skilldrop-cli 1.2.0 → 1.4.0

package/README.md

@@ -15,13 +15,13 @@ npx skilldrop-cli install --pack dev-team     # or product-manager, solution-arc
 
 From a held-out eval, written blind from the skill's description:
 
-> *"We're taking ClaimLens to the investment committee on Thursday… Can you build a lean canvas for it and set out our riskiest assumptions and how we'd test them?"*
+> *"Our design agency sent the Figma file for Ostwick Museum's new signage as a JSON export… Can you (1) list the pages and the frames on each, (2) check the Final page against what the Brief page asks for, and (3) draft the comments I should leave for the agency on any frames with problems — one line each."*
 
-| Plain Claude Code | With [`lean-canvas`](https://sananthanarayan.github.io/skilldrop/skills/lean-canvas/) |
+| Plain Claude Code | With [`figma-diagrams`](https://sananthanarayan.github.io/skilldrop/skills/figma-diagrams/) |
 |---|---|
-| Finds the corrected break-even (~225 seats), then recommends *"scope the ask to Claims-only Phase 1"*. | *"Corrected, break-even is 225 seats — more than all three departments combined (215), so full rollout still doesn't cover running costs at £40/seat."* |
+| Finds the same three problems, then drafts comments of two sentences or more, and adds a fourth one about the Archive page that the file doesn't support. | *"The cover email is wrong on both counts. The Sign Types page has 11 frames, not 12, and Type 07 is missing."* Then one line per frame with a problem. |
 
-The blind judge picked the skill's answer: *"A misses this and recommends a Claims-only phase that cannot break even."*
+Both blind judges picked the skill's answer: *"A keeps each comment to a single sentence as asked, while B's main comments run to two sentences and its fourth comment is speculative."*
 
 ## The receipts
 
@@ -80,7 +80,7 @@ Install one pack. Every role pack also brings `core` (intake, critique, review c
 ## How it works
 
 - **A skill produces one file you own.** Each ships a quality bar, named anti-patterns and acceptance evals, so the output is an artifact, not a conversation. See [every skill, by category](guides/reference/skill-catalogue.md).
-- **Loops order skills, and a gate decides when work moves on.** Five loops cover the lifecycle (`discover`, `design`, `build`, `release`, `operate`), plus the `ship-a-draft` wrapper for any document and `apply` for a job application. Each gate is a script, a review panel or a person, chosen by how expensive the mistake is to undo. See [the operating model](guides/explanation/operating-model.md) for every stage and gate on one page, [the loops, stage by stage](guides/reference/loops.md), and [why loops](guides/explanation/loops.md).
+- **Loops order skills, and a gate decides when work moves on.** Five loops cover the lifecycle (`discover`, `design`, `build`, `release`, `operate`), plus the `ship-a-draft` wrapper for any document and loops for jobs beside it, such as `research`, `comply`, `adopt` for a team starting with AI, `ship-agent` for an AI agent and `provision` for a Terraform change. Each gate is a script, a review panel or a person, chosen by how expensive the mistake is to undo. See [the operating model](guides/explanation/operating-model.md) for every stage and gate on one page, [the loops, stage by stage](guides/reference/loops.md), and [why loops](guides/explanation/loops.md).
 - **Measured, not asserted.** `run_bench.py` runs each acceptance eval with the skill and without it, in a sandbox, and reports the lift, a blind preference from two judges, and the cost per run. The results are published whether or not they flatter the skills. See [how skills are checked](https://sananthanarayan.github.io/skilldrop/evals/) and [RFC-0040](docs/rfcs/0040-skill-benchmark.md).
 - **Copy, never transform.** A skill is a plain `SKILL.md` folder in the [Agent Skills](https://agentskills.io) format, at `packs/<pack>/skills/<name>/`. What runs in your agent is byte-identical to what is reviewed here. There is no runtime, and the tooling has zero dependencies.
 - **Updates keep your edits.** `npx skilldrop-cli update` replaces files you haven't touched. For any file you changed, it leaves the new version beside it as `<file>.upstream`. See [upgrade installed skills](guides/how-to/upgrade-skills.md).

