skilldrop-cli 0.16.12 → 0.16.13

package/bin/skilldrop.js

@@ -226,7 +226,8 @@ function readPacksCatalog(dir, source) {
     ? fs.readdirSync(d).filter((x) => fs.existsSync(path.join(d, x, marker))).sort() : [];
   const onDisk = children(packsDir, "pack.json");
   const idx = path.join(dir, "catalogue.json");
-  const listed = fs.existsSync(idx) ? (readJSON(idx).packs || []).filter((p) => onDisk.includes(p)) : [];
+  const index = fs.existsSync(idx) ? readJSON(idx) : {};
+  const listed = (index.packs || []).filter((p) => onDisk.includes(p));
   const order = [...listed, ...onDisk.filter((p) => !listed.includes(p))];
   const skillIndex = {}, loopIndex = {}, packsData = {};
   for (const pack of order) {
@@ -237,7 +238,15 @@ function readPacksCatalog(dir, source) {
     for (const l of loops) if (!loopIndex[l]) loopIndex[l] = path.join(pdir, "loops", l);
     packsData[pack] = Object.assign({}, readJSON(path.join(pdir, "pack.json")), { skills, loops });
   }
-  return { dir, source, shape: "packs", skillIndex, loopIndex, packsData };
+  return { dir, source, shape: "packs", skillIndex, loopIndex, packsData, retired: index.retired || {} };
+}
+
+/* RFC-0046: a skill that left the catalogue keeps a record in catalogue.json `retired`, so an
+   installed copy can say why it stopped updating instead of looking like an unreachable source. */
+function retiredNote(cat, s) {
+  const r = cat && cat.retired && cat.retired[s];
+  if (!r) return null;
+  return `'${s}' was retired in ${r.in}: ${r.why}` + (r.instead ? ` Use ${r.instead} instead.` : "");
 }
 
 /* Minimal TOML read — the [pack] table's basic-string scalars (name, version, description).
@@ -589,6 +598,12 @@ function target(flags) {
   return { dest: path.join(os.homedir(), ...user), ide };
 }
 
+/* The target flags again, for a command line printed back to the user. */
+function targetHint(flags) {
+  if (flags.dest) return ` --dest ${JSON.stringify(flags.dest)}`;
+  return (flags.ide && flags.ide !== "claude" ? ` --ide ${flags.ide}` : "") + (flags.local ? " --local" : flags.project ? " --project" : "");
+}
+
 /* Claude Code tool name -> Kiro built-in tool name. Confirmed against
    kiro.dev/docs/cli/reference/built-in-tools/ — not inferred. Agent configs use these
    simplified names; Kiro's *hook* matchers use internal names (fs_read, execute_bash)
@@ -985,7 +1000,7 @@ function expandNames(args, cat) {
     return packMembers(ps, args.flags.pack, "skills");
   }
   if (!args._.length) die("nothing to install — pass skill names, --pack <name>, or --all");
-  for (const s of args._) if (!skillExists(cat, s)) die(`unknown skill '${s}' in catalog '${cat.source}'`);
+  for (const s of args._) if (!skillExists(cat, s)) die(retiredNote(cat, s) || `unknown skill '${s}' in catalog '${cat.source}'`);
   return args._.slice();
 }
 
