Browse Secure Claude Skills
Search verified agent skills and review security grades before installing · full A–Z index
- Designing Routing And Ranking PoliciesUse typed decision calls to choose workers, tools, models and next steps, and to score sources, while code enforces the result.Votes: 0GitHub stars: 2
- Checking Post Action ResultsConfirm an agent action changed the world as intended by comparing a pre-written expected outcome with fresh evidence gathered after it ran.Votes: 0GitHub stars: 2
- Calibrating Confidence Thresholds And Escalation PathsTurn a decision model's confidence scores into measured thresholds that decide when an agent acts, falls back, or escalates.Votes: 0GitHub stars: 2
- Building Idealized InfluenceEarn trust by modeling the standards you expect, putting the group's needs first, and acting consistently with shared values.Votes: 0GitHub stars: 2
- Applying Loop Termination And Continuation RulesWrite explicit done, failure, budget, stall and approval rules before an agent loop runs, then apply them after every iteration.Votes: 0GitHub stars: 2
- Workers Best PracticesReviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.Votes: 0GitHub stars: 2
- Modern CppWrite, review, and modernize C++ with repository-compatible language features, precise interfaces, RAII, explicit ownership, safe concurrency, and measured hardening. Use for C++ implementation, refactoring, API design, or safety review; do not use for pure C or build-system-only work.Votes: 0GitHub stars: 2
- Code StandardsGovern implementation, bug fixes, and refactors from repository orientation through scoped research, planning, evidence-led tests, implementation, review, verification, and handoff. Use for any code change; combine it with the relevant language skill for C, C++, Rust, assembly, or another stack.Votes: 0GitHub stars: 2
- Code Quality Review[Code Quality] Use when evaluating received review feedback, reviewing named code on request, or verifying a completion claim. Current diffs: changes-review; rationale: why-review.Votes: 0GitHub stars: 3
- Code Quality Review[Code Quality] Use when evaluating received review feedback, reviewing named code on request, or verifying a completion claim. Current diffs: changes-review; rationale: why-review.Votes: 0GitHub stars: 3
- Praxis TddUse when implementing any feature or bugfix with strict baby-steps TDD - enforces minimal code and mandatory checkpointsVotes: 0GitHub stars: 3
- Praxis ReviewUniversal code review - auto-detects scope from git changes, spec, commit, or brief. Use after completing tasks, implementing major features, before merging, when stuck (fresh perspective), before refactoring (baseline check), or after fixing complex bugs.Votes: 0GitHub stars: 3
- Plan ArbiterUse when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed plans, session IDs, transcripts, plan documents, PR descriptions, or pasted strategies; or when the user wants one recommended execution plan after agents review each other's proposals.Votes: 0GitHub stars: 17
- Dim ReviewReview an order's whole diff against its Build artifact, one agent per area, and return findings or the Review artifact. Use as the reviewer, when a brief names dim-review.Votes: 0GitHub stars: 5
- Dim BuildBuild an approved plan slice by slice — write test first, verify, simplify, check for correctness and pattern fit, and commit each slice through the gates, answering every finding. Use as the builder, when a brief names dim-build.Votes: 0GitHub stars: 5
- Gator GateValidate and monitor OpenShell GitHub issues and PRs using the gator:* state machine. Use when asked to triage issues/PRs for project validity, gate PRs, run gator, validate submissions, or monitor PRs toward merge readiness.Votes: 0GitHub stars: 3
- CavecrewWhen to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.Votes: 0GitHub stars: 9
- Flow 5 Review CheckParanoid red-team pass over the fixes made during review, re-verifying each oneVotes: 0GitHub stars: 1,992
- BddBehavior-first feature development — use when building newVotes: 0GitHub stars: 19
- Ralph Review TrioRun a sequential three-tier code review on a finished implementation branch — Haiku (surface) → Sonnet (logic) → Opus (deep). Restarts from Tier 1 on any tier failure, bounded, ending in a stop-and-report. Use when a solo branch or PR is code-complete and you want structured pre-merge verification before human review.Votes: 0GitHub stars: 2