CtrlK
BlogDocsLog inGet started
Tessl Logo

architecture-decision-records

Capture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is.

60

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/architecture-decision-records/SKILL.md

The canonical home for this skill is tdg-personal/architecture-decision-records

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear, checkpointed workflow and concrete file conventions, and it avoids concept-explanation padding. The two weak spots are mild verbosity in the encyclopedic reference sections and a single-file structure that could offload the template/index into reference files for cleaner progressive disclosure.

Suggestions

Trim or collapse the 'Categories of Decisions Worth Recording' table and the explicit/implicit detection-signal lists, since the When-to-Activate section already covers the core triggers.

Move the full ADR format template and the ADR index format into a reference file (e.g. references/adr-template.md) and link to it from the body, keeping SKILL.md as a lean overview.

Consider whether the 'Integration with Other Skills' section is actionable guidance or aspirational context; if the latter, cut it to save tokens.

DimensionReasoningScore

Conciseness

The body is well-organized and assumes Claude's competence (no basic-concept padding), but the 8-row categories table, the explicit/implicit detection-signal lists, and the integration section are comprehensive enough to be trimmed, sitting at 'mostly efficient but could be tightened' rather than 'every token earns its place'.

2 / 3

Actionability

Concrete guidance throughout — exact file paths (docs/adr/NNNN-decision-title.md), a copy-ready ADR template, the index format, naming conventions, and exact response strings — so an instruction-only skill still meets the fully-actionable anchor without needing executable code.

3 / 3

Workflow Clarity

The 8-step capture workflow is clearly sequenced with explicit validation/approval checkpoints (Step 1 asks confirmation before creating files; Step 7 requires explicit approval before writing and discards on decline), providing the feedback loop the rubric rewards.

3 / 3

Progressive Disclosure

No bundle files exist and the skill is a single well-sectioned document, but at ~180 lines it exceeds the under-50-line simple-skill exemption, and the full ADR template plus index format are inline content that could be split into reference files — 'some structure but content that should be separate is inline'.

2 / 3

Total

10

/

12

Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly and specifically communicates what the skill does in third person, with a distinct niche. Its main weakness is the missing explicit "Use when…" trigger guidance, which caps completeness and leaves trigger-term coverage at natural conversational phrasing only implied.

Suggestions

Add an explicit 'Use when…' clause naming natural user triggers, e.g. 'Use when the user says "let's record this decision", "ADR this", or asks "why did we choose X?"'

Surface conversational trigger terms ("ADR this", "record this decision", "why did we choose") in the description itself, not only in the body's When-to-Activate section.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Capture architectural decisions…as structured ADRs", "Auto-detects decision moments", "records context, alternatives considered, and rationale", "Maintains an ADR log" — matching the multiple-specific-actions anchor.

3 / 3

Completeness

The "what" is clearly stated, but "when" is only implied via "Auto-detects decision moments" with no explicit "Use when…" trigger clause, so per the judging guidelines completeness is capped at 2.

2 / 3

Trigger Term Quality

Contains relevant domain terms ("architectural decisions", "ADR", "decision moments", "rationale") but lacks the conversational trigger phrasing users would naturally say (e.g. "let's record this decision", "why did we choose X") and common variations, so it sits at the some-keywords anchor rather than good coverage.

2 / 3

Distinctiveness Conflict Risk

"Architectural decisions" and "ADRs" form a clear, distinct niche with little overlap risk against other skills, matching the clear-niche anchor.

3 / 3

Total

10

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 3 missing

Warning

Total

14

/

16

Passed

Repository
affaan-m/ECC
Reviewed

Table of Contents

Is this your skill?

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.