Skill Claude CodeCodex
Surface and test hidden assumptions in plans, code, architecture, and strategy. Based on the CIA's Key Assumptions Check technique. Use when reviewing decisions, designs, or proposals to find what's being taken for granted. Triggers on "what am I missing", "assumption check", "what are we assuming", or when evaluating…
Skill Claude CodeCodex
Map the full solution space and evaluate approaches against evidence. Based on the CIA's Analysis of Competing Hypotheses (ACH). Use for DECISIONS - choosing between technologies, architectures, or strategies - or when the user needs counterpoints and alternatives. Triggers on "what are the alternatives", "compare…
Skill Claude CodeCodex
Deep technical investigation for complex systems, unfamiliar codebases, architecture, data flows, and dependencies - when the system works but is not understood. Use when the user asks for a deep dive, investigate deeply, map the system, understand how it works, break down complexity, or produce an evidence-backed…
Skill Claude CodeCodex
Monitor deployments with read-only evidence gathering, anomaly detection, cadence summaries, and local alerts. Use when watching a deploy, validating staging or production after release, comparing Datadog/database/runtime evidence, investigating new errors or skipped work, or linking post-deploy anomalies back to…
Skill Claude CodeCodex
Argue the opposing position: construct the strongest possible case for the alternative or against a pending decision. Use for make the case for NOT doing this, argue the other side, steelman the alternative, what would critics say. Produces an opposing-counsel brief, not a code review. For evidence-based critique of…
Skill Claude CodeCodex
Ground every challenge, claim, and alternative in real evidence. Search codebases for existing patterns, find real-world precedents and post-mortems, and validate claims against data. Use when making or evaluating technical claims, proposing alternatives, or challenging decisions. Triggers on "show me evidence"…
Skill Claude CodeCodex
Structured failure mode analysis for code, architecture, and systems. Uses FMEA (Failure Mode and Effects Analysis), dependency chain analysis, and real-world failure pattern matching. Use when evaluating system reliability, reviewing architecture, or assessing risk. Triggers on "how could this fail", "what breaks"…
Skill Claude CodeCodex
Empirically test whether a skill actually improves model output — before trusting it. Runs a controlled experiment: planted-flaw fixture, no-skill control arm, skill arm(s), optional cross-model arms via installed CLIs, blind judging with shuffled labels, and a pressure test for verdict stability. Produces…
Skill Claude CodeCodex
Adversarial collaborator who pushes back like a senior engineer - the default adversarial reviewer. Surfaces hidden assumptions, grounds every challenge in evidence, presents real counterpoints with proven alternatives, drives toward synthesis, and records settled claims as verdict nodes in docs/verdicts/ so an…
Skill Claude CodeCodex
Create a compact handoff document for another agent session to continue the work. Use when the user asks for a handoff, next-agent context, continuation note, session summary, resume brief, or wants another agent to pick up without reconstructing the thread.
Skill Claude CodeCodex
Validate production-incident artifacts -- investigation handovers, fix PRs, and postmortems -- against the Production Issue Resolution Standard. Runs a gate matrix with live evidence verification, interrogates the author to close gaps, and issues a closure verdict. Use when writing or reviewing an incident handover, a…
Skill Claude CodeCodex
Adversarial QA — design and run test campaigns that find defects a happy-path pass misses, with evidence-backed verdicts and re-runnable cases. Use when asked to QA a feature, plan or run a test campaign, prove a change works, verify on staging, test a flow in a browser, capture QA evidence, or write a verification…
Skill Claude CodeCodex
Run premortems before risky work and postmortems after incidents or failures. Use when the user asks for premortem, postmortem, incident review, retrospective, launch risk, "how will this fail", or "what killed this". For the causal-chain analysis itself (evidence-backed five whys from symptom to systemic cause) use…
Skill Claude CodeCodex
Red-team/blue-team review for designs, plans, code, security, reliability, and launch readiness. Use when the user asks for red team, blue team, adversarial review, attack paths, defense plan, risk review, or catching issues before shipping.
Skill Claude CodeCodex
Causal-chain analysis after something already happened: trace a symptom to its systemic cause using evidence-backed Five Whys and first-principles constraint challenges. Use for root cause, why did this really happen, underlying or systemic cause, and incident causal analysis once the immediate failure is understood.…
Skill Claude CodeCodex
Safe system operations with risk classification, dry-run previews, confirmation gates, and audit trails. Use when performing mutating, destructive, or remote operations - infrastructure ops (Docker, K8s, cloud), dev workflow ops (git push/merge, CI/CD, PRs), data/service ops (databases, APIs, caches), or risky local…
Skill Claude CodeCodex
Generate or review technical specs and Architecture Decision Records. Use when the user asks for specs, ADRs, RFCs, design docs, decision records, technical requirements, non-goals, alternatives, rollout, or rollback documents.
Skill Claude CodeCodex
Toolshed — durable, model-agnostic working state for ONE coding task (feature, fix, investigation) as docs/work/SLUG/ under docs/, DELETED at close. NOT the Workbench product/MCP (Slack highlights app). Seeds STATE + decisions/questions/evidence with grades and reproduction commands. Use for "start a toolshed", "seed…
Skill Claude CodeCodex
Structured troubleshooting and bug investigation workflow for something failing NOW. Use when debugging failing tests, production issues, regressions, flaky behavior, errors, logs, broken builds, performance problems, or unclear symptoms. For tracing why a past failure really happened use root-cause; for understanding…