skilldrop-cli 0.13.7 → 0.13.8

package/packs/dev-team/pack.json

@@ -18,5 +18,39 @@
     "verification": "pre-merge-review runs the project's lint, typecheck and tests through its gate script, then the reviewer panel, and ends with READY or NOT READY.",
     "recovery": "If the gate script cannot find your lint or test commands, tell it what they are. If the panel is skipped, install the reviewer subagents with `skilldrop install --panel review`."
   },
-  "requires": ["core"]
+  "requires": ["core"],
+  "journey": {
+    "when": "You have an agreed requirement or a triaged bug and want it implemented, verified and ready to merge.",
+    "you_bring": [
+      "the epic, story or bug report",
+      "a repo with working lint, typecheck and test commands",
+      "who owns the merge"
+    ],
+    "steps": [
+      {
+        "skill": "user-story-splitter",
+        "you_do": "Paste the epic or feature request (use bug-triage instead for a defect).",
+        "you_get": "Independently shippable stories with Gherkin acceptance criteria and a recommended build order.",
+        "decide": "Pick the one slice to build now; criteria a test cannot assert send it back to be reshaped."
+      },
+      {
+        "skill": "feature-implement-loop",
+        "you_do": "Hand it the slice and its acceptance criteria.",
+        "you_get": "Code and tests, reviewed for edge cases, security and craft for up to three rounds, with a status (VERIFIED, VERIFIED WITH OPEN ITEMS or BLOCKED), a criteria-to-test table and a round log."
+      },
+      {
+        "skill": "pre-merge-review",
+        "you_do": "Ask whether the current diff is safe to merge.",
+        "you_get": "The gate script's lint, typecheck and test result, then findings from the correctness, security and code-quality reviewers, ending in one verdict.",
+        "decide": "Gate G2 is the script's exit code: READY moves on; NOT READY goes back to implementation, at most three times before BLOCKED."
+      },
+      {
+        "skill": "council-review",
+        "you_do": "Only if the review surfaced a design disagreement, put it to the panel.",
+        "you_get": "Independent positions, the named cruxes, and a Chair's verdict with dissent recorded.",
+        "decide": "Gate G2.1: a human merges. SPLIT and RECONSIDER leave the loop rather than revising in the diff."
+      }
+    ],
+    "you_end_with": "A shaped story, verified code and tests, a READY verdict with the review findings, and a human merge decision."
+  }
 }

package/packs/dev-team/skills/accessibility-audit/evals/eval_queries.json

@@ -0,0 +1,30 @@
+[
+  {
+    "query": "Run an a11y audit on this signup page markup",
+    "should_trigger": true
+  },
+  {
+    "query": "Is this component WCAG 2.2 AA compliant? Find what blocks screen-reader users",
+    "should_trigger": true
+  },
+  {
+    "query": "Here's a screenshot of our dashboard — what accessibility issues can you spot before we build it?",
+    "should_trigger": true
+  },
+  {
+    "query": "We failed an accessibility review; check this modal for keyboard traps and focus problems",
+    "should_trigger": true
+  },
+  {
+    "query": "What WCAG level should our new product commit to, and on which scope?",
+    "should_trigger": false
+  },
+  {
+    "query": "Review this PR for correctness bugs and edge cases",
+    "should_trigger": false
+  },
+  {
+    "query": "Implement this date-picker story with tests until the acceptance criteria pass",
+    "should_trigger": false
+  }
+]

