{ "$comment": "Provider-neutral, cost-aware model routing for skilldrop skills. Skills declare an ABSTRACT tier (light/standard/heavy) describing how much reasoning the task needs. The `providers` map resolves that tier to a concrete model for whatever tool you use (Claude Code, Cursor, Codex, Kiro, ...). Set `active_provider` to your tool. Tier is decided ONCE per skill (the decision is stable), not re-derived per call — that keeps routing free. Runtime heuristics in `escalation_rules` handle the cases that actually vary.", "version": "0.2.0", "active_provider": "claude-code", "tiers": { "light": { "use_for": "Mechanical mapping, extraction, and lookup against a fixed rubric. Deterministic enough that a small/cheap model matches a large one.", "relative_cost": 1 }, "standard": { "use_for": "Most generation. Synthesizing a structured artifact from a brief, where quality matters but the reasoning is not adversarial. The default tier.", "relative_cost": 4 }, "heavy": { "use_for": "Adversarial reasoning and weighted judgment, where a cheaper model demonstrably misses edge cases, under-calls severity, or mis-weights tradeoffs. Spend here only when the hard thinking IS the value.", "relative_cost": 20 } }, "providers": { "claude-code": { "label": "Claude Code (Anthropic)", "models": { "light": "claude-haiku-4-5-20251001", "standard": "claude-sonnet-5", "heavy": "claude-opus-5" }, "select_via": "`/model ` in the session, or hand the skill to the model-router agent for automatic dispatch.", "automation": ".claude/agents/model-router.md" }, "cursor": { "label": "Cursor", "models": { "light": "", "standard": "", "heavy": "" }, "select_via": "Pick the model in the chat/composer model dropdown before invoking the skill. Cursor rules cannot switch models programmatically — this is a manual lookup.", "automation": null, "note": "Cursor exposes whatever models your plan enables (Claude, GPT, Gemini). Fill in the three you actually use." }, "openai-codex": { "label": "OpenAI Codex CLI", "models": { "light": "", "standard": "", "heavy": "" }, "select_via": "Set the model via the Codex `--model` flag or its config before running the skill.", "automation": null, "note": "Fill in with the model identifiers your Codex install accepts. Model names change — verify against `codex --help` / your config." }, "kiro": { "label": "Kiro", "models": { "light": "", "standard": "", "heavy": "" }, "select_via": "Select the model in Kiro's model picker, or pin it in the custom-agent / steering definition that loads the skill.", "automation": null }, "generic": { "label": "Any other tool", "models": { "light": "", "standard": "", "heavy": "" }, "select_via": "However your tool selects a model. The tier tells you which of your three to pick.", "automation": null } }, "escalation_rules": [ { "id": "large-input", "rule": "Escalate one tier (light→standard, standard→heavy) when the input the skill must reason over exceeds ~30 pages / ~20k words / ~15 source files. Large context degrades small models faster than large ones.", "type": "heuristic_no_llm" }, { "id": "reasoning-floor", "rule": "Never downgrade a skill whose tier is 'heavy'. These are the reasoning skills; downgrading defeats their purpose. The router may upgrade but never demote below the skill's declared tier.", "type": "hard_constraint" }, { "id": "ambiguous-input", "rule": "Escalate one tier when the input is contradictory, underspecified, or the user explicitly asks for the most rigorous output ('be thorough', 'this is going to the board'). Do NOT escalate just because the topic sounds important.", "type": "heuristic_no_llm" }, { "id": "downgrade-trivial", "rule": "Downgrade one tier (never below 'light', never below the skill's declared floor) when the input is tiny and templated — e.g. a one-paragraph brief into adr-generator, a 3-line note into decision-log.", "type": "heuristic_no_llm" }, { "id": "user-override", "rule": "An explicit user model choice always wins. The router reports what it would have picked, then honors the override.", "type": "hard_constraint" } ], "skills": { "audience-profile": { "tier": "light", "rationale": "Maps a fixed set of audience archetypes to structural rules. Lookup against a rubric, not synthesis." }, "decision-log": { "tier": "light", "rationale": "Extracts decisions/owners/dates from notes. Pattern extraction; escalate on long transcripts via large-input rule." }, "sonar-onboard": { "tier": "light", "rationale": "Scaffolds config from detected language + a template. Deterministic fill-in; little judgment." }, "adr-generator": { "tier": "standard", "rationale": "Structures a decision into MADR/Nygard. Some judgment on title/consequences; not adversarial." }, "architecture-diagrams": { "tier": "standard", "rationale": "Translates prose to diagram syntax. Correctness matters; reasoning is bounded." }, "brief-intake": { "tier": "standard", "rationale": "Extraction + tagging [explicit]/[implied]/[inferred]. The tagging needs care — above light, below heavy." }, "deck-builder": { "tier": "standard", "rationale": "Generates pptx content + runs a script. Content shaping, not hard reasoning." }, "design-doc": { "tier": "standard", "rationale": "Synthesizes a design doc from a brief. Escalate to heavy via large-input or ambiguous-input when alternatives are genuinely contested." }, "exec-summary": { "tier": "standard", "rationale": "Compression to one page. Needs to keep the right signal; escalate on very long source