m0n0x41d
- 41 skills
- 0 followers
- 17 hours ago last updated
- ▌ H Note 2 · m0n0x41dPersist an explicitly requested non-binding fact, observation, caveat, or small rationale in Haft project memory. Do not auto-persist ordinary reasoning.
- ▌ H Spec 2 · m0n0x41dManage Haft's typed spec lifecycle, source-currentness, carrier edits, and semantic fanout repair. Treat markdown as a carrier and kernel lifecycle plus explicit human gates as authority.
- ▌ H Frame 2 · m0n0x41dShape an under-articulated engineering problem without assuming a solution or forcing a project phase. Default to a conversational frame; create a ProblemCard only on explicit save intent or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs a durable accepted problem statement.
- ▌ H Decide 2 · m0n0x41dRoute one direct, unambiguous operator request for a bounded binding choice. A manual h-decide invocation is a compatible shortcut, not an authorization receipt.
- ▌ H Reason 2 · m0n0x41dSource-first umbrella for FPF-aware reasoning in a Haft project. Use for ambiguous engineering, management, architecture, specification, or project questions when no narrower Haft capability is already current. Ordinary reasoning stays conversational; persistence is conditional and binding actions remain manual.
- ▌ H Status 2 · m0n0x41dRead-only Haft project cockpit for active problems, decisions, notes, evidence freshness, drift, commissions, spec lifecycle, module coverage, and bounded exact file-link gaps from a current code index. Use for project status, session resumption, what is decision-linked, what is uncovered, or what needs attention.
- ▌ H Verify 2 · m0n0x41dVerify that a recorded DecisionRecord or claim still holds by comparing its baseline and predictions with current code, tests, measurements, or incidents. Keep design-time claims distinct from runtime evidence.
- ▌ H Compare 2 · m0n0x41dCompare two or more existing candidates under an explicit characteristic space, parity basis, and predeclared selection policy. Return trade-offs and a non-dominated set; persistence is conditional and a binding choice requires a direct unambiguous operator request.
- ▌ H Explore 2 · m0n0x41dGenerate 3-5 genuinely distinct candidate approaches for a current question, with the weakest link of each visible. May work from an inline question or a durable ProblemCard; persistence is conditional.
- ▌ H Onboard 2 · m0n0x41dBootstrap Haft through the readable task-level onboarding surface, prepare a non-binding project-profile review when needed, and orient only applicable typed spec carriers. Project memory is ready immediately after haft init; profile apply and lifecycle gates remain human.
- ▌ H Diagnose 2 · m0n0x41dDiagnose a concrete failure with rival-hypothesis testing. Stabilize the symptom, generate distinct explanations, test discriminating observations read-only in parallel, and rank by evidence while retaining losing rivals.
- ▌ H Commission 2 · m0n0x41dManual-only skill that creates bounded execution authority from an explicit operator grant. Never auto-trigger or infer approval from prompt text or tool schemas.
- ▌ Fpf Core · m0n0x41d bundleFPF session bootstrap. MUST be auto-invoked at the start of any non-trivial task. Writes sentinel, triggers worklog, activates FPF rules. After this, MUST invoke /fpf-worklog.
- ▌ Fpf Sota · m0n0x41dSurvey existing approaches and produce a strategy card (method family bet). Think through what exists before choosing where to search. MUST invoke for architectural decisions before variant generation.
- ▌ Fpf Active · m0n0x41dFPF global toggle and status. Check whether FPF is enabled or disabled globally. Enable or disable FPF across all Claude Code sessions. Triggers on "fpf status", "fpf on", "fpf off", "enable fpf", "disable fpf", "is fpf active", "/fpf-active".
- ▌ Fpf Parity · m0n0x41dEnsure fair comparison conditions before evaluating variants. Produces PAR-* parity plan. SHOULD invoke before /fpf-selection when comparing ≥2 variants with measurable indicators.
- ▌ Fpf Review · m0n0x41dEnd-of-session quality gate. Verify the creative and assurance pipeline — not just artifacts. MUST invoke before ending any non-trivial session.
- ▌ Fpf Status · m0n0x41dShow current FPF session state — tier, edit count, artifacts, pending gates. Read-only diagnostic.
- ▌ Fpf Worklog · m0n0x41dCreate or append session work log. MUST be invoked at session start (Gate 0 chain) before any substantive work.
- ▌ Fpf Evidence · m0n0x41dTest a claim against reality by running the evidence procedure. Produce EVID-* record with commands, outputs, and interpretation. MUST invoke before claiming "works" or "verified".
- ▌ Fpf Glossary · m0n0x41dMaintain project glossary and cross-context bridge cards. MUST invoke for naming inconsistency, overloaded terms, or new terminology.
- ▌ Fpf Variants · m0n0x41dExplore the solution space by generating ≥3 genuinely distinct variants within the chosen method family. Think through alternatives using the portfolio template as scaffolding.
- ▌ Fpf Selection · m0n0x41dPerform qualitative Pareto analysis on variants, apply explicit selection policy, record stepping-stone bets. Think through the trade-offs using the selection template.
- ▌ Fpf Strategize · m0n0x41dBet on a method family — choose WHICH CLASS of approach to explore, not which specific solution. First-class creative act. MUST invoke for T4 architectural work before variant generation.
- ▌ Fpf Characterize · m0n0x41dDefine the characteristic space — what could matter, how to measure it, how to compare. Think through what "better" means before generating or comparing anything.
- ▌ Fpf Decision Record · m0n0x41dRecord non-trivial or irreversible decisions with options, rationale, risks, and rollback plan.
- ▌ Fpf Problem Framing · m0n0x41dThink through a problem by working through the problem card template. Design what problem you're solving and how you'll know it's solved. MUST invoke for debugging, new features, design decisions, or any substantive work.
