-mentoring-for-architects-mrwakd20/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/technical-mentoring' && cp -R '.skill-downloads/technical-mentoring-for-architects-mrwakd20' '.claude/skills/technical-mentoring'Cursor
test -f '.skill-downloads/technical-mentoring-for-architects-mrwakd20/SKILL.md' && test -s '.skill-downloads/technical-mentoring-for-architects-mrwakd20/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/technical-mentoring' && cp -R '.skill-downloads/technical-mentoring-for-architects-mrwakd20' '.cursor/skills/technical-mentoring'Codex
test -f '.skill-downloads/technical-mentoring-for-architects-mrwakd20/SKILL.md' && test -s '.skill-downloads/technical-mentoring-for-architects-mrwakd20/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/technical-mentoring' && cp -R '.skill-downloads/technical-mentoring-for-architects-mrwakd20' '.agents/skills/technical-mentoring'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/technical-mentoring-for-architects-mrwakd20'openskills read 'technical-mentoring-for-architects-mrwakd20'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/technical-mentoring-for-architects-mrwakd20/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.