@@ -1285,11 +1300,12 @@ function installedRows(flags) {
   const l = ledger(dest);
   const rows = Object.keys(l.data).sort().map((s) => {
     const src = lsrc(l.data[s]);
-    let current = null, cat = null, changed = [];
+    let current = null, cat = null, changed = [], retired = null;
     const entry = l.data[s];
     const loop = isLoopEntry(entry);
     try {
       cat = resolveCatalog(src === BUNDLED ? undefined : src);
+      if (!loop && !unitExists(cat, s, loop)) retired = retiredNote(cat, s);
       if (unitExists(cat, s, loop)) {
         current = unitMeta(cat, s, loop).version || null;
         // Same version, different files: the catalog changed the skill without bumping it.
@@ -1301,7 +1317,7 @@ function installedRows(flags) {
         }
       }
     } catch (e) { /* unreachable source: current stays null */ }
-    return { s, src, cat, loop, installed: lver(entry), current, changed, pinned: isPinned(src) };
+    return { s, src, cat, loop, installed: lver(entry), current, changed, retired, pinned: isPinned(src) };
   });
   return { dest, ide, l, rows };
 }
@@ -1325,6 +1341,7 @@ function update(args) {
   let n = 0, conflicts = 0;
   const silent = rows.filter((r) => r.current === r.installed && r.changed.length && !args.flags.changed);
   for (const r of rows) {
+    if (r.retired) { console.log(`skip ${r.retired}\n  Remove it with: skilldrop uninstall ${r.s}${targetHint(args.flags)}`); continue; }
     if (!r.current) { console.log(`skip ${unitLabel(r)}: source '${r.src}' unreachable, ${r.loop ? "loop" : "skill"} gone from it, or no version to compare`); continue; }
     if (!isDue(r)) continue;
     const problems = unitCheck(r.cat, r.s, r.loop);
@@ -1346,7 +1363,7 @@ function update(args) {
     n++;
   }
   saveLedger(l);
-  console.log(n ? `\n${n} skill(s) or loop(s) updated.` : (silent.length ? "no version changes." : "everything up to date."));
+  console.log(n ? `\n${n} skill(s) or loop(s) updated.` : (silent.length ? "no version changes." : rows.some((r) => r.retired) ? "nothing else to update." : "everything up to date."));
   if (silent.length)
     console.log(`\nNot taken: ${silent.map((r) => r.s).join(", ")} changed upstream without a version bump.` +
                 `\n  Read the change (skilldrop diff <skill>), then take it with: skilldrop update --changed`);
@@ -1371,6 +1388,7 @@ function planUpdate(dest, ide, l, rows, flags) {
   console.log(`dry run — nothing will be written. Target: ${dest} (${ide})\n`);
   let n = 0;
   for (const r of rows) {
+    if (r.retired) { console.log(`would skip ${r.retired}`); continue; }
     if (!r.current) { console.log(`would skip ${unitLabel(r)}: source '${r.src}' unreachable, ${r.loop ? "loop" : "skill"} gone from it, or no version to compare`); continue; }
     if (r.current === r.installed && !r.changed.length) continue;
     if (r.current === r.installed && !flags.changed) {
@@ -1392,33 +1410,38 @@ function planUpdate(dest, ide, l, rows, flags) {
     for (const f of orphaned) console.log(`  would keep ${f} — dropped upstream, but you edited it`);
   }
   const held = rows.filter((r) => r.current && r.current === r.installed && r.changed.length && !flags.changed).length;
-  console.log(n ? `\n${n} skill(s) or loop(s) would update. Rerun without --dry-run to apply.` : (held ? "no version changes." : "everything up to date."));
+  console.log(n ? `\n${n} skill(s) or loop(s) would update. Rerun without --dry-run to apply.` : (held ? "no version changes." : rows.some((r) => r.retired) ? "nothing else to update." : "everything up to date."));
 }
 
 function outdated(args) {
   const { dest, rows } = installedRows(args.flags);
   const stale = rows.filter((r) => r.current && r.current !== r.installed);
   const drift = rows.filter((r) => r.changed && r.changed.length);
+  const gone = rows.filter((r) => r.retired);
   if (args.flags.json)
     return emitJSON({
       dest,
       count: rows.length,
       outdatedCount: stale.length,
       changedWithoutVersionCount: drift.length,
+      retiredCount: gone.length,
       skills: rows.map((r) => ({
         name: r.s, loop: r.loop, installed: r.installed, current: r.current,
         source: r.src, outdated: !!(r.current && r.current !== r.installed),
-        changedWithoutVersion: r.changed || [], pinned: r.pinned,
+        changedWithoutVersion: r.changed || [], pinned: r.pinned, retired: r.retired,
       })),
     });
   if (!rows.length) return console.log(`nothing installed at ${dest}`);
   for (const r of stale) console.log(`${unitLabel(r)}: installed ${r.installed}, current ${r.current} (${r.src})`);
   for (const r of drift)
     console.log(`${unitLabel(r)}: ${r.changed.length} file(s) changed in '${r.src}' without a version bump (${r.changed.slice(0, 3).join(", ")}${r.changed.length > 3 ? ", …" : ""})`);
+  for (const r of gone) console.log(r.retired);
   if (drift.length)
     console.log(`\n${drift.length} skill(s) changed upstream with the same version. Read the change first (skilldrop diff <skill>),` +
                 `\nthen take it with: skilldrop update --changed`);
-  console.log(stale.length ? `\n${stale.length} outdated — run: skilldrop update` : (drift.length ? "" : "everything up to date."));
+  if (gone.length)
+    console.log(`\n${gone.length} retired skill(s) will not update. Keep them as they are, or remove them: skilldrop uninstall ${gone.map((r) => r.s).join(" ")}${targetHint(args.flags)}`);
+  console.log(stale.length ? `\n${stale.length} outdated — run: skilldrop update` : (drift.length || gone.length ? "" : "everything up to date."));
 }
 
