mike-skills

Use when the user wants Claude, Codex, agy, and the Cursor models Composer 2.5 and Grok Build to iterate together until they converge on a mutually-agreed result — or hit a deadlock the user must arbitrate — and for fresh-eyes adversarial review of drafted artifacts. Five modes — plan, implement, verify, review, and audit (the folded-in adversarial review). Triggers — "converge", "have claude and codex work it out", "iterate until you agree", "three-AI consensus", "multi-AI consensus", "deadlock me a decision", "adversarial review this", "audit my drafts", "fresh eyes on this", "review for fabrications".

Use when starting any substantial feature — the before/during/after development lifecycle: interview rounds, parallel blind-spot/references/reality-probe passes, a knowns matrix folded into the plan, an implementation-notes log during the build, and a compounding step after (explainer, quiz, memory/skill extraction). Triggers — "feature passes", "run the pre-build passes", "blind spot pass", "knowns matrix", "interview me about this feature", "compound the learnings".

Use before baking an external config value — a model id, endpoint, ARN, bucket, region, credential, API version, image tag — into code or a deploy. Invoke the real dependency ONCE against the target account/environment and read the response, so a dead/renamed/deprecated/permission-blocked value is caught at the source instead of failing in production. The config equivalent of "verify against reality, not the doc." Triggers — "probe before wire", "smoke the dependency first", "is this model/endpoint/ARN actually live", "verify the config before deploy", "does this id still work", "check it against the real account".

Use when an agent, workflow, or fan-out died mid-work — API connection drops, session/spend limits, forced structured-output timeouts — and work must be recovered without loss. Triggers — "resume the run", "the agent died", "hit the session limit", "recover the workflow", "connection closed mid-response".

Use when you need to maximally verify a piece of code — especially AI-generated code — by stacking every independent check it admits (differential/property/metamorphic/fuzz/concurrency/static/cross-model), anchored on the strongest available oracle, and breaking the correlated-failure trap (one agent wrote both code and tests). Triggers — "how do I maximally verify this", "make this bulletproof", "how should I test this", "make this safe to optimize/refactor with AI", "what oracle should I use", "I don't trust the agent's tests", "maximize verification", "is my test suite actually verifying anything".

Use when a deployed/wired integration is FAILING (silently or opaquely) and you're tempted to try a fix. The failure lives at one of several layers — your wiring, your env, your IAM, an org policy/SCP, an account-level enablement/subscription, or the provider's response format — and each layer has a DIFFERENT OWNER. Ladder down them, verify what you own is actually applied, and get to the ONE authoritative signal (the real log line, an elevated-creds probe, latency-as-discriminator) before attributing blame or attempting a fix. Triggers — "why is this silently failing", "it deployed but doesn't work", "ladder the failure", "localize before fixing", "read the real error", "is it my code or their config", "diagnose the integration", "AccessDenied but the IAM looks right".

Use when shipping a change through a gated pipeline (local verify → commit → push → CI → adversarial audit → auto-merge) and you must not let a check be claimed without being read. Turns the ship sequence into a hard READ-gate state machine — every gate's actual exit code / number / verdict must be read before the next step, and "run the audit" can never be co-scheduled with "arm the merge." Triggers — "ship this", "verified ship", "open the PR and merge", "gate this change", "ship with the discipline", "don't claim a number you didn't read", "read the audit before arming".

Use when you want Claude and Codex to work an artifact through an explicit thesis → antithesis → synthesis loop until a transcendent position emerges (or the dialectic stalls). Works in four modes — plan, implement, verify, review — same artifact types as /converge but with a structurally different rhythm. Triggers — "hegelian dialectic", "thesis antithesis synthesis", "dialectic this <plan|code|tests|PR>", "synthesize claude and codex on this", "transcend the disagreement".

Use when designing a skill, agent, or system and you have to decide whether a capability belongs in code (a script/helper) or in the prompt (the SKILL.md / agent instructions / model reasoning). Applies the three-condition Primitive Test — Atomicity, Bitter Lesson, ZFC — and produces a per-capability verdict. Triggers — "primitive test", "should this be in code or in the prompt", "encode or leave in prompt", "what should this script do vs the SKILL.md", "audit my skill for over-prompting / under-encoding", "is this judgment or transport".

Use whenever the user references a GitHub repo by URL or owner/repo and you'd otherwise make repeated `gh api repos/.../contents` calls. Clones the repo into `~/.cache/claude-repo-cache/<owner>/<repo>` (shallow) and returns a local path so subsequent exploration uses Read/Grep/find on local files. Triggers — any github.com URL the user wants explored, "look at <owner>/<repo>", "what's in the X repo", "compare to <gh-url>", "find Y in <repo>".

Use when the user asks to install a skill or skill framework from a GitHub URL ("install https://github.com/...", "add the X framework", "pull in superpowers/gsd/bmad/speckit/openspec", "set up this framework").

Use when the user wants to scaffold a new Claude Code skill ("new skill", "scaffold a skill", "create a skill for X", "start a skill called Y", "bootstrap a skill").

Use when the user wants to analyze their Claude Code chat history for recurring patterns, forgotten threads, or skill-abstraction candidates ("review my chats", "abstract skills from chat logs", "what am I repeating", "find patterns in my Claude sessions", "retro my chat history").

Use when the user wants an inventory of installed Claude Code skills, to find duplicates, orphan symlinks, trigger overlaps, or unknown-origin skills ("audit my skills", "what skills do I have", "skill inventory", "find orphan/duplicate skills", "what framework does X come from").

Use when the user wants to remove a Claude Code skill or skill framework ("uninstall X", "remove the X skill", "get rid of superpowers/gsd/bmad", "clean up broken skill", "undo last install").