Adr Writing
v1.0.1Use when writing or formatting an ADR document using the MADR template, applying Definition of Done (E.C.A.D.R.) criteria, or verifying ADR completeness. Tri...
⭐ 0· 150·1 current·1 all-time
byKevin Anderson@anderskev
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the provided assets: MADR template, DoD checklist, and a small helper script to allocate sequence numbers. The included script and reference files are appropriate for creating ADRs.
Instruction Scope
SKILL.md directs the agent to read repo paths (docs/adrs), load local reference templates, run the included next_adr_number.py script, and write files to docs/adrs/NNNN-slugified-title.md. This is expected, but the agent will have filesystem read/write access in the repository and may be asked to 'gather context' (e.g., related code, PRs) which could require additional repository access or user-provided links.
Install Mechanism
No install spec; instruction-only skill plus a small Python script. Nothing is downloaded or executed from remote sources.
Credentials
No environment variables or credentials are requested. The workflow suggests checking PRs/issues for context but does not request tokens — if the agent is to access remote issue trackers or CI systems, explicit credentials would be needed outside this skill; absence of such credentials is reasonable but users should be aware.
Persistence & Privilege
Skill is not always-enabled and does not request elevated platform privileges. It writes ADR files within the repo (normal for this purpose) and does not modify other skills or global agent configuration.
Assessment
This skill is coherent for writing MADR-format ADRs: it reads local ADR directories, uses the included template and checklist, and can generate a correctly front‑mattered Markdown file. Before installing or running: (1) review and be comfortable with the small Python script (it only lists and parses filenames and locates the repo root; it does not modify files or call the network), (2) be aware the skill will read and write files under the repository (docs/adrs/) so run it in the correct working directory or a safe environment, and (3) if you expect the agent to pull context from remote PRs/issues, you will need to supply or authorize access to those services separately (no tokens are requested by the skill). Finally, avoid calling the allocation script concurrently without a pre-assigned number to prevent duplicate ADR numbers.Like a lobster shell, security has layers — review code before you run it.
latestvk978kmkx3j10z9jwvw83dp070s84p54m
License
MIT-0
Free to use, modify, and redistribute. No attribution required.