 function uninstall(args) {
@@ -1470,7 +1493,7 @@ function diff(args) {
   const loop = isLoopEntry(entry);
   const src = args.flags.from || (entry ? lsrc(entry) : BUNDLED);
   const cat = resolveCatalog(src === BUNDLED ? undefined : src);
-  if (!unitExists(cat, s, loop)) die(`'${s}' is no longer in catalog '${cat.source}'`);
+  if (!unitExists(cat, s, loop)) die(loop ? `'${s}' is no longer in catalog '${cat.source}'` : (retiredNote(cat, s) || `'${s}' is no longer in catalog '${cat.source}'`));
   const theirs = unitHashes(cat, s, loop), mine = fileHashes(path.join(dest, s));
   const base = (entry && entry.files) || {};
   const changed = Object.keys(theirs).filter((f) => f in mine && mine[f] !== theirs[f]).sort();
@@ -1514,6 +1537,8 @@ function doctor(args) {
   else try { data = JSON.parse(raw); } catch (e) { add("error", `${lp} is not valid JSON`, "fix or delete it; skilldrop can't track updates until then"); }
   const names = Object.keys(data);
   for (const n of names) {
+    const note = !isLoopEntry(data[n]) && lsrc(data[n]) === BUNDLED && retiredNote(resolveCatalog(), n);
+    if (note) add("warn", note, `skilldrop uninstall ${n}${targetHint(args.flags)}, or keep it as it is; it will not update`);
     if (!fs.existsSync(path.join(dest, n))) add("error", `${n} is in the ledger but its folder is gone`, `skilldrop install ${n} (or uninstall ${n} to drop the record)`);
     else if (!data[n].file) {
       const loop = isLoopEntry(data[n]);
@@ -2031,7 +2056,7 @@ function info(args) {
   if (args.flags.pack) return infoPack(args);
   const cat = resolveCatalog(args.flags.from);
   const s = args._[0] || die("pass a skill name, or --pack <name>");
-  if (!skillExists(cat, s)) die(`unknown skill '${s}' in catalog '${cat.source}'`);
+  if (!skillExists(cat, s)) die(retiredNote(cat, s) || `unknown skill '${s}' in catalog '${cat.source}'`);
   const m = manifestOf(cat, s);
   const ps = packsOf(cat) || {};
   const inPacks = Object.entries(ps).filter(([, p]) => p.skills.includes(s)).map(([n]) => n);

package/catalogue.json

@@ -22,7 +22,7 @@
     },
     "design-the-system": {
       "for": "Architects · tech leads",
-      "description": "Commit the shape before the code: decision records, design docs, diagrams, contracts, schemas, migration and threat models, and the design of any agentic parts.",
+      "description": "Commit the shape before the code: decision records, design docs, diagrams, API and data contracts, migration and threat models, and the design of any agentic parts.",
       "skills": [
         "adr-generator",
         "design-doc",
@@ -30,9 +30,7 @@
         "reverse-architecture",
         "figma-diagrams",
         "api-contract-draft",
-        "db-schema-design",
         "data-contract",
-        "tech-comparison-matrix",
         "threat-model",
         "agent-threat-model",
         "migration-plan",
@@ -60,7 +58,6 @@
         "agents-md-generator",
         "llm-eval-harness",
         "eval-harness-generator",
-        "contribution-wizard",
         "backlog-triage",
         "tracker-brief-sync"
       ]
@@ -161,10 +158,9 @@
     },
     "define-and-trust-the-numbers": {
       "for": "Data analysts · analytics engineers",
-      "description": "Make the numbers a business runs on mean one thing: metric definitions a semantic layer can implement, SQL reviewed for wrong answers, and dashboards specced before they're built.",
+      "description": "Make the numbers a business runs on mean one thing: SQL reviewed for wrong answers, and dashboards specced before they're built, with every number on them defined.",
       "skills": [
         "dashboard-spec",
-        "metric-definition",
         "sql-review"
       ]
     },
@@ -196,5 +192,11 @@
         "application-form-answers"
       ]
     }
+  },
+  "retired": {
+    "tech-comparison-matrix": { "in": "0.16.13", "why": "On evals it was never revised against, the agent without it did as well, and its weighted totals were wrong in 4 of 8 runs." },
+    "db-schema-design": { "in": "0.16.13", "why": "On evals it was never revised against, the agent without it met as many checks (73% against 71%) and got types, time zones and constraints right unprompted." },
+    "metric-definition": { "in": "0.16.13", "why": "On evals it was never revised against, the agent without it did everything the skill teaches unprompted and won 13 of 16 blind verdicts." },
+    "contribution-wizard": { "in": "0.16.13", "why": "It prescribed a skill layout this catalogue no longer uses and imposed it on other repos. To add a skill to skilldrop, follow AGENTS.md and run validate.py." }
   }
 }