- ▌ Fpf Problem Portfolio · m0n0x41dManage problems as a portfolio with explicit selection rules, goldilocks assessment, and diversification. Think through what to solve next, not just what's urgent.
- ▌ Fpf · m0n0x41dApply First Principles Framework (FPF) reasoning — principled problem design, variant generation, and evidence-based decisions.
- ▌ H Note · m0n0x41dPersist a fact, observation, caveat, or small non-binding rationale in Haft project memory when the operator explicitly asks or current Work supplies a concrete operator-named or agent-inferred receiving use that needs a lightweight addressable fact. Use for "remember this", "запиши", or "note for later". Do not auto-persist ordinary reasoning. A note is not a choice, ProblemCard, evidence verdict, approval, or WorkPlan.
- ▌ H Spec · m0n0x41dManage Haft's typed specification lifecycle and source-currentness repair: inspect current SpecSections, draft or clarify carriers, classify FPF semantic fanout, record operator-requested spec changes, and cross explicit approve/rebaseline/reopen gates only with human authorization. Use for "spec status", "update specs", "запиши в спеки", stale spec sections, newer FPF source revisions, or semantic changes that must be repaired across several spec carriers. Treat markdown as a carrier and the kernel projection as the lifecycle contract. Use h-status for read-only module/file coverage and h-onboard for first bootstrap.
- ▌ H Frame · m0n0x41dShape an engineering problem without assuming a solution or forcing a project phase. Use when a redesign, refactor, or proposal arrives before the affected object, observed signal, constraints, unresolved relation, and acceptance basis are clear. Default to a conversational frame; record a ProblemCard only on explicit save intent or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs a durable accepted problem statement. Prefer h-diagnose for a concrete failure with unclear cause.
- ▌ H Decide · m0n0x41dRoutes one direct, unambiguous operator request to bind a bounded choice as a DecisionRecord. Use when the operator asks to decide, bind, or supersede a choice; h-frame, h-explore, and h-compare are independent capabilities, not mandatory phases.
- ▌ H Reason · m0n0x41dSource-first umbrella for FPF-aware reasoning in a Haft project. Use when the operator asks to think through an ambiguous engineering, management, architecture, specification, or project question without naming a narrower Haft capability. Recover the current object and question, query the bundled FPF source, inspect the governing pattern body, and choose only the capability that is current. Ordinary reasoning stays conversational; proactively persist the minimum needed memory when current Work supplies a concrete durable receiving use. h-decide may route a direct operator request; h-commission remains manual-only.
- ▌ H Status · m0n0x41dRead-only Haft project cockpit for active problems, decisions, notes, evidence freshness, drift, commissions, spec lifecycle, module decision coverage, and bounded exact file-link gaps from a current code index. Use for project status, session resumption, "what is decision-linked", "what is uncovered", or "what needs attention". This skill reports current graph state and drill-downs; it does not mutate artifacts, infer a project phase, or prescribe a universal next step.
- ▌ H Verify · m0n0x41dVerifies that a recorded DecisionRecord still holds — baseline-vs-measure evidence loop with drift detection per FPF Evidence Decay. Make sure to use this skill whenever the user asks "did dec-X work", "is decision Y still valid", "did the prediction come true", "check if the migration held", "is X stale", "measure that decision against reality", "did we actually fix Z", "is our caching decision still right" — or whenever a shipped decision needs a post-implementation reality-check before further work relies on it. Also use when /h-status surfaces a refresh-due decision. NOT for ad-hoc sanity checks (just run the tests directly). NOT for re-framing the underlying problem (use h-frame).
- ▌ H Compare · m0n0x41dCompare two or more existing candidates under an explicit characteristic space, parity basis, and predeclared selection policy. Return constraints, trade-offs, and a non-dominated set rather than hiding the choice in one score. This skill is independent of h-frame and h-explore. Default to a conversational comparison; persist comparison artifacts only on explicit save intent or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs replay. A binding choice requires a direct unambiguous operator request routed through h-decide.
- ▌ H Explore · m0n0x41dGenerate 3-5 genuinely distinct candidate approaches for a current question, with the weakest link of each kept visible. Use when alternatives are needed or one favored approach is prematurely closing the search. This skill is independent: it may work from an inline question, cue, accepted problem, or other current basis. Default to conversational candidates; persist a SolutionPortfolio only on explicit save intent or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs replay.
- ▌ H Onboard · m0n0x41dBootstrap Haft through one readable onboarding surface, prepare an initial profile review or one bounded existing-scope relation change, and orient applicable specification carriers. Use for first-time setup, incomplete setup, or profile-underdetermined spec recovery. Project memory is ready immediately after haft init. Status and repository detection are read-only; all reviewed profile effects and specification lifecycle gates remain explicit human acts.
- ▌ H Diagnose · m0n0x41dDiagnose a concrete failure with parallel rival-hypothesis testing. Use when symptoms are observable but cause is unclear. Stabilize the signal, generate distinct explanations, test them read-only in parallel, and rank by evidence while keeping losing rivals visible. This skill is independent and ordinarily non-persistent; save a diagnosis frame or hypothesis portfolio only on explicit request or when current Work supplies a concrete operator-named or agent-inferred receiving use that needs replay.
- ▌ H Commission · m0n0x41dCreates a WorkCommission — bounded execution authority — from an active DecisionRecord. MANUAL ONLY: operator must explicitly type /h-commission. Never auto-invoked: commissions are execution-authority grants under Transformer Mandate. Runs freshness check, scope check, derives an ImplementationPlan, snapshots the autonomy envelope, then STOPS before execution. NOT for the decision itself (use /h-decide first). NOT for running tests or one-off tasks (the operator's coding agent handles those directly).