SKILLEMALL.ai
GitHub ↗ RU Sign in

AF Living ADR

Living Architecture Decision Records — automatically draft, number, and update ADRs from git diffs, PR descriptions, or plain-English decisions. Detects architectural signals in code changes (new database tables, new auth methods, new external integrations, framework changes) and drafts a pre-filled ADR in the RFC 822 / Nygard format. Also marks existing ADRs as "Superseded" when new decisions replace them. Outputs to docs/adr/ with sequential ADR-NNN numbering. Zero external API — works entirely from your codebase and git history. Triggers on "write ADR", "document this decision", "architecture decision", "new ADR", "living adr", "/living-adr".

ClawHub Agent Skills author: Lucius Pang v1.0.3 MIT-0 2 files body ≈ 2 704 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 51/100 · Will not run — References files that are not bundled: ADR-${NEXT_NUM}-${SLUG}.md, $fname

GeneratorSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
91/100
safety, quality, tests
Safety 60%
100
Quality 40%
78
Run on models
none yet
Process rating
F
51/100
Will not run
References files that are not bundled: ADR-${NEXT_NUM}-${SLUG}.md, $fname
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning missing-ref reference to a missing file: ADR-${NEXT_NUM}-${SLUG}.md
  • warning missing-ref reference to a missing file: $fname
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 51/100

Will not run. References files that are not bundled: ADR-${NEXT_NUM}-${SLUG}.md, $fname
  • 0Tools and files. 2 referenced file(s) missing: ADR-${NEXT_NUM}-${SLUG}.md, $fname
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 40Consistency. Frontmatter name (Living ADR) differs from the folder (phy-living-adr)
  • 55Failures and branches. 1 branches
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 14 steps
  • 100Execution cost. Instruction body is 2704 tokens
  • 100Running it twice. Mutating operations check current state
  • low 13 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +2Single-language instructions
  • +5Description quotes 7 example trigger phrases
  • +3Description length 653: enough signal without eating the budget
  • +4Structure: 20 headings
  • +3Step-by-step instructions: 14 items
  • +3Output format is stated explicitly
  • +4Has examples (17 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.

External checks

ClawHub: clean
This skill is a local ADR documentation helper that reads repository context and creates or updates markdown files in a disclosed, purpose-aligned way.
LLM: benign (high) · VirusTotal: · 29 May 2026