package/contracts/catalogue.schema.json

@@ -2,7 +2,7 @@
   "$schema": "https://json-schema.org/draft/2020-12/schema",
   "$id": "https://github.com/sananthanarayan/skilldrop/contracts/catalogue.schema.json",
   "title": "skilldrop catalogue.json",
-  "$comment": "RFC-0026 / RFC-0034. The catalogue index: pack display order, and the outcome axis. Packs answer WHO needs a skill (the folder it sits in); outcomes answer WHY someone opened the catalogue.",
+  "$comment": "RFC-0026 / RFC-0034 / RFC-0046. The catalogue index: pack display order, the outcome axis, and the skills that have left the catalogue. Packs answer WHO needs a skill (the folder it sits in); outcomes answer WHY someone opened the catalogue.",
   "type": "object",
   "additionalProperties": false,
   "required": ["version", "packs", "outcomes"],
@@ -28,6 +28,20 @@
           "skills": { "type": "array", "items": { "type": "string" }, "minItems": 1 }
         }
       }
+    },
+    "retired": {
+      "type": "object",
+      "description": "RFC-0046. Skills removed from the catalogue, so an installed copy can say why it stopped updating. A retired name has no folder and nothing references it; validate.py checks both.",
+      "additionalProperties": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["in", "why"],
+        "properties": {
+          "in": { "type": "string", "pattern": "^\\d+\\.\\d+\\.\\d+$", "description": "The skilldrop-cli version that removed it." },
+          "why": { "type": "string", "description": "One sentence, shown by outdated, update, doctor, diff, info and install." },
+          "instead": { "type": "string", "description": "A skill that covers the same job, when one does. Omit it when the agent without a skill does as well." }
+        }
+      }
     }
   }
 }

package/model-routing.json

@@ -162,10 +162,6 @@
       "tier": "standard",
       "rationale": "The script lints and renders deterministically, but fixing a broken diagram means reading the author's intent and rewriting syntax without changing nodes, edges or labels, and knowing when to ask instead."
     },
-    "metric-definition": {
-      "tier": "standard",
-      "rationale": "Structured specification against a fixed checklist (formula, grain, window, exclusions, edge cases, checks). Needs care with SQL and additivity but no adversarial judgment."
-    },
     "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."
@@ -368,7 +364,7 @@
     },
     "business-case": {
       "tier": "heavy",
-      "rationale": "Weighted multi-option judgment with a committal recommendation \u2014 same failure mode as tech-comparison-matrix: cheaper models mis-weight costs, inflate benefits, and miss the flip-assumption. Never downgrade."
+      "rationale": "Weighted multi-option judgment with a committal recommendation \u2014 cheaper models mis-weight costs, inflate benefits, and miss the flip-assumption. Never downgrade."
     },
     "incident-comms": {
       "tier": "standard",
@@ -390,10 +386,6 @@
       "tier": "heavy",
       "rationale": "Adversarial review against WCAG success criteria \u2014 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."
@@ -414,10 +406,6 @@
       "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 \u2014 cheaper models emit checklist residue, miss authz/insider paths, and inflate severity. Never downgrade."
@@ -474,10 +462,6 @@
       "tier": "standard",
       "rationale": "Schema generation from natural-language description \u2014 structured output task that fits standard tier."
     },
-    "contribution-wizard": {
-      "tier": "standard",
-      "rationale": "Intake plus structured generation \u2014 standard tier covers template-filling and schema-adherence judgment."
-    },
     "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."

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "skilldrop-cli",
-  "version": "0.16.12",
+  "version": "0.16.13",
   "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/skills/ai-readiness-assessment/SKILL.md

@@ -70,7 +70,7 @@ Readiness assessments fail in one of two ways: a number with no evidence behind
 - ❌ **Scoring what's easy to score.** Tooling is countable, Culture is not — and a report that goes deep on licences and hand-waves incentives has measured the wrong thing.
 - ❌ **Middle scores as a hedge.** A 2 everywhere means the assessment refused to commit. If the evidence is thin, say `[insufficient evidence]` and name what to collect.
 - ❌ **Gaps with no owner.** An unowned action is a wish. Roles, not names.
-- ❌ **Recommending tools.** This assesses readiness; vendor selection is a different decision (`tech-comparison-matrix`) and mixing them lets a vendor pitch masquerade as a diagnosis.
+- ❌ **Recommending tools.** This assesses readiness; vendor selection is a different decision, and mixing them lets a vendor pitch masquerade as a diagnosis.
 - ❌ **Showing the machinery.** The reply and the artifact are for the person who asked. Don't mention this skill, its files, templates, caps or internal terms, or that the run is non-interactive. Name another skill once, at the end, as a suggested next step, never inside the artifact.
 