package/catalogue.json

@@ -18,8 +18,7 @@
         "success-metrics",
         "user-story-splitter",
         "user-journey-map",
-        "feedback-synthesis",
-        "lean-canvas"
+        "feedback-synthesis"
       ]
     },
     "design-the-system": {
@@ -124,7 +123,6 @@
         "ai-adoption-rollout",
         "ai-usage-policy",
         "agent-adoption-stage",
-        "ai-usage-report",
         "agent-config-review",
         "agent-incident-response"
       ]
@@ -217,6 +215,8 @@
     "md-to-html": { "in": "1.2.0", "why": "On its held-out evals, in each of two trials and with both blind judges, the agent without it made the better page: the skill's script showed raw HTML as text and its security policy blocked embeds, and it adds no rule the agent breaks." },
     "mermaid-render": { "in": "1.2.0", "why": "On its held-out evals, in each of two trials and with both blind judges, the agent without it fixed the same diagrams, ran the Mermaid CLI itself and said plainly what it had not rendered; the skill adds no rule it breaks." },
     "marketing-flyer": { "in": "1.2.0", "why": "On its held-out evals, in each of two trials and with both blind judges, the agent without it built the whole flyer with placeholders where the skill stopped or used a generic template; it adds no rule the agent breaks." },
-    "deck-builder": { "in": "1.2.0", "why": "On its held-out evals the agent without it built the better deck in each of two trials; rebuilt rule-first, with its script able to run, it still lost on fresh evals (judges 2 and 1 of 4; 69% of checks against 81%).", "instead": "md-to-pptx" }
+    "deck-builder": { "in": "1.2.0", "why": "On its held-out evals the agent without it built the better deck in each of two trials; rebuilt rule-first, with its script able to run, it still lost on fresh evals (judges 2 and 1 of 4; 69% of checks against 81%).", "instead": "md-to-pptx" },
+    "ai-usage-report": { "in": "1.4.0", "why": "On its held-out evals, over three trials and with both blind judges, the agent without it made the better report: it kept every rule the skill teaches (counts show activity, not quality; missing data is not zero; no leaderboard), while the skill refused to rank when asked, hid names the manager had supplied, and its script read neither eval's export." },
+    "lean-canvas": { "in": "1.4.0", "why": "On its held-out evals, in each of three trials and with both blind judges, the agent without it made the better canvas: it caught the same errors and went further, while the skill's lead on checks came from its own format and its script's break-even left out the cost of replacing lost customers.", "instead": "business-case" }
   }
 }