docs." }, "figma-diagrams": { "tier": "standard", "rationale": "API calls + spec generation. Bounded transformation." }, "guide-builder": { "tier": "standard", "rationale": "Shapes notes into a styled guide. Generation, not adversarial review." }, "reverse-architecture": { "tier": "standard", "rationale": "Extracts architecture from code/IaC. Escalate to heavy on large codebases where cross-file inference is heavy." }, "runbook-generator": { "tier": "standard", "rationale": "Operational doc from service facts. Bounded synthesis." }, "slide-outliner": { "tier": "standard", "rationale": "Outlines a deck to a time budget. Structuring, not deep reasoning." }, "sonar-review": { "tier": "standard", "rationale": "Formats Sonar API findings into a report. The hard analysis is Sonar's; this is synthesis. Escalate on very large diffs." }, "ai-usage-report": { "tier": "standard", "rationale": "Tabulates telemetry into a report. Mostly mechanical, but the 'AI theater' effectiveness call needs judgment." }, "ai-readiness-assessment": { "tier": "standard", "rationale": "Scores six fixed dimensions against a rubric and ranks gaps by blocking order. Bounded structured judgment, not adversarial reasoning; escalate via ambiguous-input when the evidence is thin or contested." }, "agent-adoption-stage": { "tier": "standard", "rationale": "Places a team on a fixed 5-stage ladder from observables and routes one unlock. Bounded diagnosis against a rubric; escalate via ambiguous-input when the observables are contradictory or the distribution is heavily skewed." }, "ai-use-case-triage": { "tier": "standard", "rationale": "Scores candidates on weighted axes and forces a rejection list. Structured comparison with stated weights; escalate via ambiguous-input when candidates are numerous or the value data is contested." }, "ai-adoption-rollout": { "tier": "standard", "rationale": "Generates a phased people-rollout with gates and enablement from a stated tool and population. Structured planning against a fixed shape; escalate via ambiguous-input for large or politically contested rollouts." }, "ai-usage-policy": { "tier": "standard", "rationale": "Drafts a policy document against a fixed structure (tiers, behaviours, review matrix, exception route). Bounded generation; escalate via ambiguous-input where a regulatory regime is named or contested." }, "feature-implement-loop": { "tier": "standard", "rationale": "Code + test generation against acceptance criteria. The adversarial pass delegates to devils-advocate (heavy) where available; the loop itself is generation." }, "pre-merge-review": { "tier": "standard", "rationale": "Orchestration: runs a deterministic gate script, dispatches the (heavy) reviewer subagents, and renders a rule-based go/no-go. The adversarial reasoning is delegated to the panel, so the skill itself is coordination." }, "user-story-splitter": { "tier": "standard", "rationale": "Decomposes an epic into INVEST slices with testable ACs. Structured synthesis; escalation rules cover large or contradictory PRDs." }, "test-plan-generator": { "tier": "standard", "rationale": "Synthesizes a structured plan from a change description. Risk ranking needs judgment but is bounded; escalate via ambiguous-input on contested or high-stakes releases." }, "release-notes": { "tier": "standard", "rationale": "Classifies commits and rewrites them for a reader. The audience translation needs judgment; escalate via large-input on very long ranges." }, "postmortem-generator": { "tier": "standard", "rationale": "Synthesizes a structured doc from incident notes. Contributing-factor chains need judgment but are bounded; escalate via large-input on huge scrollbacks." }, "migration-plan": { "tier": "standard", "rationale": "Phased plan synthesis with a strong template. Ordering judgment is bounded by the expand/migrate/contract pattern; escalate via ambiguous-input on contested, high-stakes cutovers." }, "api-contract-draft": { "tier": "standard", "rationale": "Schema synthesis against fixed conventions. The resource modeling needs judgment; the conventions bound it. Escalate via ambiguous-input on contested multi-team contracts." }, "bug-triage": { "tier": "standard", "rationale": "Extraction plus judgment calls (severity vs priority, hypothesis ranking) — same shape as brief-intake: above light, below heavy." }, "prd-draft": { "tier": "standard", "rationale": "Synthesizes a structured requirements doc from a brief. The solution-language discipline needs care; bounded by the template. Escalate via ambiguous-input on contested scope." }, "nfr-spec": { "tier": "standard", "rationale": "Rubric-driven sweep with archetype defaults; the judgment is calibrating targets to business reality. Bounded by the catalog; escalate via ambiguous-input on contested SLOs." }, "success-metrics": { "tier": "standard", "rationale": "Structured measurement design; the primary-metric and counter-metric choices need judgment but the template bounds it. Escalate via ambiguous-input when the goal itself is contested." }, "requirements-interview": { "tier": "standard", "rationale": "Question banks are rubric-shaped, but ranking by design impact and deriving falsification conditions for the specific feature is synthesis — above light." }, "business-case": { "tier": "heavy", "rationale": "Weighted multi-option judgment with a committal recommendation — same failure mode as tech-comparison-matrix: cheaper models mis-weight costs, inflate benefits, and miss the flip-assumption. Never