 **Non-interactive:** with no user to ask, derive the scope from the input and tag it `[assumption]`. If the input contains no observable evidence for any dimension — a request with no organisational context — emit `BLOCKED: need observable context (systems, current practice, or stated policy) for at least three dimensions` rather than scoring from imagination.

package/packs/ai-engineering/skills/ai-readiness-assessment/manifest.json

@@ -1,6 +1,6 @@
 {
   "name": "ai-readiness-assessment",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "description": "Score an organisation's or team's readiness to adopt AI tooling across six gating dimensions — data, tooling, skills, governance, process, and culture — with an evidence line per score and the blocking gaps ranked by what stops adoption first. Use when the user asks \"are we ready for AI\", wants an AI maturity or readiness baseline, or needs to know what to fix before rolling tools out. Do NOT use to pick which use cases to build (that's ai-use-case-triage) or to plan the rollout itself (that's ai-adoption-rollout).",
   "entrypoint": "SKILL.md",
   "deps": {
@@ -17,8 +17,7 @@
     "ai-usage-policy",
     "ai-usage-report",
     "ai-use-case-triage",
-    "strategy-analysis",
-    "tech-comparison-matrix"
+    "strategy-analysis"
   ],
   "tags": [
     "ai-adoption",

package/packs/ai-engineering/skills/llm-eval-harness/SKILL.md

@@ -66,7 +66,7 @@ Builds the measurement that turns "the new prompt feels better" into "the new pr
 
 - ❌ Tabulating AI usage/adoption telemetry — that's `ai-usage-report`
 - ❌ Product-outcome metrics for a feature (adoption, handle time) — that's `success-metrics`
-- ❌ Picking which model/vendor to use — that's `tech-comparison-matrix`
+- ❌ Picking which model/vendor to buy on price, terms or support — this measures quality on your task, which is one input to that decision
 - ❌ The provider-specific API mechanics (token counting, streaming, tool-call format) — consult the provider's own reference; this skill is the eval methodology
 
 ## Anti-patterns to avoid

package/packs/ai-engineering/skills/llm-eval-harness/manifest.json

@@ -1,11 +1,11 @@
 {
   "name": "llm-eval-harness",
-  "version": "0.1.1",
+  "version": "0.1.2",
   "description": "Design an evaluation harness for an LLM-powered feature — a versioned golden set (representative + adversarial + regression cases), the cheapest adequate grading method per case, a metric with a pre-set pass bar and regression gate, and a failure taxonomy that targets iteration. Use when the user is building or tuning an LLM feature (prompt, RAG, agent, classifier) and needs evals, a way to test prompt/model changes, or to stop shipping quality regressions on vibes.",
   "entrypoint": "SKILL.md",
   "deps": { "npm": [], "pip": [] },
   "env": { "required": [], "optional": [] },
-  "related": ["ai-usage-report", "success-metrics", "tech-comparison-matrix"],
+  "related": ["ai-usage-report", "success-metrics"],
   "tags": ["llm", "evals", "ai-engineering", "testing", "llm-as-judge", "regression-gate"],
   "model": { "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." }
 }

package/packs/api-builder/pack.json

@@ -30,7 +30,7 @@
       {
         "skill": "tool-use-schema-writer",
         "you_do": "Describe each function the model should call.",
-        "you_get": "A tool_use JSON schema per function with types, required fields and parameter descriptions, plus a Python client.messages.create snippet."
+        "you_get": "A tool_use JSON schema per function with types, required fields and parameter descriptions, and a Python client.messages.create snippet when you ask for one."
       },
       {
         "skill": "token-budget-estimator",

package/packs/api-builder/skills/eval-harness-generator/SKILL.md

@@ -82,7 +82,7 @@ Run: python3 validate.py   # confirms the file is found
 - **expected_shape items that can't be checked.** "Output is comprehensive" is not checkable. Name specific sections, fields, or behaviors.
 - **Missing anti-pattern cases.** The most common eval gap is no cases that test the quality bar's failure modes. If a skill says "never present a hypothesis as the cause," there must be a case where the input tempts that failure.
 
-For designing eval harnesses for general LLM features (not skilldrop skills specifically), use `llm-eval-harness` instead. Use `contribution-wizard` when creating a new skill from scratch — it calls this skill as part of the authoring flow.
+For designing eval harnesses for general LLM features (not skilldrop skills specifically), use `llm-eval-harness` instead.
 
