Skill
chaos-engine
Canonical provider-neutral skill router and working contract. Use at the start of every task, on every host, in every main thread…
@shafthqInstall SkillTesting
Skill
/architect
Use for design-level judgement: requirements, quality attributes, trade-offs, ADR, contracts, resilience, security, observability, refactor, debug, review, debt.
Install
$ npx -y skills add ShaftHQ/SHAFT_ENGINE --skill architect --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/architect
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use for design-level judgement: requirements, quality attributes, trade-offs, ADR, contracts, resilience, security, observability, refactor, debug, review, debt.
SKILL.md
architect.SKILL.mdname: architect
description: >-
Use for design-level judgement: requirements, quality attributes, trade-offs,
ADR, contracts, resilience, security, observability, refactor, debug, review,
debt.
license: MIT
Architect
Judgement cards for design-level work. Core [triage](../chaos-engine/SKILL.md#triage) sets depth; [Ponytail](../../companions/ponytail-ultra.md) still caps scope. Load ONE card file below, not all.
First: retrieve
1. `python3 .chaos-engine/tool.py retrieve --store graphify "<module> callers dependencies"`: blast radius, seams, who breaks. 2. `python3 .chaos-engine/tool.py retrieve --store mempalace "<topic> decision ADR gotcha"`: prior decisions, rejected options, lessons. 3. Record `retrieve: used`. Contradicts a prior decision: cite it, supersede it in the ADR, never silently diverge.
Tier → cards
| Triage tier | Use | | --- | --- | | One file, reversible | 18 debug, 19 review only | | One module, reversible | add 1, 3, 9, 16, 17 | | Public contract / hard to reverse | all relevant; 4 ADR mandatory |
Card index
| # | Card | Rule | File | | --- | --- | --- | --- | | 1 | Requirements | Testable acceptance criteria + non-goals before design. | [analyze](references/analyze.md#1-requirements) | | 2 | Quality attributes | Name top 3 (ISO 25010) as measurable scenarios. | [analyze](references/analyze.md#2-quality-attributes) | | 3 | Trade-offs | 2+ options, criteria from 2, pick by reversibility. | [analyze](references/analyze.md#3-trade-offs) | | 4 | ADR | Hard-to-reverse choice gets a 10-line ADR. | [analyze](references/analyze.md#4-adr) | | 5 | C4 sketch | Multi-component change: context + container diagram. | [analyze](references/analyze.md#5-c4-sketch) | | 6 | API contracts | Additive change; versioned; idempotent; Hyrum's law. | [design](references/design.md#6-api-contracts) | | 7 | Boundaries | Domain inward, I/O outward; depend on stable things. | [design](references/design.md#7-boundaries) | | 8 | Domain language | Code names = domain words; one context, one model. | [design](references/design.md#8-domain-language) | | 9 | Principles | SOLID/DRY/KISS/YAGNI calibrated; rule of three. | [design](references/design.md#9-principles) | | 10 | Patterns | Pattern by forces present today, never speculative. | [design](references/design.md#10-patterns) | | 11 | Failure modes | Timeout, bounded retry+jitter, idempotency, breaker. | [operate](references/operate.md#11-failure-modes) | | 12 | Observability | Structured logs, RED metrics, traces, SLO. | [operate](references/operate.md#12-observability) | | 13 | Security | Trust boundaries, STRIDE-lite, least privilege. | [operate](references/operate.md#13-security) | | 14 | Performance | Measure first; budget; fix the bottleneck only. | [operate](references/operate.md#14-performance-and-scale) | | 15 | Data | Expand/contract migrations; one writer per fact. | [operate](references/operate.md#15-data-and-state) | | 16 | Test strategy | Risk-based mix; contract tests at boundaries. | [change](references/change.md#16-test-strategy) | | 17 | Refactor/legacy | Characterize, then small safe steps; strangler. | [change](references/change.md#17-refactoring-and-legacy) | | 18 | Debugging | Root cause before fix; 3 failed fixes → rethink. | [change](references/change.md#18-debugging) | | 19 | Review | Design > correctness > tests > clarity; severity. | [change](references/change.md#19-review) | | 20 | Tech debt | Name it, price it, file it; pay where you touch. | [change](references/change.md#20-tech-debt) |
Sources: [sources](references/sources.md).
Read more
name: architect description: >- Use for design-level judgement: requirements, quality attributes, trade-offs, ADR, contracts, resilience, security, observability, refactor, debug, review, debt. license: MIT
Architect
Judgement cards for design-level work. Core [triage](../chaos-engine/SKILL.md#triage) sets depth; [Ponytail](../../companions/ponytail-ultra.md) still caps scope. Load ONE card file below, not all.