package/model-routing.json

@@ -107,8 +107,8 @@
       "rationale": "Structures a decision into MADR/Nygard. Some judgment on title/consequences; not adversarial."
     },
     "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."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 79% and 86% of checks in two tier trials, against standard's 82% and heavy's 79% and 79%, within 5 points of the best both times."
     },
     "agent-budget": {
       "tier": "standard",
@@ -135,8 +135,8 @@
       "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."
     },
     "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."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 79% and 71% of checks in two tier trials, against standard's 75% and heavy's 64% and 64%, within 5 points of the best both times."
     },
     "ai-readiness-assessment": {
       "tier": "standard",
@@ -146,25 +146,21 @@
       "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."
     },
-    "ai-usage-report": {
-      "tier": "standard",
-      "rationale": "Tabulates telemetry into a report. Mostly mechanical, but the 'AI theater' effectiveness call needs judgment."
-    },
     "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."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 83% and 92% of checks in two tier trials, against standard's 81% and heavy's 85% and 92%, within 5 points of the best both times."
     },
     "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."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 76% and 92% of checks in two tier trials, against standard's 69% and heavy's 69% and 76%, within 5 points of the best both times."
     },
     "application-form-answers": {
-      "tier": "standard",
-      "rationale": "Sorts questions into three kinds and drafts short answers from the resume. The hard rule is mechanical: a declaration is never answered for the person."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 88% and 94% of checks in two tier trials, against standard's 88% and heavy's 81% and 81%, within 5 points of the best both times."
     },
     "architecture-diagrams": {
-      "tier": "standard",
-      "rationale": "Translates prose to diagram syntax. Correctness matters; reasoning is bounded."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 93% and 100% of checks in two tier trials, against standard's 93% and heavy's 93% and 93%, within 5 points of the best both times."
     },
     "audience-profile": {
       "tier": "light",
@@ -219,8 +215,8 @@
       "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."
     },
     "cover-letter": {
-      "tier": "standard",
-      "rationale": "A short letter from supplied facts, with a script listing every figure and name the person's material doesn't contain."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 100% and 100% of checks in two tier trials, against standard's 100% and heavy's 100% and 100%, within 5 points of the best both times."
     },
     "dashboard-spec": {
       "tier": "standard",
@@ -231,8 +227,8 @@
       "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."
     },
     "decision-log": {
-      "tier": "light",
-      "rationale": "Extracts decisions/owners/dates from notes. Pattern extraction; escalate on long transcripts via large-input rule."
+      "tier": "standard",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier fell more than 5 points behind the best in both tier trials (79% and 61% against standard's 79%); one step up, to standard."
     },
     "delivery-metrics-report": {
       "tier": "standard",
@@ -243,8 +239,8 @@
       "rationale": "Reads a version diff, changelogs and CI evidence against a fixed checklist; the merge verdict follows from what is verified, not open-ended judgment."
     },
     "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."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 88% and 88% of checks in two tier trials, against standard's 92% and heavy's 91% and 91%, within 5 points of the best both times."
     },
     "design-system-spec": {
       "tier": "standard",
@@ -276,16 +272,16 @@
       "rationale": "Compression to one page. Needs to keep the right signal; escalate on very long source docs."
     },
     "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."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 85% and 85% of checks in two tier trials, against standard's 85% and heavy's 76% and 85%, within 5 points of the best both times."
     },
     "feedback-synthesis": {
       "tier": "standard",
       "rationale": "Coding feedback into themes is bounded judgment; the counts by distinct person and segment come from its script."
     },
     "figma-diagrams": {
-      "tier": "standard",
-      "rationale": "API calls + spec generation. Bounded transformation."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 92% and 92% of checks in two tier trials, against standard's 92% and heavy's 75% and 92%, within 5 points of the best both times."
     },
     "file-to-markdown": {
       "tier": "light",
@@ -300,8 +296,8 @@
       "rationale": "Judgment-heavy: generating real rivals, rating every evidence-hypothesis cell honestly and resisting the favourite theory is where a fast pass fails; the script only does the arithmetic."
     },
     "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."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 93% and 100% of checks in two tier trials, against standard's 85% and heavy's 92% and 93%, within 5 points of the best both times."