package/packs/dev-team/skills/accessibility-audit/evals/evals.json

@@ -0,0 +1,19 @@
+{
+  "skill_name": "accessibility-audit",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Audit this checkout form component before we ship:\n\n<form>\n  <div class=\"title\">Payment</div>\n  <input placeholder=\"Card number\" style=\"color:#999;background:#fff\">\n  <input placeholder=\"Expiry\">\n  <span class=\"err\" style=\"color:red\">Invalid</span>\n  <img src=\"lock.svg\" alt=\"image\">\n  <div class=\"btn\" onclick=\"submit()\" style=\"width:20px;height:20px\">Pay</div>\n</form>\n\nTarget is WCAG 2.2 AA.",
+      "assertions": [
+        "Opens with a coverage note stating what markup alone can and cannot verify (e.g. actual screen-reader output, live focus order)",
+        "Every finding cites a specific success criterion with number, name, and level (e.g. 2.1.1 Keyboard [A], 4.1.2 Name, Role, Value [A])",
+        "Every finding names the user group and assistive tech it blocks (e.g. keyboard-only, NVDA/VoiceOver users)",
+        "The div-as-button is a blocker for keyboard and screen-reader users; minor issues like the lock icon's alt text are not inflated to blocker",
+        "Contrast for #999 on #fff is given as a computed ratio (about 2.85:1) against the 4.5:1 threshold, and the 20x20 target is checked against 2.5.8's 24x24 minimum",
+        "Each finding is tagged [auto] or [manual] and has a concrete fix",
+        "Ends with a 'what's solid' section and a must-verify-with-live-AT checklist",
+        "Does not claim a pass on any behavior the markup can't show, and does not invent elements not in the snippet"
+      ]
+    }
+  ]
+}

package/packs/dev-team/skills/contribution-wizard/evals/eval_queries.json

@@ -0,0 +1,30 @@
+[
+  {
+    "query": "Help me create a new skilldrop skill from scratch",
+    "should_trigger": true
+  },
+  {
+    "query": "Generate the manifest, SKILL.md, and evals for a skill I want to contribute",
+    "should_trigger": true
+  },
+  {
+    "query": "I have an idea for a skill in the dev-team pack — walk me through authoring it",
+    "should_trigger": true
+  },
+  {
+    "query": "Scaffold a new skill for our private fork so it passes validate.py",
+    "should_trigger": true
+  },
+  {
+    "query": "I edited the bug-triage SKILL.md — regenerate its eval cases",
+    "should_trigger": false
+  },
+  {
+    "query": "Add more eval coverage to an existing skill's evals folder",
+    "should_trigger": false
+  },
+  {
+    "query": "Generate an AGENTS.md for this repository",
+    "should_trigger": false
+  }
+]

package/packs/dev-team/skills/contribution-wizard/evals/evals.json

@@ -0,0 +1,19 @@
+{
+  "skill_name": "contribution-wizard",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "I want to add a new skill to skilldrop called `sla-credit-calculator`. It takes a customer contract's SLA terms plus a month of uptime data and outputs the service credit owed, with the calculation shown. It belongs in the sre-oncall pack, it generates an artifact (not a gate), it relates to runbook-generator and incident-comms, and it needs no external deps. Generate everything I need to submit it.",
+      "assertions": [
+        "Produces manifest.json, SKILL.md, evals/cases.json, and a skill-catalogue row, each in its own fenced code block, in a single response",
+        "The manifest includes every required field (name, version, description, entrypoint, deps, env, related, tags, model with tier and rationale)",
+        "The related array lists only skills that exist (runbook-generator, incident-comms) and tells the author to check the skills directory before finalizing",
+        "SKILL.md's How to respond steps are observable actions — none read 'think about X' or 'consider Y'",
+        "The quality bar names at least two things the output must never do (e.g. never invent uptime figures not in the input)",
+        "evals/cases.json has eight cases with realistic triggers, covering happy-path, edge, anti-pattern, and boundary cases",
+        "Ends with next steps that place files under packs/sre-oncall/skills/sla-credit-calculator/ and require python3 validate.py to pass before opening a PR",
+        "Does not invent inputs, deps, or related skills the author did not give"
+      ]
+    }
+  ]
+}

package/packs/dev-team/skills/feature-implement-loop/evals/eval_queries.json

@@ -0,0 +1,30 @@
+[
+  {
+    "query": "Implement this ticket and make sure every acceptance criterion actually has a test",
+    "should_trigger": true
+  },
+  {
+    "query": "Build this story, review your own code adversarially, and fix the gaps",
+    "should_trigger": true
+  },
+  {
+    "query": "Here's a feature spec with acceptance criteria — give me shippable, self-checked code",
+    "should_trigger": true
+  },
+  {
+    "query": "Implement the password-reset flow per these criteria and loop until the review is clean",
+    "should_trigger": true
+  },
+  {
+    "query": "Review this PR I wrote for edge cases and broken assumptions",
+    "should_trigger": false
+  },
+  {
+    "query": "Should we use Postgres or DynamoDB for the new service? Write it up for review",
+    "should_trigger": false
+  },
+  {
+    "query": "Run the pre-merge gate on my branch before I open the PR",
+    "should_trigger": false
+  }
+]