downgrade." }, "incident-comms": { "tier": "standard", "rationale": "Audience-segmented message generation under a strict don't-retract discipline. Same shape as exec-summary/audience-profile — translation and altitude, not adversarial reasoning." }, "data-contract": { "tier": "standard", "rationale": "Schema + SLA synthesis against fixed quality dimensions and an evolution matrix. Semantics capture needs care; bounded by the catalog. Escalate via large-input on wide schemas." }, "llm-eval-harness": { "tier": "standard", "rationale": "Methodology synthesis against a fixed decision tree and pitfall catalog. Grading-method and metric choices need judgment but are bounded; escalate via ambiguous-input on novel task types." }, "capacity-cost-model": { "tier": "standard", "rationale": "Quantitative projection from a demand model against a fixed cost catalog. Headroom and scaling-cliff judgment is bounded by the reference; escalate via ambiguous-input on novel architectures." }, "accessibility-audit": { "tier": "heavy", "rationale": "Adversarial review against WCAG success criteria — cheaper models fault alt-text presence over quality, under-call severity, miss focus-order/name-role-value issues, and claim AT passes from screenshots. Never downgrade." }, "db-schema-design": { "tier": "standard", "rationale": "Design synthesis from access patterns against a fixed paradigm/indexing/anti-pattern reference. Paradigm and denormalization judgment is bounded; escalate via ambiguous-input on contested scale/consistency tradeoffs." }, "observability-plan": { "tier": "standard", "rationale": "Methodology synthesis against fixed SRE practices (golden signals, burn-rate alerting, pillar split). SLO calibration needs judgment but is bounded; escalate via ambiguous-input on contested reliability targets." }, "council-review": { "tier": "heavy", "rationale": "Multi-perspective deliberation + weighted reconciliation across distinct expert seats. Cheaper models collapse the seats into one voice and either manufacture or miss the real cruxes. Never downgrade." }, "devils-advocate": { "tier": "heavy", "rationale": "Adversarial code review across four lenses. Cheaper models miss edge cases and under-call severity — the whole value is the hard thinking. Never downgrade." }, "output-hygiene": { "tier": "standard", "rationale": "The mechanical pass is a deterministic script; the model does bounded rewriting of flagged prose against a fixed tell list, not adversarial review." }, "doc-critique": { "tier": "heavy", "rationale": "Adversarial doc review against rubrics. Same as devils-advocate: the value is catching what a fast pass misses. Never downgrade." }, "tech-comparison-matrix": { "tier": "heavy", "rationale": "Weighted multi-criteria judgment with a recommendation. Mis-weighting is the failure mode; heavy is worth it. Never downgrade." }, "threat-model": { "tier": "heavy", "rationale": "Adversarial reasoning over a design — cheaper models emit checklist residue, miss authz/insider paths, and inflate severity. Never downgrade." }, "prfaq": { "tier": "standard", "rationale": "Synthesizes a press release and FAQs from a product concept against a fixed format. The specificity discipline needs care but the template bounds it; escalate via ambiguous-input when the concept itself is contested." }, "okr-cascade": { "tier": "standard", "rationale": "Structured derivation against a fixed roll-up discipline; the causal-sentence and gap judgments need care but the template bounds them. Escalate via ambiguous-input when the company objectives themselves are contested." }, "user-journey-map": { "tier": "standard", "rationale": "Structured synthesis into a fixed four-row stage model plus bounded ranking judgment. Escalate via ambiguous-input when the persona or outcome is contested or research inputs conflict." }, "strategy-analysis": { "tier": "heavy", "rationale": "Framework selection plus evidenced multi-factor judgment ending in a ranked, committal verdict. Cheaper models fill cells with generic filler, skip the TOWS crossings, and refuse to take a side. Never downgrade." }, "agent-loop-design": { "tier": "standard", "rationale": "Design synthesis against a fixed state-machine pattern and exit-criteria catalog. The gate-placement judgment is bounded by the blast-radius rule; escalate via ambiguous-input when the task itself is contested." }, "subagent-design": { "tier": "standard", "rationale": "Design synthesis against a fixed topology catalog and role-card template. The fan-out-or-refuse judgment is bounded by the three-reasons rule; escalate via ambiguous-input on genuinely novel workflow shapes." }, "agent-budget": { "tier": "standard", "rationale": "Quantitative spec synthesis against a fixed tier vocabulary and degradation ladder. Cap-setting judgment is bounded by the 3-5x rule; escalate via ambiguous-input when the workflow itself is undefined." }, "agents-md-generator": { "tier": "standard", "rationale": "Repo inspection plus synthesis against a fixed section order and line budget — the same shape as reverse-architecture. The judgment is the counterfactual test on each convention line, which is bounded; escalate via large-input on monorepos." }, "agent-threat-model": { "tier": "heavy", "rationale": "Adversarial reasoning over a capability graph — the judgment is which mitigations are architectural versus theatrical, and that call is exactly where a weaker model produces a confident wrong answer. Never downgraded." } } }