com um clique
deliberate-engineering
deliberate-engineering contém 12 skills coletadas de lucasfugisawa, com cobertura ocupacional por repositório e páginas de detalhe dentro do site.
Skills neste repositório
Use when applying any deliberate-engineering lens or standing rule. Reads ~/.claude/deliberate-engineering/overrides.md before applying catalog lenses or standing rules, honors disable/modify/add overrides, and declares each deviation. Stays silent when no override file exists or no override matches.
Use on software-engineering work — writing, reviewing, debugging, planning, migrating, shipping, or operating code, specs, schemas, or deploys. Establishes the standing rules of deliberate practice — calibrate autonomy and ceremony to consumers, risk, and reversibility; keep a human gate on irreversible and outward-facing actions; verify claims against primary evidence before endorsing; and treat trust as earned by convergence, not granted on a single pass. Skip for research, prose, ad-hoc analysis, disposable no-consumer scripts, and non-technical work.
Use when a live system behaves unexpectedly and you must diagnose under uncertainty or respond to an incident — error rates climbing, a flow broken with no known cause, a page you have to act on. You don't yet hold a reliable expectation; you're discovering what's true while the system may be degraded. Classifies the evidence quality and how irreversible being wrong is, then selects strategies from the catalog and dispatches superpowers for the debugging method. Distinct from verify: verify confirms an expectation you already hold; this is discovery under failure.
Use on demand to drive a pending candidate into the catalog systematically. Runs the leak-audit gate, classifies isolated vs structural, then (isolated) edits the catalog append-only + runs skill-reviewer or (structural) stops and recommends the proper design cycle. This is the promotion step of the author contribution flow — it drives a candidate into the shared catalog (working tree only, gated). It is not the contribute skill, which captures candidates, nor the adopter capture skill, which writes your personal override file. Stays silent unless invoked.
Use at the start of an engineering task when you're not sure which phase you're in, or for broad or multi-phase work — building a feature, changing a live system, chasing an incident, reviewing a diff, or shaping a design. It classifies the work, names the phase sequence and ceremony band, and routes to the matching selector (plan / review / verify / debug-operate), conducting between phases and stopping at the irreversible action. Skip for research, prose, and ad-hoc analysis.
Use when work spans phases or sessions and process state must survive — the current phase and phase sequence, the chosen ceremony band and rituals, open pendings, and the decisions made and why. Reads and rehydrates a per-work-unit working-note at the start of a session or phase, and rewrites it at Rule 6 checkpoints with a changed-since-read safety check. Delegates to a tracker or superpowers when one is present; falls back to its own note otherwise. Consulted by the router and Rule 6, not invoked directly; stays silent when there is no state to record.
Use after any baseline code review, or when reviewing a change, to deliberately select the right review lenses for THIS change instead of running a generic pass. Classifies by risk, reversibility, requirement clarity, and size, then applies matching strategies from the catalog. Less vibe coding, more deliberate craft.
Use when you need to establish that something is actually true in reality — not just plausible on paper: verifying a claim, number, or assumption against primary evidence; getting a change ready to merge; promoting across environments; confirming production behavior after a deploy; or mutating production data safely. Classifies what's being verified and how irreversible being wrong is, then selects the right strategies from the catalog. Distinct from code review: review asks 'does this look correct?', verification asks 'is it correct, and what's my evidence?'
Use when producing a communication around engineering work — a PR/MR description, a review comment, a message to a stakeholder, a handoff, or a writeup presenting alternatives. Classifies the communication by audience and artifact, then selects and applies the matching lenses from the catalog so the message is tuned to its reader and artifact instead of generic. Cross-cutting: consult it from any phase; it is not a phase itself.
Use on demand to capture what you did this session into durable overrides. Observes the full session transcript on disk (operator-typed messages only, mined via subagent fan-out) for deviations (you corrected/skipped a catalog lens or rule), patterns (recurring practice the catalog lacks), and calibration adjustments (recurring ceremony heavier/lighter than the default for a class of work), discusses candidates, and on approval appends disable/modify/add entries to ~/.claude/deliberate-engineering/overrides.md. This is the adopter's write side — it grows YOUR personal override file. It is not the author contribution tools (contribute/promote), which propose lenses for the shared catalog. Stays silent unless invoked.
Use on demand to turn generalizable engineering judgment from this session into clean catalog candidates. Observes review tactics, verification modes, planning disciplines, and debugging strategies, extracts employer-neutral principles, and on approval deposits pending candidate files in candidates/ for later promotion. This is the author/contributor write side — it proposes lenses for the shared catalog via the candidates/ queue. It is not the adopter capture skill, which grows your own personal override file. Stays silent unless invoked.
Use before building, when deciding what work to do and how to approach it — scoping a feature, shaping a spec or ticket, planning a migration or refactor, or choosing how much process a task calls for. Classifies the work by requirement clarity, risk, reversibility, and reach, then selects the right planning lenses: scope to the real requirement, ground the plan in the actual codebase, calibrate ceremony to risk, decompose and sequence safely, and capture the plan well — judgment applied to planning, not a planning engine.