package/packs/dev-team/skills/feature-implement-loop/evals/evals.json

@@ -0,0 +1,19 @@
+{
+  "skill_name": "feature-implement-loop",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Implement this story in our Python/FastAPI service (pytest, ruff, mypy already set up):\n\nAs an admin, I can export the audit log for a date range as CSV.\nAcceptance criteria:\n1. GET /admin/audit/export?from=YYYY-MM-DD&to=YYYY-MM-DD returns text/csv.\n2. Non-admins get 403.\n3. from after to returns 400 with a clear message.\n4. Ranges over 90 days return 400.\n5. The CSV opens cleanly in Excel.\n\nBuild it and check your own work.",
+      "assertions": [
+        "Restates the five acceptance criteria as a numbered checklist before writing code",
+        "Plans a named test per criterion up front and flags criterion 5 (opens cleanly in Excel) as manual-verify",
+        "Runs the project's tests plus ruff and mypy, and does not report VERIFIED while any command is red",
+        "Review findings are tagged blocker/major/minor/nit with file:line and a concrete fix, covering edge cases, security (e.g. authz on the admin route, CSV formula injection), and craft",
+        "Tests assert the criterion's expected output (status codes, content type, messages), not just that the call didn't throw",
+        "Stops at or before 3 rounds, and later rounds patch only the named gaps rather than regenerating the whole feature",
+        "Final report has a status (VERIFIED, VERIFIED WITH OPEN ITEMS, or BLOCKED), an acceptance-criteria table mapping each criterion to a test, manual-verify, or open item, an honest round log, and open items",
+        "Does not add criteria the user did not give without echoing them back first"
+      ]
+    }
+  ]
+}

package/packs/dev-team/skills/release-notes/evals/eval_queries.json

@@ -0,0 +1,30 @@
+[
+  {
+    "query": "Write release notes for everything since the last tag",
+    "should_trigger": true
+  },
+  {
+    "query": "Update CHANGELOG.md for v3.1 from the git history",
+    "should_trigger": true
+  },
+  {
+    "query": "What's in this release? Turn v1.8.0..v1.9.0 into customer-facing notes",
+    "should_trigger": true
+  },
+  {
+    "query": "Draft a deploy announcement for internal stakeholders from these merged PRs",
+    "should_trigger": true
+  },
+  {
+    "query": "Review the changes in this release for risk before we ship",
+    "should_trigger": false
+  },
+  {
+    "query": "Write a one-page summary for the board on why this release matters strategically",
+    "should_trigger": false
+  },
+  {
+    "query": "Run a Sonar quality review on the code merged this sprint",
+    "should_trigger": false
+  }
+]

package/packs/dev-team/skills/release-notes/evals/evals.json

@@ -0,0 +1,19 @@
+{
+  "skill_name": "release-notes",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Write release notes for v2.4.0 from this log (range v2.3.0..HEAD, 2026-08-12 to 2026-09-28):\n\na1b2c3d|feat: bulk CSV import for contacts (#412)\ne4f5a6b|fix: NPE in ReportExporter.flush() when >10k rows (#418)\nc7d8e9f|feat!: remove legacy /v1/contacts endpoint (#420)\n0a1b2c3|chore(deps): bump lodash 4.17.20 -> 4.17.21\n4d5e6f7|refactor: extract ExportService\n8a9b0c1|fix stuff\n2d3e4f5|perf: cache tenant settings, report export ~3x faster (#425)",
+      "assertions": [
+        "States the range, commit count (7), and date span at the top",
+        "The removal of /v1/contacts is hoisted to the top of both artifacts with an 'Action required' line and names the !: marker that flagged it",
+        "Customer notes contain no commit-speak — no ReportExporter.flush(), class names, ticket numbers, or author names",
+        "The lodash bump and the ExportService refactor appear only in the internal changelog, never in customer notes, not even as 'various improvements'",
+        "Every internal changelog line ends with its short hash, plus PR number where present",
+        "The vague 'fix stuff' commit (8a9b0c1) goes in the Needs review list with its hash, not guessed into customer notes",
+        "No marketing adjectives; the performance line states the measured change (~3x faster export) rather than 'blazing fast'",
+        "Does not invent features or fixes not present in the log"
+      ]
+    }
+  ]
+}

