Use to remove dead code, duplication, indirection, or unnecessary complexity while preserving behavior.
Skills in this repository
douglance/sdlc-plugin - Page 2
SkillsMP has collected 78 skills from douglance/sdlc-plugin. Open a skill to review its source and details.
douglance/sdlc-pluginShowing 38 of 78 collected skills.
Use when a live service needs observability, incident response, SLOs, runbooks, or continuity work.
Use when a validated nontrivial change needs milestones, dependencies, risks, and an explicit out-of-scope boundary.
Use for independent verification, validation, inspection, and quality judgment beyond whether tests pass.
Use when a request is ambiguous, high-blast-radius, difficult to reverse, or missing a material product decision.
Use after implementation to probe edge cases, failure modes, malformed input, scale, security, and contradictions.
Use when creating or reviewing a user-facing layout, state, illustration, document, slide, motion treatment, or rendered visual result.
Use for consequential handoffs, blockers, completion reports, requirements, procedures, interface content, or formal documentation that must be easy to act on.
Use for consequential handoffs, blockers, completion reports, requirements, procedures, interface content, or formal documentation that must be easy to act on.
Use when designing a public API, schema, module boundary, or frontend-backend contract.
Use when a failure's cause is unknown, evidence conflicts, or an initial fix did not solve the problem.
Use when tested code must be released with versioning, rollout, smoke checks, and a rollback path.
Use when a nontrivial change has unsettled interfaces, contracts, file structure, trade-offs, or verification boundaries.
Use to remove unnecessary generated patterns from the current diff without changing behavior.
Use when a consequential decision, public contract, or durable rationale must be recorded for future maintainers.
Use after behavior ships or an interface changes when documentation must be created, corrected, or verified against the source.
Use when unfamiliar technology or constraints require sourced options and feasibility evidence before choosing an approach.
Use when proliferating rules, exceptions, adapters, or workarounds suggest the underlying model may be wrong and a falsifiable simpler model is needed.
Use when building or restyling a user-facing web interface where art direction and production-quality visual execution matter.
Use for commits, branching, merge conflicts, versioning, or integration across parallel workstreams.
Use when requirements are clear and code must be added, changed, or fixed against an observable success criterion.
Use when implementation should be split into multiple independently verifiable slices or commits.
Use when the user explicitly wants a plan, design, specification, approach, or decision stress-tested through disciplined questions.
Use when the user wants a proposal stress-tested against the domain model while terminology and project decision records are updated.
Use to create or review a formal, traceable lifecycle artifact or phase handoff that another person or system must consume.
Use to remove dead code, duplication, indirection, or unnecessary complexity while preserving behavior.
Use when a live service needs observability, incident response, SLOs, runbooks, or continuity work.
Use when a measured regression, explicit performance target, or profiler evidence identifies work to optimize.
Use when an accepted specification or plan must become ordered tasks, vertical slices, atomic commits, or parallel work boundaries.
Use when a validated nontrivial change needs milestones, dependencies, risks, and an explicit out-of-scope boundary.
Use for independent verification, validation, inspection, and quality judgment beyond whether tests pass.
Use when a request is ambiguous, high-blast-radius, difficult to reverse, or missing a material product decision.
Use when a request spans multiple lifecycle phases or the correct next phase is unclear.
Use for authentication, authorization, secrets, untrusted input, sensitive storage, or an explicit security review.
Use when a significant change needs a durable specification before implementation can begin safely.
Use when a behavior change or defect is best defined and protected by a failing test before implementation.
Use after implementation to probe edge cases, failure modes, malformed input, scale, security, and contradictions.
Use when creating or reviewing a user-facing layout, state, illustration, document, slide, motion treatment, or rendered visual result.