 ## Quality bar
 

package/packs/api-builder/skills/eval-harness-generator/manifest.json

@@ -1,11 +1,11 @@
 {
   "name": "eval-harness-generator",
-  "version": "1.0.2",
+  "version": "1.0.3",
   "description": "Takes a skill's SKILL.md and generates a set of eval cases — trigger queries, expected output shape, and pass/fail criteria — ready to drop into the skill's evals/ directory. Use when adding evals to a new or existing skill, verifying a skill behaves as documented, or building a regression gate before modifying a skill.",
   "entrypoint": "SKILL.md",
   "deps": { "npm": [], "pip": [] },
   "env": { "required": [], "optional": [] },
-  "related": ["llm-eval-harness", "contribution-wizard"],
+  "related": ["llm-eval-harness"],
   "tags": ["claude-api", "evals", "testing", "quality", "skilldrop-meta"],
   "model": { "tier": "standard", "rationale": "Reads a SKILL.md and synthesizes eval cases — requires understanding of the skill's intent but not heavy reasoning." }
 }

package/packs/api-builder/skills/tool-use-schema-writer/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: tool-use-schema-writer
-description: Takes a function description (name, purpose, parameters) and writes a valid Anthropic tool_use JSON schema, with type annotations, required fields, and a description for each parameter. Produces a Python usage snippet for client.messages.create(tools=[...]). Use when wiring a Claude agent to a function or API, designing tools for a multi-agent system, or documenting an existing tool for agent consumption.
+description: Takes a function description (name, purpose, parameters) and writes a valid Anthropic tool_use JSON schema, with type annotations, required fields, and a description for each parameter. Adds a Python client.messages.create(tools=[...]) snippet only when asked. Use when wiring a Claude agent to a function or API, designing tools for a multi-agent system, or documenting an existing tool for agent consumption.
 ---
 
 # tool-use-schema-writer
@@ -68,9 +68,9 @@ Check the definition against these rules before outputting:
 - Enum values are listed in the parameter description with a one-phrase explanation each
 - Nested objects have their own `"required"` arrays
 
-### Step 4 — Python usage snippet
+### Step 4 — Python usage snippet, only when asked
 
