リポジトリの README を読み込んでいます…
収集済み skill 35 件中 35 件を表示しています。
Operate Ledger for owner-defined artifact validation, materialization, durable custody, migration, and recovery. Use for runtime bootstrap, passive definitions, or repository/worktree-family storage; not merely because work creates history or a receipt.
原文の言語: 英語
Recall prior attempts or handle witnessed failed/no-effect routes, regressions, reverts, abandoned strategies, repeated retries, and negative-evidence lifecycle or memory admission. Not ordinary successful closeout.
原文の言語: 英語
Adversarially adjudicate a concrete claim for explicit `$prove-it` or equivalent claim stress-testing intent. Certainty words, quoted instructions, and ordinary rigor, implementation, or review alone do not activate.
原文の言語: 英語
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…
原文の言語: 英語
Implement, debug, review, migrate, and optimize Zig code and build systems. Use when the task requires Zig-specific language or toolchain expertise.
原文の言語: 英語
Explicit-only PR review: adjudicate your prior threads, review unchecked files and their causal consequences, and return evidence-backed findings with an interactive local report. Request 'for resolution' for groups, or 'for construction' to adjudicate PR…
原文の言語: 英語
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.
原文の言語: 英語
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…
原文の言語: 英語
Translate software and architecture into sensory models and back into precise engineering meaning. Use for explicit sensory explanations or renditions, compare-by-feel requests, concrete representational ambiguity, and reuse or revision of established sensory…
原文の言語: 英語
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.
原文の言語: 英語
Raise ambition and resourcefulness when current work settles for adequacy, accepts an assumed limit too readily, or leaves important possibilities unexplored. Use for `$glaze` or task-relevant ambition escalation. Apply the canonical encouragement unchanged…
原文の言語: 英語
Reconsider task framing when assumptions, repeated repair or accretion, contradictions, high-regret commitments, or an apparently limited solution space may hide a better approach. Use for `$metanoetic` or task-relevant reframing, including removing burdens…
原文の言語: 英語
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.
原文の言語: 英語
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.
原文の言語: 英語
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 findings and, for PRs,…
原文の言語: 英語
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.
原文の言語: 英語
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…
原文の言語: 英語
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…
原文の言語: 英語
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…
原文の言語: 英語
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.
原文の言語: 英語
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.
原文の言語: 英語
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…
原文の言語: 英語
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…
原文の言語: 英語
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…
原文の言語: 英語
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…
原文の言語: 英語
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.
原文の言語: 英語
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…
原文の言語: 英語
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 $ergon or implicitly when the request calls for…
原文の言語: 英語
Turn should-never-happen into cannot-happen with authority-gated invariant design: owned inductive invariants, counterexample traces, source-of-truth proof, transition preservation, exception authority, witness parity, enforcement boundary, and verification.…
原文の言語: 英語
Safely finish an explicitly selected GitHub PR: reconcile every unresolved review thread, bind each successor head as a fresh landing epoch, verify merge admission, merge the exact approved head or wait for queue/auto-merge completion, prove live MERGED…
原文の言語: 英語
Performance optimization with measurement-driven latency, throughput, memory/GC, tail, algorithmic, systems, and micro-architectural work; profile evidence, score-gated experiments, behavior proofs, golden oracles, and regression guards. Use for optimize,…
原文の言語: 英語
Audit over-engineered codebases by factoring layers into live obligations, quotienting redundant distinctions, ablating unearned surface, and normalizing the survivors while preserving required behavior. Use when change latency or agent difficulty comes from…
原文の言語: 英語
Reconstruct provenance-preserving observations from Codex and OpenCode execution/session evidence with Seq 1.x. Use for explicit `$seq`, session/tool/message forensics, skill activation and outcome audits, decision provenance, `$tune` evidence, `$retrace`…
原文の言語: 英語
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…
原文の言語: 英語
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…
原文の言語: 英語
このプロンプトをコピーして、使用中の AI アシスタントに送ってください。
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/tkersey/dotfiles.README を読み込めませんでした。リポジトリの Skill 一覧は下で引き続き確認できます。