     },
     "information-architecture": {
       "tier": "standard",
@@ -323,13 +319,9 @@
       "tier": "standard",
       "rationale": "Checks evidence against a fixed checklist. Bounded synthesis, not adversarial review."
     },
-    "lean-canvas": {
-      "tier": "standard",
-      "rationale": "Filling the canvas is structured; the value is in ranking assumptions by risk and naming the cheapest test that could kill the riskiest one."
-    },
     "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."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 71% and 71% of checks in two tier trials, against standard's 71% and heavy's 71% and 71%, within 5 points of the best both times."
     },
     "mcp-pairing": {
       "tier": "standard",
@@ -340,8 +332,8 @@
       "rationale": "Mechanical conversion to Confluence storage format done by its script, with an optional publish; the model checks what was dropped and what will be overwritten."
     },
     "md-to-docx": {
-      "tier": "standard",
-      "rationale": "A stdlib script does the conversion; the model restructures the Markdown so it converts cleanly (heading levels, footnotes, HTML), reads each warning and explains the losses. Bounded editing, no open-ended generation."
+      "tier": "heavy",
+      "rationale": "Measured (RFC-0073): on its held-out evals the heavy tier met 79% and 93% of checks in two tier trials, against standard's 64% and light's 71% and 79%, more than 5 points ahead both times."
     },
     "md-to-pptx": {
       "tier": "light",
@@ -368,24 +360,24 @@
       "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."
     },
     "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."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 100% and 100% of checks in two tier trials, against standard's 92% and heavy's 100% and 92%, within 5 points of the best both times."
     },
     "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."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 93% and 91% of checks in two tier trials, against standard's 92% and heavy's 90% and 87%, within 5 points of the best both times."
     },
     "pr-description-writer": {
-      "tier": "standard",
-      "rationale": "Reads a diff and rewrites it for a reviewer. Bounded by the diff; the judgment is in picking what a reviewer needs first."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 85% and 85% of checks in two tier trials, against standard's 85% and heavy's 77% and 85%, within 5 points of the best both times."
     },
     "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."
     },
     "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."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 93% and 93% of checks in two tier trials, against standard's 86% and heavy's 93% and 93%, within 5 points of the best both times."
     },
     "prfaq": {
       "tier": "standard",
@@ -400,8 +392,8 @@
       "rationale": "Sequencing behaviour-preserving steps follows known patterns (characterise, parallel change, strangle); escalate via ambiguous-input for contested rewrites."
     },
     "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."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 96% and 96% of checks in two tier trials, against standard's 91% and heavy's 100% and 98%, within 5 points of the best both times."
     },
     "rendering-strategy": {
       "tier": "standard",
@@ -412,12 +404,12 @@
       "rationale": "Question banks are rubric-shaped, but ranking by design impact and deriving falsification conditions for the specific feature is synthesis — above light."
     },
     "research-plan": {
-      "tier": "standard",
-      "rationale": "Structured planning against a fixed shape (decision, sub-questions, methods, criteria, stopping rule); needs judgment to cut scope but no adversarial reasoning."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 79% and 79% of checks in two tier trials, against standard's 79% and heavy's 79% and 79%, within 5 points of the best both times."
     },
     "resume-tailor": {
-      "tier": "standard",
-      "rationale": "Reorders and rewords existing content against a posting, with a script listing every figure and name the original doesn't contain."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 100% and 100% of checks in two tier trials, against standard's 100% and heavy's 100% and 100%, within 5 points of the best both times."
     },
     "reverse-architecture": {
       "tier": "standard",
@@ -444,20 +436,20 @@
       "rationale": "Matches questions to evidence and writes short answers. The hard rule is mechanical: no evidence, no answer."
     },
     "service-blueprint": {
-      "tier": "standard",
-      "rationale": "Structured mapping of a described service into fixed lanes, with fail points, waits and a ranking. Tracing causes needs judgment, but the lane structure and the input bound it."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 100% and 92% of checks in two tier trials, against standard's 92% and heavy's 85% and 92%, within 5 points of the best both times."
     },
     "skill-author": {
-      "tier": "standard",
-      "rationale": "Structured authoring against a fixed anatomy. The judgment is in the description and sibling boundaries, which the interview anchors; skill-review is the adversarial pass."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 100% and 93% of checks in two tier trials, against standard's 93% and heavy's 100% and 92%, within 5 points of the best both times."
