All authors
Claude Skills by Eliyce
github.com/Eliyce110 skills4 installs208 views
- Rate Limiting ReviewIdentify missing rate limiting and denial-of-service surfaces on authentication endpoints, bulk operations, expensive queries, and WebSocket handlers.Votes: 0GitHub stars: 8
- Retest VerificationRe-evaluate prior pentest findings against fresh local evidence.Votes: 0GitHub stars: 8
- Runtime Surface ProbingPlan and interpret safe runtime checks against a locally running application.Votes: 0GitHub stars: 8
- Stride Threat ModelEnumerate threats systematically using STRIDE before scripted checks run so all downstream findings map to a threat category.Votes: 0GitHub stars: 8
- FixturesNo description providedVotes: 0GitHub stars: 8
- Sample SkillSample bundled skill fixtureVotes: 0GitHub stars: 8
- Expert Need DetectorDecide, from the request and the S0 grounding, which domain experts (db, security, ui, ...) the spec pipeline needs — the one model call that replaces a deterministic signal-scorer, because no script can reliably tell which expert a request needs without emitting false signals. Emits a roster-constrained JSON need artifact the pipeline script validates and records. Phase 2 of the spec pipeline (issue #521). TS guard is `src/spec-pipeline/experts/need.ts`.Votes: 0GitHub stars: 8
- Expert NotesRead one expert's brief and, through that expert's lens, write short request-time notes for the spec pipeline — what this request must do, must never break, and still leaves undecided — as findings plus plain-language questions. One runner skill with a lens per expert (db, security, ui, ...), so the procedure is shared and only the lens differs. The pipeline script validates the output against the roster; it never decides. Phase 2 of the spec pipeline (issue #547). TS guard is `src/spec-pipel...Votes: 0GitHub stars: 8
- Expert SynthesisThe chief architect for the spec pipeline. Read the request, the grounding, every expert note and the script's merge, then accept or decline each finding with a reason, recommend a resolution for each conflict (never apply it), list the gaps nobody covered, and give a readiness verdict. It is never picked by the detector; it runs automatically once any expert fired, and it may not invent a finding. The pipeline script validates the output and turns each conflict into a decision packet. Phase ...Votes: 0GitHub stars: 8
- Test Runner DiscoveryWhen no script can classify how a project's test runner parallelizes, read the manifests and lockfiles, decide whether a parallel mode exists and its prerequisite is installed, and emit a validated JSON record for `paqad-ai checks record-runner`. Issue #554, Part B.5. The deterministic guard is the `checks record-runner` verb (src/checks/record-runner.ts), which validates the result against an argv allowlist and never trusts it.Votes: 0GitHub stars: 8