Menu
SkillsMP has collected 35 skills from tkersey/dotfiles. Open a skill to review its source and details.
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/tkersey/dotfiles.Showing 35 of 35 collected skills.
Choose or reconsider a semantic code boundary when ownership, representation, composition, or required laws are in question. Also use for distributed implementations of one law or invalidated decisions. Not routine work under an accepted architecture.
Explicit-only architectural review of a PR, subsystem, repository, or proposed design. Reconstruct obligations and interactions, challenge the decomposition, and use Universalist for bounded constructive alternatives. Return evidenced defects, risks,…
Explicit-only Elenctic adjudicates the authenticated gh user's prior review threads, then runs an exact-head PR review campaign for the current branch or an explicit PR, forking prepared file reviewers with at most 20 active at once, reconciling their…
Implement accepted goals, analyze counterexamples, or close out reviewed changes. Turn supported failure families into constructions that preserve required-valid behavior. Unqualified review or analysis is read-only.
Build AI-powered software with TypeSafe or review local text and Markdown with the typesafe CLI. Use when an app needs programmable common sense, typed judgments and probabilities from System One models such as Jev, brainstorming AI possibilities, or…
Use for deliberate Lean 4 work: proof repair, theorem development, verified programs, model/specification design, external-code models, state-machine or trace invariants, termination proofs, Std/mathlib theorem discovery, Lake/toolchain diagnosis, and…
Capture or recall evidence-backed execution learnings; evaluate capture at validation transitions, strategy pivots, footguns, retry loops, and material delivery or handoff. Also handle explicit learning-memory admission and supersession.
Implicitly invoke when implementation, debugging, review, or validation encounters a witnessed failed/no-effect attempt, benchmark or test regression, revert, repeated same-cluster retry, abandoned strategy, or asks what has already been tried. Project the…
Optimize software and agentic systems from measured bottlenecks, latency, throughput, memory, cost, reliability, or task-quality evidence; create, edit, and diagnose Codex skill packages, including activation and behavioral regressions. Use for performance…
Reduce unresolved user-owned judgments before planning or implementation. Research discoverable facts, resolve model-owned technical choices, order remaining decisions by dependency, ask only the material current frontier, and route questions that…
Operate the CAS Codex control-plane CLI: app-server, automations, account/goal facts, reviews, session inquiry, smoke/conformance checks, and instance fanout. Callers retain semantic authority.
Derive or refresh durable, evidence-backed repository doctrine, including correctness atlases, doctrine audits, task-context projections, and repository-skill recommendations. Not quick onboarding, ordinary implementation, or generic review.
Produce or revise a self-contained execution specification from an objective or candidate spec, including migration, proof, and rollback planning. Not implementation, debugging, generic review, explanation, or divergent options.
Classify and quotient current review findings, tests, incidents, and other witnessed falsifiers while preserving original provenance. Decide current applicability and whether each proposed law is entailed by the accepted Goal, a strengthening, preference, new…
Create, update, or promote a pull request for validated work without merging. Also observe or adopt an exact already-public subject when Actuating explicitly hands off that route.
Existing-code comprehension and local winnowing preflight. Use for simplify/refactor/clean up/untangle, nested branches, boolean soup, opaque names, mixed responsibilities, cross-file state, or review stalls. Factor the local whole, separate…
Read-only review lens for latent misuse hazards: APIs, defaults, flags, fallbacks, examples, config, state, cleanup, permissions, and workflows where the easy or obvious use is unsafe, surprising, irreversible, or likely to be copied wrong. Use for…
Generate a compact five-tier strategy portfolio when the next task is choosing among materially different paths. Implicitly invoke for explicit requests for options, alternatives, trade-offs, reframing, or help escaping repeated failure. A name-only or meta…
Create Deckset markdown presentations and speaker notes from conversation context. Use for explicit Deckset requests, markdown slide decks, or edits to an existing Deckset deck. PowerPoint and Google Slides artifacts belong to the presentations skill.
Define, compile, run, mutate, compare, and export total synthetic or partial session-derived agent environments. Use for `$emulator`, executable synthetic worlds, session-derived environment atlases and correction charts, fresh baseline/candidate harness…
Use for durable dependency-aware work tracking: create, close, reopen, link or unlink task prerequisites, and inspect ready work, exact blockers, task dependencies, or task history. Invoke explicitly with $ergon or implicitly when the request calls for…
Turn should-never-happen into cannot-happen with authority-gated invariant design: owned inductive invariants, counterexample traces, source-of-truth proof, transition preservation, exception authority, witness parity, enforcement boundary, and verification.…
Safely finish an explicitly selected GitHub PR: reconcile every unresolved review thread, bind each successor head as a fresh landing epoch, verify merge admission, merge the exact approved head or wait for queue/auto-merge completion, prove live MERGED…
Performance optimization with measurement-driven latency, throughput, memory/GC, tail, algorithmic, systems, and micro-architectural work; profile evidence, score-gated experiments, behavior proofs, golden oracles, and regression guards. Use for optimize,…
Transport source-approved Learnings, Negative Ledger, and Synesthesia admissions through validated adapters to the `memory-note` CLI; inspect, reconcile, and diagnose immutable-note, digest, and Phase 2 visibility gaps. Never decides source eligibility or…
Adversarially adjudicate a concrete claim when explicitly requested with `$prove-it` or equivalent claim stress-testing intent. Certainty words and ordinary implementation or review alone do not activate. Rounds 1-9 are independent lens packets produced…
Audit over-engineered codebases by factoring layers into live obligations, quotienting redundant distinctions, ablating unearned surface, and normalizing the survivors while preserving required behavior. Use when change latency or agent difficulty comes from…
Reconstruct provenance-preserving observations from Codex and OpenCode execution/session evidence with Seq 1.x. Use for explicit `$seq`, session/tool/message forensics, skill activation and outcome audits, decision provenance, `$tune` evidence, `$retrace`…
Reversible cross-modal diagnostic lens for software. Use when the user asks what code, architecture, behavior, logs, APIs, or alternatives feel, sound, look, or move like; for compare-by-feel analysis; when literal analysis leaves multiple plausible…
Use for Zig 0.16.0 implementation, review, migration, build/package, comptime/codegen, formatting/lint, testing/fuzzing, profiling, hazardous low-level code, FFI/layout, concurrency, cache operations, boundedness/assertion/control-flow review, and semantic…
Ensure Ledger 1.0.3 or newer within major version 1 is available and use its passive-definition runtime to validate, canonicalize, materialize, transact, replay, project, doctor, bind, rebind, and recover owner-defined artifacts and stores. Use for native…
Challenge a concrete incumbent when repeated repair or accretion, a live contradiction, or a suspect owner, model, representation, or solution class makes nonlocal reframing plausible. Also consider high-regret or difficult-to-reverse commitments,…
Raise solution ambition when candidate generation is timid or an adequate approach may leave substantial value unrealized. Use for `$glaze` or selective ambition escalation. Apply the canonical encouragement unchanged for one candidate-generation pass;…
Run one explicit first-principles pass verbatim, rebuilding the target axiomatically from its irreducible outcome, established facts, necessary constraints, invariants, and causal mechanisms rather than inherited assumptions, conventions, analogies, or the…
Run one explicit fresh-eyes review pass verbatim, rechecking the whole target for blunders, mistakes, errors, oversights, omissions, problems, misconceptions, bugs, and related defects. Use for `$fresh-eyes` or as the mandatory fresh-eyes auxiliary lane in…