     },
     "skill-review": {
       "tier": "heavy",
       "rationale": "Adversarial audit with a verdict: routing collisions and paraphrased safety issues are what a fast pass misses, and the lint script covers only the mechanical half."
     },
     "slide-outliner": {
-      "tier": "standard",
-      "rationale": "Outlines a deck to a time budget. Structuring, not deep reasoning."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 86% and 90% of checks in two tier trials, against standard's 83% and heavy's 83% and 93%, within 5 points of the best both times."
     },
     "slo-spec": {
       "tier": "standard",
@@ -476,8 +468,8 @@
       "rationale": "Formats Sonar API findings into a report. The hard analysis is Sonar's; this is synthesis. Escalate on very large diffs."
     },
     "source-synthesis": {
-      "tier": "standard",
-      "rationale": "Bounded synthesis over supplied text with a fixed citation format and strength criteria; the citation checker catches the mechanical failures, so mid-tier judgment is enough."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 83% and 78% of checks in two tier trials, against standard's 76% and heavy's 85% and 82%, within 5 points of the best both times."
     },
     "sql-review": {
       "tier": "heavy",
@@ -496,24 +488,24 @@
       "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."
     },
     "team-status-report": {
-      "tier": "standard",
-      "rationale": "A script computes every count and the suggested RAG; the model writes plain-language summaries, attributes outside facts and frames risks and asks. Bounded writing over computed numbers."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 93% and 93% of checks in two tier trials, against standard's 93% and heavy's 93% and 93%, within 5 points of the best both times."
     },
     "tech-debt-register": {
       "tier": "standard",
       "rationale": "Structures and ranks items against stated evidence. Judgment is bounded: a cost with no evidence is recorded as unknown, not estimated."
     },
     "terraform-module": {
-      "tier": "standard",
-      "rationale": "Structured generation against fixed module conventions and a secure-defaults checklist; the judgment is bounded to choosing defaults and validation rules for a described need."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 100% and 100% of checks in two tier trials, against standard's 92% and heavy's 83% and 100%, within 5 points of the best both times."
     },
     "terraform-plan-review": {
       "tier": "heavy",
       "rationale": "Adversarial review of a destructive change: judging which replacements lose data, which access changes widen exposure, and what is out of scope needs careful reasoning; a missed destroy costs far more than the model."
     },
     "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."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 76% and 92% of checks in two tier trials, against standard's 76% and heavy's 61% and 54%, within 5 points of the best both times."
     },
     "threat-model": {
       "tier": "heavy",
@@ -524,24 +516,24 @@
       "rationale": "Arithmetic breakdown plus heuristic judgment on dominant cost drivers — standard fits."
     },
     "tool-use-schema-writer": {
-      "tier": "standard",
-      "rationale": "Schema generation from natural-language description — structured output task that fits standard tier."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 94% and 94% of checks in two tier trials, against standard's 96% and heavy's 97% and 97%, within 5 points of the best both times."
     },
     "tracker-brief-sync": {
       "tier": "standard",
       "rationale": "Maps doc sections to items and writes acceptance criteria that restate requirements; a script checks the spec, writes the import file and computes drift. Bounded transformation with a deterministic check."
     },
     "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."
+      "tier": "heavy",
+      "rationale": "Measured (RFC-0073): on its held-out evals the heavy tier met 83% and 83% of checks in two tier trials, against standard's 75% and light's 67% and 75%, more than 5 points ahead both times."
     },
     "user-story-splitter": {
       "tier": "standard",
       "rationale": "Decomposes an epic into INVEST slices with testable ACs. Structured synthesis; escalation rules cover large or contradictory PRDs."
     },
     "ux-writing": {
-      "tier": "standard",
-      "rationale": "Short-form writing to fixed slot rules and character budgets, plus a terminology consistency pass. Bounded generation with clear checks."
+      "tier": "light",
+      "rationale": "Measured (RFC-0073): on its held-out evals the light tier met 92% and 92% of checks in two tier trials, against standard's 83% and heavy's 75% and 83%, within 5 points of the best both times."
     },
     "web-performance-review": {
       "tier": "standard",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "skilldrop-cli",
-  "version": "1.2.0",
+  "version": "1.4.0",
   "description": "Portable AI-agent skills, measured against the agent without them. ADRs, PRDs, runbooks, decks and reviews, installable into Claude Code, Cursor, Kiro, and any IDE that takes custom instructions. One command per skill or per role-based pack.",
   "author": {
     "name": "Sanjay Ananthanarayan",

