Write and maintain Architecture Decision Records (ADRs) following best practices for technical decision documentation. Use when documenting significant technical decisions, reviewing past architectural choices, or establishing decision processes.
Install with Tessl CLI
npx tessl i github:Dicklesworthstone/pi_agent_rust --skill architecture-decision-records81
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Full MADR format ADR
Valid status value
100%
100%
Decision Drivers section
0%
100%
Multiple options with pros/cons
100%
100%
Rationale section
25%
100%
Positive consequences
100%
100%
Negative consequences
100%
100%
Risks with mitigations
100%
100%
Implementation Notes section
62%
100%
Related Decisions section
0%
100%
References section
100%
100%
docs/adr/ placement
0%
100%
NNNN-title-with-dashes.md naming
100%
100%
Without context: $0.2690 · 4m 17s · 11 turns · 81 in / 4,707 out tokens
With context: $0.6336 · 7m 40s · 28 turns · 481 in / 7,686 out tokens
ADR supersession workflow
New file, not edit
100%
100%
Supersedes reference in status
100%
100%
Old ADR status updated
100%
100%
Sequential file naming
100%
100%
Migration plan with phases
46%
100%
Considered alternatives
0%
100%
Positive and negative consequences
100%
100%
Context references old approach limitations
100%
100%
Related Decisions links ADR-0008
0%
100%
README index updated
100%
100%
Without context: $0.2479 · 5m 43s · 12 turns · 81 in / 3,890 out tokens
With context: $0.6762 · 9m 49s · 27 turns · 481 in / 8,429 out tokens
ADR directory structure and index
docs/adr/ directory
0%
100%
README index table columns
0%
100%
template.md present
0%
100%
NNNN-title-with-dashes.md naming
100%
100%
Index links to ADR files
37%
100%
adr-tools commands in setup script
0%
100%
Valid status values in ADRs
100%
100%
New ADR creation instructions
50%
100%
Both decisions documented with trade-offs
100%
100%
README index updated
85%
100%
Without context: $0.4939 · 5m 49s · 18 turns · 171 in / 8,304 out tokens
With context: $0.7188 · 11m 32s · 22 turns · 194 in / 10,555 out tokens
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.