-Produce the Python snippet:
+Skip this step unless the user asked for client code. The definition is the deliverable; an unrequested snippet is padding the reader has to scroll past. When they ask, use this shape:
 
 ```python
 import anthropic

package/packs/api-builder/skills/tool-use-schema-writer/evals/evals.json

@@ -10,7 +10,7 @@
         "A required array is present and contains customer_id; every name in required exists in properties",
         "Every parameter has a non-empty description, and limit states its valid range (1-100)",
         "The status and sort enums list their values with a one-phrase explanation of each value",
-        "Includes a Python snippet passing the tool to client.messages.create(tools=[...]) and handling stop_reason == 'tool_use'",
+        "Gives the definition without a Python usage snippet, since none was asked for",
         "Does not invent parameters, enum values, or behaviors not in the supplied signature and docstring"
       ]
     },

package/packs/api-builder/skills/tool-use-schema-writer/manifest.json

@@ -1,7 +1,7 @@
 {
   "name": "tool-use-schema-writer",
-  "version": "1.0.1",
-  "description": "Takes a function description (name, purpose, parameters) and writes a valid Anthropic tool_use JSON schema, with type annotations, required fields, and a description for each parameter. Produces a Python usage snippet for client.messages.create(tools=[...]). Use when wiring a Claude agent to a function or API, designing tools for a multi-agent system, or documenting an existing tool for agent consumption.",
+  "version": "1.0.2",
+  "description": "Takes a function description (name, purpose, parameters) and writes a valid Anthropic tool_use JSON schema, with type annotations, required fields, and a description for each parameter. Adds a Python client.messages.create(tools=[...]) snippet only when asked. Use when wiring a Claude agent to a function or API, designing tools for a multi-agent system, or documenting an existing tool for agent consumption.",
   "entrypoint": "SKILL.md",
   "deps": { "npm": [], "pip": [] },
   "env": { "required": [], "optional": [] },

package/packs/core/skills/brief-intake/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: brief-intake
-description: Turn raw mess — a Slack thread, meeting transcript, Jira ticket, half-written Notion page, email chain, or paragraph of free-form context — into a structured brief that the downstream skill (adr-generator, design-doc, runbook-generator, exec-summary, deck-builder, tech-comparison-matrix) can consume without further intake. Use whenever the user has unstructured source material and is about to invoke another skilldrop skill, or when a draft is missing the load-bearing context the next step will need.
+description: Turn raw mess — a Slack thread, meeting transcript, Jira ticket, half-written Notion page, email chain, or paragraph of free-form context — into a structured brief that the downstream skill (adr-generator, design-doc, runbook-generator, exec-summary, deck-builder) can consume without further intake. Use whenever the user has unstructured source material and is about to invoke another skilldrop skill, or when a draft is missing the load-bearing context the next step will need.
 ---
 
 # brief-intake
@@ -16,7 +16,7 @@ You help the user (or the next skill in the chain) absorb raw unstructured input
    | `adr-generator` | "ADR", "decision record", "capture a decision", "we decided X" |
    | `design-doc` | "design doc", "tech proposal", "one-pager for review", "RFC" |
    | `runbook-generator` | "runbook", "on-call doc", "operational doc", "prod-readiness" |
-   | `tech-comparison-matrix` | "compare X vs Y", "vendor selection", "tech selection" |
+   | _(tech comparison)_ | "compare X vs Y", "vendor selection", "tech selection" |
    | `exec-summary` | "exec summary", "1-pager for the VP", "board update" |
    | `deck-builder` / `slide-outliner` | "deck", "slides", "presentation", "pitch", "review meeting" |
    | `decision-log` | "decisions and action items", "follow-ups from the meeting" |

package/packs/core/skills/brief-intake/manifest.json

@@ -1,11 +1,11 @@
 {
   "name": "brief-intake",
-  "version": "0.1.1",
-  "description": "Turn raw mess — a Slack thread, meeting transcript, Jira ticket, half-written Notion page, email chain, or paragraph of free-form context — into a structured brief that the downstream skill (adr-generator, design-doc, runbook-generator, exec-summary, deck-builder, tech-comparison-matrix) can consume without further intake. Use whenever the user has unstructured source material and is about to invoke another skilldrop skill, or when a draft is missing the load-bearing context the next step will need.",
+  "version": "0.1.2",
+  "description": "Turn raw mess — a Slack thread, meeting transcript, Jira ticket, half-written Notion page, email chain, or paragraph of free-form context — into a structured brief that the downstream skill (adr-generator, design-doc, runbook-generator, exec-summary, deck-builder) can consume without further intake. Use whenever the user has unstructured source material and is about to invoke another skilldrop skill, or when a draft is missing the load-bearing context the next step will need.",
   "entrypoint": "SKILL.md",
   "deps": { "npm": [], "pip": [] },
   "env": { "required": [], "optional": [] },
-  "related": ["adr-generator", "decision-log", "deck-builder", "design-doc", "exec-summary", "runbook-generator", "slide-outliner", "tech-comparison-matrix"],
+  "related": ["adr-generator", "decision-log", "deck-builder", "design-doc", "exec-summary", "runbook-generator", "slide-outliner"],
   "tags": ["intake", "brief", "extraction", "preprocessing", "pipeline"],
   "model": { "tier": "standard", "rationale": "Extraction + [explicit]/[implied]/[inferred] tagging. The tagging needs care — above haiku, below opus." }
 }

package/packs/core/skills/brief-intake/templates/brief-tech-comparison.md

@@ -1,6 +1,6 @@
 # Brief: Tech Comparison
 
-> Target downstream skill: `tech-comparison-matrix`
+> Target downstream: whoever scores the candidates — the agent in the next turn, or the people making the choice. No dedicated skill.
 
 ## The question
 {One sentence — what's being chosen and what for. e.g. "Pick a primary OLTP datastore for the new checkout service."} [explicit|implied|inferred|missing]

package/packs/core/skills/council-review/SKILL.md

@@ -7,7 +7,7 @@ description: Convene a council of distinct senior-engineer personas (Architect,
 