package/packs/ai-engineering/loops/adopt/LOOP.md

@@ -0,0 +1,120 @@
+---
+name: adopt
+description: Take an organisation from a pile of AI ideas to a first rollout wave its sponsor approved: the use cases ranked with a first slice, readiness scored against that slice, a usage policy covering the data the slice touches, and a cohort rollout whose first wave is the slice's users, with a gate that sends the slice back when a blocking gap stands in its way. Use when the user says "help us start using AI", "roll out AI across the team", "run the adopt loop", or has AI ideas, no policy and no rollout plan.
+---
+
+# adopt
+
+One first slice, from a list of ideas to a wave of people using it. The four skills each work
+alone; in order, each one narrows the next. Triage picks one use case, so readiness is scored
+against what that use case needs instead of against the whole organisation. Readiness names the
+gaps, so the policy covers the data the slice really touches. The rollout's pilot is the slice's
+own users, and its adoption gate is the observable triage said would prove or kill the slice.
+
+## Stages
+
+| # | Stage | Type | Skills | Gate |
+|---|---|---|---|---|
+| 1 | `triage` | generate | [`ai-use-case-triage`](../../skills/ai-use-case-triage/SKILL.md) | — |
+| 2 | `readiness` | verify | [`ai-readiness-assessment`](../../skills/ai-readiness-assessment/SKILL.md) | **G11** review |
+| 3 | `policy` | generate | [`ai-usage-policy`](../../skills/ai-usage-policy/SKILL.md) | — |
+| 4 | `rollout` | generate | [`ai-adoption-rollout`](../../skills/ai-adoption-rollout/SKILL.md) | — |
+| 5 | `sign-off` | gate | [`doc-critique`](../../../core/skills/doc-critique/SKILL.md) | **G11.1** human |
+
+## How to run this loop
+
+1. **Triage the ideas.** Run `ai-use-case-triage` on whatever the person brought: a brainstorm,
+   a backlog, interview notes. Save it as `triage.md`. Carry three things from it into every
+   later stage: the first slice (one workflow and the people who do it), the observable that
+   proves or kills it, and the time box.
+2. **Score readiness for the slice.** Run `ai-readiness-assessment` scoped to the slice's team
+   and the decision "can this slice start". Each dimension is read against what the slice
+   needs: Data is the data the slice reads, Tooling is the tool the slice uses, Process is the
+   review step the slice's output passes through. Save it as `readiness.md`.
+3. **Judge the slice at G11.** Ask three questions, then choose the verdict below:
+   - Does any gap the assessment ranks as blocking sit on something the slice needs?
+   - Can each remaining gap be closed inside the slice's time box, with an owner role named?
+   - Is there a review step where a person checks the slice's output before anyone acts on it?
+4. **On `REVISE`, change the slice, not the scores.** Return to `triage` with the blocking gap
+   as a constraint, and pick the highest-ranked candidate that does not need what is missing.
+   The not-yet list's promotion conditions say which one. Each return counts against the cap.
+5. **Write the policy for the slice's data.** Run `ai-usage-policy` for the slice's people,
+   naming every kind of data the slice puts into a tool (from triage and the Data line of
+   readiness). Every kind of data the slice touches gets a rule; a rule for data the slice
+   never touches stays out of this version. Save it as `policy.md`.
+6. **Plan the rollout from the slice.** Run `ai-adoption-rollout` with the slice's users as the
+   pilot cohort and triage's observable as the pilot's adoption gate. G11's conditions become
+   preconditions the pilot cannot open without. Save it as `rollout.md`.
+7. **Ask the sponsor at G11.1.** Run `doc-critique` over the policy and the rollout together,
+   then put the first wave, the conditions and the critique's open findings to the person who
+   sponsors the slice. Only they choose the verdict. In a non-interactive run, stop here and
+   write the decision they need to make; never record their verdict for them.
+8. **Hand over the plan, then the verdict.** Lead with the slice, who starts using it and when,
+   and what would end it. The scorecard, the policy and the cohort plan go underneath. Close
+   with each gate on its own line, `G11: <VERDICT>` and `G11.1: <VERDICT>` (or
+   `G11.1: awaiting <role>`), and one sentence of reasons.
+
+## Verdicts
+
+Defined in [`contracts/terminals.json`](../../../../contracts/terminals.json). G11 emits:
+
+- `PROCEED`: no blocking gap sits on what the slice needs, and its output has a review step.
+- `PROCEED WITH CONDITIONS`: a gap sits on the slice but can close inside the time box, with
