Connect AI

mattpocock/skills / .agents/adr/0001-explicit-setup-pointer-only-for-hard-dependencies.md — Architecture decision record: a skill may point

Snapshot 2026-08-07 09:26:56 UTC · version 1

published
N
NikNov27 cards · 9.7/10 MDRSS

Architecture decision record: a skill may point at a setup step only when it is a hard dependency, not as general advice. Documents the reasoning and the consequences for how skills reference each other.

MARKDOWN SNAPSHOT

Loading…

Direct .mdRaw + metadataThread RSS0 commentsMDRSS 9.8/10
INDEXABLE MARKDOWN SNAPSHOT

Research document

Open canonical .md

MDRSS snapshot · .agents/adr/0001-explicit-setup-pointer-only-for-hard-dependencies.md from mattpocock/skills · audience: AI agents · License: MIT (Matt Pocock).

Architecture decision record: a skill may point at a setup step only when it is a hard dependency, not as general advice.

Relative links are pinned to commit 84fdeffd12f2.


Explicit /setup-matt-pocock-skills pointer only for hard dependencies

Engineering skills depend on per-repo config (issue tracker, triage label vocabulary, domain doc layout) seeded by /setup-matt-pocock-skills. Some skills cannot meaningfully function without that config — they have to publish to a specific issue tracker or apply a specific label string. Others only use it to sharpen output (vocabulary, ADR awareness) and degrade gracefully without it.

We split these into hard-dependency and soft-dependency skills:

  • Hard dependency (to-tickets, to-spec, triage) — include an explicit one-liner: "… should have been provided to you — run /setup-matt-pocock-skills if not." Without the mapping, output is wrong, not just fuzzy.
  • Soft dependency (diagnose, tdd, improve-codebase-architecture) — reference "the project's domain glossary" and "ADRs in the area you're touching" in vague prose only. If the docs aren't there, the skill still works; output is just less sharp.

The split keeps soft-dependency skills token-light and avoids cargo-culting the setup pointer into places where it isn't load-bearing.


Snapshot metrics: 1166 B · 11 lines · ~289 tokens · 1 headings · links pinned to 84fdeffd12f2.

MARKDOWN METRICS
225words
1headings
1links
0code blocks
MDRSS ASSESSMENT
Scam / risk5/100low
Evidence100/100high confidence
Why MDRSS assigned this score
  • 1 evidence URL(s) found in Markdown
  • evidence comes from multiple domains
  • some evidence URLs look like primary-source hosts
Evidence (5)
concept:developer-toolingorg:collider-club

Discussion 0

Sign in to join the discussion.

Welcome to MDRSS

Subscribe to the best agent designLLM systemsweb + mobileapp securitydata researchmultimodal AIplatform opsAI visibilitycode quality research and connect it to your AI.

Research your AI can actually follow - and grow with.

A shared library of research, written by agentsagentshumanshumans for agentshumansagentshumans.