 You convene a **council of distinct expert personas** to deliberate something consequential, then reconcile their views into a decision. The value is not five voices agreeing — it's **surfacing where senior engineers genuinely disagree, naming the tradeoff at the heart of it, and deciding anyway.**
 
-This is the deliberation counterpart to the single-voice reviewers. Use [`devils-advocate`](../../../dev-team/skills/devils-advocate/SKILL.md) when you want one adversarial pass on code, [`doc-critique`](../doc-critique/SKILL.md) for one pass on a doc, [`tech-comparison-matrix`](../../../solution-architect/skills/tech-comparison-matrix/SKILL.md) for a weighted scoring of named options. Use the **council** when the question is open, the tradeoffs are real, and you need multiple disciplines in the room.
+This is the deliberation counterpart to the single-voice reviewers. Use [`devils-advocate`](../../../dev-team/skills/devils-advocate/SKILL.md) when you want one adversarial pass on code, [`doc-critique`](../doc-critique/SKILL.md) for one pass on a doc. Use the **council** when the question is open, the tradeoffs are real, and you need multiple disciplines in the room.
 
 ## What the council reviews
 
@@ -89,7 +89,7 @@ The **Chair** is not a sixth opinion. The Chair facilitates, finds the cruxes, a
 ## When NOT to use this skill
 
 - ❌ A trivial or one-line change — convening five voices is noise. Use `devils-advocate` or just review it.
-- ❌ A single-lens task. Pure code review → `devils-advocate`. Pure doc review → `doc-critique`. Scoring named options on weighted criteria → `tech-comparison-matrix`.
+- ❌ A single-lens task. Pure code review → `devils-advocate`. Pure doc review → `doc-critique`.
 - ❌ When you need **one** expert answer fast, not a deliberation. The council is for when the disagreement *is* the point.
 - ❌ Greenfield spike/throwaway code — deliberation wastes effort on what won't survive.
 - ❌ As a rubber stamp to manufacture consensus for a decision already made. If the call is final, don't stage a fake trial.

package/packs/core/skills/council-review/manifest.json

@@ -1,11 +1,11 @@
 {
   "name": "council-review",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "Convene a council of distinct senior-engineer personas (Architect, Security, Operator/SRE, Pragmatist, User-Advocate, plus optional bench seats) to deliberate a decision, design, or code change — each takes an independent stance, the genuine disagreements are surfaced as named cruxes, and a Chair issues a reconciled verdict that records dissents and states what would change the decision. The \"Claude Council.\" Use when a choice has real tradeoffs and one reviewer's voice isn't enough: architecture decisions, risky changes before merge, RFC/design scrutiny, \"should we adopt X?\", rewrite-vs-refactor, or a pre-mortem.",
   "entrypoint": "SKILL.md",
   "deps": { "npm": [], "pip": [] },
   "env": { "required": [], "optional": [] },
-  "related": ["devils-advocate", "doc-critique", "tech-comparison-matrix"],
+  "related": ["devils-advocate", "doc-critique"],
   "tags": ["review", "deliberation", "council", "decision", "architecture", "pre-mortem", "multi-perspective", "dev-workflow"],
   "model": { "tier": "heavy", "rationale": "Multi-perspective deliberation + weighted reconciliation. Cheaper models collapse the seats into one voice and manufacture or miss the real cruxes. Never downgrade." }
 }

package/packs/core/skills/council-review/reference.md

@@ -70,7 +70,6 @@ When two seats genuinely converge, that's a *stronger* signal — present it as
 The council is heavier than the focused reviewers — use it when the multi-disciplinary tension is the point, not as a default. Rules of thumb:
 - One adversarial pass on just-written code → [`devils-advocate`](../../../dev-team/skills/devils-advocate/SKILL.md).
 - One rubric pass on a doc → [`doc-critique`](../doc-critique/SKILL.md).
-- Score named options on weighted criteria → [`tech-comparison-matrix`](../../../solution-architect/skills/tech-comparison-matrix/SKILL.md).
 - A decision/design/change where security, ops, maintainability, delivery, and correctness pull in different directions → **council-review**.
 
 Don't chain these internally (per the repo's no-internal-chaining rule). A human runs the council, then hands a specific finding to `devils-advocate` if they want it drilled.

package/packs/core/skills/doc-critique/SKILL.md

@@ -104,7 +104,7 @@ You help the user review an existing document with the same opinionated rubric t
 
 ## When NOT to use this skill
 
-- ❌ For evaluating the *underlying decision* (is Postgres the right choice?). That's a tech-debate, not a doc review — use `tech-comparison-matrix` instead.
+- ❌ For evaluating the *underlying decision* (is Postgres the right choice?). That's a tech debate, not a doc review — argue the decision itself, or put it to `council-review`.
 - ❌ For grammar / spelling pass on a doc that's otherwise solid. Use a normal editor.
 - ❌ For evaluating code. This skill reviews *documents*; for code review, the user has other tools.
 - ❌ For generating the doc. If the user wants a draft, that's the matching generator skill.

package/packs/core/skills/doc-critique/manifest.json

@@ -1,11 +1,11 @@
 {
   "name": "doc-critique",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "Review an existing document — ADR, design doc, runbook, exec summary, tech-comparison matrix, deck outline, decision log — and produce a structured critique against the same quality bars the skilldrop generators enforce. Categorizes findings by severity (blocker / major / minor / nit), points to the exact section/line, and suggests a concrete fix for each. Use when the user wants a second-pair-of-eyes review before sharing a doc, or has been handed someone else's artifact and wants to know what to push back on.",
   "entrypoint": "SKILL.md",
   "deps": { "npm": [], "pip": [] },
   "env": { "required": [], "optional": [] },
-  "related": ["decision-log", "tech-comparison-matrix"],
+  "related": ["council-review", "decision-log"],
   "tags": ["review", "critique", "quality", "rubric", "feedback"],
   "model": { "tier": "heavy", "rationale": "Adversarial doc review against rubrics. The value is catching what a fast pass misses. Never downgrade." }
 }

package/packs/core/skills/doc-critique/rubrics/tech-comparison.md

@@ -1,6 +1,6 @@
 # Rubric: Tech-Comparison Matrix
 
-Mirrors `tech-comparison-matrix`'s quality bar.
+For any weighted comparison of named options: a vendor selection, a datastore pick, a build-vs-buy matrix.
 
 ## Blockers
 - **The question is one sentence and answerable.** ❌ *"Database options"* ✅ *"Pick a primary OLTP datastore for the new checkout service."*