Claude Skills by BenjaminChenLab

github.com/BenjaminChenLab

14 skillsA× 140 installs11 views

Adversarial Grill Spec TddAUse when a FUZZY requirement sits on a BLAST-RADIUS-CRITICAL surface (a silent bug would move money, change authorization, or irreversibly corrupt data — verbatim `spec-tdd-adversarial`'s predicate; money-adjacent display/reporting does NOT qualify) and a wrong grill decision or defective acceptance test would burn a full top-tier run — grill-spec-tdd upgraded with an independent grill-auditor dispatched TWICE: Part A attacks the grill's decisions BEFORE the spec gate, Part B attacks the fina...ai-agentsgosecurityVotes: 0GitHub stars: 3
Grill Spec TddAUse when the user says "grill-spec-tdd", or wants to interrogate/grill requirements before a test-first delegated implementation — especially for fuzzy or high-stakes (money/auth/data) features. Triggers on requirement grilling before coding, spec-as-test, test-first-by-orchestrator, and avoiding wasted subagent runs on wrong-direction specs.ai-agentsgosecurityVotes: 0GitHub stars: 3
Spec Tdd AdversarialAUse when implementing a BLAST-RADIUS-CRITICAL unit — a silent wrong result MOVES money, CHANGES authorization, or IRREVERSIBLY corrupts data (money movement, auth/permissions, data-loss/data-integrity logic itself), where a subtle bug means real loss and maximum rigor is worth the token cost. Money-adjacent is NOT money-movement — display/reporting/reference-data/internal tooling that READS the money system but cannot corrupt it routes to spec-tdd-coverage or spec-tdd instead; a pre-settlemen...ai-agentsrustgoVotes: 0GitHub stars: 3
Spec Tdd CoverageAUse when delegating test-first feature work to a subagent and you need EVIDENCE the new code is fully branch-covered — not just passing tests. Use when "good coverage" / "high coverage" matters, when weak or incomplete unit tests are a risk, or when spec-tdd's green-tests-but-no-coverage-evidence gap matters.ai-agentspythonrustVotes: 0GitHub stars: 3
Spec Tdd EscalateAUse when the user says "spec-tdd-escalate", or has a SETTLED requirement (plan/spec/design doc already locked — no grilling wanted) and wants the spec-tdd tier picked for them automatically. Triggers on requirement-already-decided, auto-pick tier, skip grilling, route to spec-tdd-lite / spec-tdd / spec-tdd-coverage / spec-tdd-adversarial.ai-agentsgoawsVotes: 0GitHub stars: 3
Spec Tdd LiteAUse when the user says "spec-tdd-lite", or wants test-first development WITHOUT delegating to a subagent — ONE small/medium non-critical unit (a single feature, bugfix, or refactor) in a session you'll clear after, where full spec-tdd is overkill but shallow same-context tests are still a risk. Triggers on in-session acceptance-test-first, "too small for spec-tdd", light tier, quick feature work with green-lie risk.ai-agentsrustgoVotes: 0GitHub stars: 3
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Spec TddAUse when the user says "spec-tdd" or wants acceptance-test-first development delegated to a subagent — one feature, or a multi-unit batch (bug list, task-split feature). Triggers on spec-as-test, test-first-by-orchestrator, preventing weak/green-lie AI tests, circular test+implementation reasoning.ai-agentsrustgoVotes: 0GitHub stars: 3
Spec 2nd OpinionAUse when the user says "spec-2nd-opinion", or a plan/design/ordering has been settled by grill or discussion (pre-implementation) and the user wants an independent audit before committing to it. Dispatches ONE read-only auditor subagent to verify the plan's claims against the codebase; the final plan is presented only when orchestrator and auditor agree.ai-agentsgogitVotes: 0GitHub stars: 3
Spec 3rd OpinionAUse when the user says "spec-3rd-opinion", or a settled plan needs maximum pre-commit scrutiny — same flow as spec-2nd-opinion plus a SECOND concurrent auditor on an adversarial brief (assume the plan flawed, hunt what the standard lens misses). The final plan is presented only when ALL THREE agree: orchestrator + standard auditor + adversarial auditor.ai-agentsgogitVotes: 0GitHub stars: 3
Spec Tdd SupervisorAUse when the user says "spec-tdd-supervisor", or wants ONE settled unit implemented with the WHOLE spec-tdd machinery delegated to a subagent while the final comprehensive review itself is a TOP-tier read-only audit dispatch — supervisor mode / full delegation of a single unit; every machinery dispatch (level-1 orchestrator, nested implementer, encoding audit, lite fresh review) is pinned to the MID tier as a recorded user opt-in, and the session's own tier is never a premise of the shape (an...ai-agentsgojavaVotes: 0GitHub stars: 3
Spec Tdd Task DagAUse when driving a multi-task feature phase whose WALL-CLOCK matters and the task plan is a dependency DAG — independent tasks run as parallel waves on a task-loop substrate (authoritative plan doc + per-task commits). Parallel multiplies quota pressure ×N (cap 3, user-adjustable); the serial sibling spec-tdd-task-loop is the 429-safe mode; a plain multi-unit bug batch is NOT this skill. Triggers on parallel tasks, dependency graph, task waves, wall-clock pressure, auto time-band switching, D...ai-agentsrustgoVotes: 0GitHub stars: 3
Spec Tdd Task LoopAUse when driving a whole MULTI-TASK feature phase — a task plan split into many self-contained task docs, run one task at a time with per-task commits, a plan-doc status board, and sessions that must survive the phase. The main session stays a LIGHTWEIGHT gate (compile + `git diff --stat` + JUnit-XML number recheck — never deep review, never running the tests itself); each task dispatches a level-1 sub-agent that runs the spec-tdd-escalate/tier machinery and itself dispatches the nested imple...ai-agentsgojavaVotes: 0GitHub stars: 3
Spec Tdd ManagerAUse when the user says "spec-tdd-manager", or wants ONE feature walked end-to-end through the family's whole running order as a single invocation — inventory-resume → grill the requirement if fuzzy (the grill's spec gate is Gate 1) → size route (one unit vs multi-task) → top-layer breakdown in the Phase-0 shape (authoritative plan trio + self-contained task docs, dag-ready columns) → independent plan audit via spec-2nd-opinion (auto-escalates to spec-3rd-opinion when any decision carries an I...ai-agentsgosecurityVotes: 0GitHub stars: 3
Spec Tdd QuickfixAUse when the user is LIVE-TESTING the product (UAT, live field testing) and streaming small fix requests — "quick fix", "small tweak", "change a word here" — one at a time or a handful, while they keep testing. Triggers on time-pressed small defects, cosmetic/string/config tweaks, wiring restorations too small for spec-tdd-lite's write-test-first cycle. NOT for anything needing an acceptance test.ai-agentsrustgoVotes: 0GitHub stars: 3