architecture-principles
Architecture principles for manifest-dev: how its maintainer wants skills, wrappers, references, state and the workflow structured, and why. Use before planning, designing, building or reviewing a new skill or entry point, a change to where state or a decision lives, how skills call or coordinate with each other, or a wait or loop a workflow can enter.
How do I install this agent skill?
npx skills add https://github.com/doodledood/manifest-dev --skill architecture-principlesIs this agent skill safe to install?
- Gen Agent Trust Hubpass
This skill provides architectural guidelines for developers and contains no executable code or security risks.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Edit rule: each line is a principle with its reason and when it yields. Decisions go to the decision records, rules a check can hold go to the check, and a line is added only on a person's yes, after sharpening an existing line is ruled out.
- A new need lands on a mechanism, concept and state owner that already exist — figure-out, define, do, task files, the logs, the Ticket — before it earns a new skill, setting, file, ledger or surface, and a named entry is at most a thin wrapper that routes and restates no rule — a second loop or record is a second place to drift and disagree, every added concept is one more thing each user learns, and a rule in a wrapper reaches only runs that start there. Yields when no existing owner can carry it without changing what it means: then add the narrowest new one that closes the gap; or when people reach for a name: then add only the wrapper.
- Ship skills as the protocol, never the platform: no scheduler, hosting or host-bound runner; start from what the user already runs, use a host capability where it is offered and a plain path where it is not — infrastructure ties the project to one host and adds complexity each user carries. Yields to a coordinating skill, started by hand or by the user's own scheduler, when the alternative leaves users to build the machinery themselves.
- A skill that inspects or reports stays blind to its caller's workflow and returns what it saw with hints that name an action on the thing inspected, never a step of the caller's workflow; each decision lives once, in the skill that holds the context to make it, and a decision that belongs to one caller stays with that caller rather than in the path every caller shares — the caller steers toward the hint, a fixed set alone cannot cover the unexpected, a rule restated per caller drifts, and another caller that later wants something else can have it without disturbing the rest. No yield has been stated beyond the verdict itself, which stays fixed.
- Every wait or loop a workflow can enter has a stated exit — done, a bounded retry, or a named person — reading the prose missed these: they surfaced as a landing that stalled for good and an escalation that fired every tick. No yield has been stated.
- Work that may run again — a retry, a repeated event, a second worker, a restart — ends in the same state, each step starting from the state actually present, and an effect that must not happen twice, such as a charge or a message, is guarded by a key recorded before it fires — retries and restarts are certain over time, and work that assumes a single run duplicates or corrupts. Holds without a yield, since a run dying midway is only a matter of time.
- A decision that depends on shared state takes effect in one atomic step, or checked again after every pause — other writers act during each pause, so what was true before it may be false after. Yields when acting on a stale decision is shown to cost nothing.
- A record's status moves only through the single place that owns its lifecycle — a status set from several places reaches states no one designed. Holds without a yield.
Before calling architecture work done, check it against these principles from a fresh start — a new session, or a reviewer who did not do the work. Fix what departs unless the person chose the departure, and check again only after a fix, until a check finds none. Name each departure kept, with the principle and why.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/doodledood/manifest-dev/architecture-principles">View architecture-principles on skillZs</a>