+  an owner role. Each condition travels into the rollout as a precondition for the pilot.
+- `REVISE`: a blocking gap sits on the slice and won't close inside the time box. Return to
+  `triage` with that gap as a constraint.
+- `RECONSIDER`: the gap blocks every candidate, such as no rule for what may go into any tool
+  or no tool access at all. Fixing it is the work, so the loop ends here with that gap's first
+  action and owner role.
+- `BLOCKED`: no candidates to triage, or no team the slice belongs to.
+
+G11.1 emits `PROCEED`, `PROCEED WITH CONDITIONS`, `REVISE` (back to `policy`, when the sponsor
+rejects a rule or a cohort) or `BLOCKED` (no sponsor named).
+
+On the cap-th `REVISE` at G11, emit `RECONSIDER`: three slices in a row hit blocking gaps, so
+the gaps are the work.
+
+## Non-interactive runs
+
+With no candidates, `ai-use-case-triage` emits `BLOCKED`; carry it through as the loop's
+verdict and run no further stages. Missing weights and readiness evidence degrade to the
+skills' own `[assumption]` and `[insufficient evidence]` tags. G11.1 always stops at the
+sponsor: write `G11.1: awaiting <role>` with the decision they face, never a verdict.
+
+## When a stage's skill is not installed
+
+Name the missing skill and skilldrop as its source, do the minimal inline version of that
+stage, and record that it ran degraded. A degraded `readiness` still scores Data, Tooling,
+Governance and Process against the slice with an evidence line each, because G11 can't be
+judged without them. Never skip G11 or G11.1.
+
+## Run log (opt-in)
+
+Only when the environment variable `SKILLDROP_LOOP_LOG` is set to a file path: after each
+gate's verdict, append one JSON line to that file. Nothing else is recorded, and nothing is
+sent anywhere. When the variable isn't set, or you can't read it, skip this section.
+
+```bash
+printf '%s\n' '{"ts":"2026-11-03T10:15:00Z","loop":"adopt","stage":"readiness","gate":"G11","verdict":"REVISE","round":1}' >> "$SKILLDROP_LOOP_LOG"
+```
+
+Fields: `ts` (UTC), `loop`, `stage`, `gate` (`null` for a stage without one), `verdict` (the
+gate's exact word), and `round` (1 for the first attempt, counting returns under the cap).
+The log holds verdicts only: never the use cases, the scores or the policy.
+`skilldrop loop-stats` summarises the file.
+
+## Quality bar
+
+- **Readiness is scored against the slice.** An organisation-wide score hides the one gap that stops the slice and flags gaps that stop nothing yet.
+- **A `REVISE` changes the slice.** It never re-scores a dimension upward to let the same slice through.
+- **The policy covers every kind of data the slice touches,** each restriction with what to do instead.
+- **The pilot is the slice's users, and its adoption gate is triage's observable.** A pilot of volunteers from elsewhere proves nothing about the slice.
+- **G11.1 is the sponsor's call.** The loop writes the decision they face; it never records their verdict.
+
+## Anti-patterns to avoid
+
+- ❌ **Scoring the whole company's readiness first.** The assessment then ranks gaps by how bad they look, not by what they block.
+- ❌ **Writing a policy for every tool and every kind of data before anything ships.** It is long, it is late, and nobody reads the part that matters to the pilot.
+- ❌ **Passing G11 with a blocking gap and a promise.** A gap that won't close inside the time box is a `REVISE`, however good the slice looks.
+- ❌ **A pilot gate that is "the pilot went well".** The gate is triage's observable, with its threshold and time box.
+- ❌ **Running all four skills before the first gate.** A policy and a rollout written for a slice that then fails G11 are thrown away.

package/packs/ai-engineering/loops/adopt/evals/eval_queries.json

@@ -0,0 +1,10 @@
+[
+  {"query": "help us start using AI in the finance team, we have ideas but no rules and no plan", "should_trigger": true},
+  {"query": "run the adopt loop on these AI use cases from the workshop", "should_trigger": true},
+  {"query": "we want to roll out AI across the support team: pick where to start, check we're ready, write the rules and plan the waves", "should_trigger": true},
+  {"query": "take this list of AI ideas to a first pilot our VP can sign off", "should_trigger": true},
+  {"query": "rank these twelve AI use cases by value and risk", "should_trigger": false},
+  {"query": "write an AI acceptable-use policy for our staff", "should_trigger": false},
+  {"query": "how far along is our engineering team with coding agents?", "should_trigger": false},
+  {"query": "design an eval harness for our support chatbot", "should_trigger": false}
+]