First: retrieve
1. `python3 .chaos-engine/tool.py retrieve --store graphify "<module> callers dependencies"`: blast radius, seams, who breaks. 2. `python3 .chaos-engine/tool.py retrieve --store mempalace "<topic> decision ADR gotcha"`: prior decisions, rejected options, lessons. 3. Record `retrieve: used`. Contradicts a prior decision: cite it, supersede it in the ADR, never silently diverge.
Tier → cards
| Triage tier | Use | | --- | --- | | One file, reversible | 18 debug, 19 review only | | One module, reversible | add 1, 3, 9, 16, 17 | | Public contract / hard to reverse | all relevant; 4 ADR mandatory |
Card index
| # | Card | Rule | File | | --- | --- | --- | --- | | 1 | Requirements | Testable acceptance criteria + non-goals before design. | [analyze](references/analyze.md#1-requirements) | | 2 | Quality attributes | Name top 3 (ISO 25010) as measurable scenarios. | [analyze](references/analyze.md#2-quality-attributes) | | 3 | Trade-offs | 2+ options, criteria from 2, pick by reversibility. | [analyze](references/analyze.md#3-trade-offs) | | 4 | ADR | Hard-to-reverse choice gets a 10-line ADR. | [analyze](references/analyze.md#4-adr) | | 5 | C4 sketch | Multi-component change: context + container diagram. | [analyze](references/analyze.md#5-c4-sketch) | | 6 | API contracts | Additive change; versioned; idempotent; Hyrum's law. | [design](references/design.md#6-api-contracts) | | 7 | Boundaries | Domain inward, I/O outward; depend on stable things. | [design](references/design.md#7-boundaries) | | 8 | Domain language | Code names = domain words; one context, one model. | [design](references/design.md#8-domain-language) | | 9 | Principles | SOLID/DRY/KISS/YAGNI calibrated; rule of three. | [design](references/design.md#9-principles) | | 10 | Patterns | Pattern by forces present today, never speculative. | [design](references/design.md#10-patterns) | | 11 | Failure modes | Timeout, bounded retry+jitter, idempotency, breaker. | [operate](references/operate.md#11-failure-modes) | | 12 | Observability | Structured logs, RED metrics, traces, SLO. | [operate](references/operate.md#12-observability) | | 13 | Security | Trust boundaries, STRIDE-lite, least privilege. | [operate](references/operate.md#13-security) | | 14 | Performance | Measure first; budget; fix the bottleneck only. | [operate](references/operate.md#14-performance-and-scale) | | 15 | Data | Expand/contract migrations; one writer per fact. | [operate](references/operate.md#15-data-and-state) | | 16 | Test strategy | Risk-based mix; contract tests at boundaries. | [change](references/change.md#16-test-strategy) | | 17 | Refactor/legacy | Characterize, then small safe steps; strangler. | [change](references/change.md#17-refactoring-and-legacy) | | 18 | Debugging | Root cause before fix; 3 failed fixes → rethink. | [change](references/change.md#18-debugging) | | 19 | Review | Design > correctness > tests > clarity; severity. | [change](references/change.md#19-review) | | 20 | Tech debt | Name it, price it, file it; pay where you touch. | [change](references/change.md#20-tech-debt) |
Sources: [sources](references/sources.md).
Ships withshaft-engine
One Java engine for web, mobile, API, CLI, database, and desktop. Drivers, waits, and evidence are handled. Every run ends in an Allure report. Upgrade to SHAFT_ENGINE · ▶ Watch the 26-second clip with sound and captions · 100-second overview
Get the whole plugin
Other skills on shaft-engine.
@shafthqInstall SkillSkill
ci-cd
Use when PR merge waits are long or CI/CD is being designed, audited, or sped up: targets, PR/main/nightly tiers, opt-in labels,…
@shafthqInstall SkillSkill
colibri
Frontier MoE through a disk/RAM/VRAM hierarchy via the optional Colibri process. Use when a large-model offline job needs…
@shafthqInstall SkillSkill
freetoken
Standalone FreeToken process: install, READY probe and bounded dispatch. Use when the local-runtimes table points a job at…
@shafthqInstall SkillSkill
git-cleanup
Use when a git worktree is dirty or another local branch or worktree exists. Ask before cleanup unless the session is unattended.
@shafthqInstall Skill