package/packs/product-manager/pack.json

@@ -18,5 +18,44 @@
     "verification": "prfaq returns a launch press release, a customer FAQ and an internal FAQ that names the hard questions.",
     "recovery": "If prfaq does not activate, ask for it by name (\"use prfaq\") and check that its folder exists in your skills folder (`~/.claude/skills/` by default)."
   },
-  "requires": ["core"]
+  "requires": ["core"],
+  "journey": {
+    "when": "You are deciding what to build and need a requirement a human has agreed to before design starts.",
+    "you_bring": [
+      "the feature idea or problem and who it is for",
+      "the stakeholders you can talk to",
+      "interview notes or evidence you already have"
+    ],
+    "time": "1–2 hours of working time, plus the interviews themselves",
+    "steps": [
+      {
+        "skill": "requirements-interview",
+        "you_do": "Describe the feature idea and list the stakeholders.",
+        "you_get": "An interview kit per stakeholder with up to seven questions ranked by how much the answer changes the design, at least one disconfirming question each, and an assumptions ledger."
+      },
+      {
+        "skill": "brief-intake",
+        "you_do": "Paste the interview notes once you have run the interviews.",
+        "you_get": "One brief with every field tagged explicit, implied, inferred or missing, quoting the source.",
+        "decide": "Resolve the missing fields yourself; the PRD must not invent them."
+      },
+      {
+        "skill": "prd-draft",
+        "you_do": "Hand it the resolved brief.",
+        "you_get": "A PRD with an evidence-backed problem statement, numbered MoSCoW requirements, non-goals, and a success line per goal."
+      },
+      {
+        "skill": "doc-critique",
+        "you_do": "Run it on the PRD, then take the result to whoever owns the decision.",
+        "you_get": "A severity-tagged critique of the PRD with a verdict and a fix for each finding.",
+        "decide": "Gate G0, a human call: PROCEED, PROCEED WITH CONDITIONS, REVISE (back to the brief), RECONSIDER (wrong problem) or BLOCKED."
+      },
+      {
+        "skill": "success-metrics",
+        "you_do": "Once the PRD is ratified, ask how you will know the feature worked.",
+        "you_get": "One primary metric with baseline, target and timeframe, guardrail metrics, the events to instrument, and a decision rule if the target is missed."
+      }
+    ],
+    "you_end_with": "Interview kits, a tagged brief, a ratified PRD, and a measurement plan agreed before anyone builds."
+  }
 }

package/packs/product-manager/skills/business-case/evals/eval_queries.json

@@ -0,0 +1,30 @@
+[
+  {
+    "query": "Write the business case for building our own feature-flag service versus buying one",
+    "should_trigger": true
+  },
+  {
+    "query": "Should we invest two engineer-quarters in rebuilding search? I need something to take to the sponsor",
+    "should_trigger": true
+  },
+  {
+    "query": "Compare build vs buy vs defer for the new data pipeline, with the cost of doing nothing priced",
+    "should_trigger": true
+  },
+  {
+    "query": "I need budget approval for an observability overhaul — help me justify the spend",
+    "should_trigger": true
+  },
+  {
+    "query": "The investment's approved — now write the PRD for the ML router",
+    "should_trigger": false
+  },
+  {
+    "query": "Pick between Kafka, Kinesis, and Pub/Sub for the approved event bus",
+    "should_trigger": false
+  },
+  {
+    "query": "Compress this 12-page business case into a one-page summary for the board",
+    "should_trigger": false
+  }
+]

package/packs/product-manager/skills/business-case/evals/evals.json

@@ -0,0 +1,19 @@
+{
+  "skill_name": "business-case",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Write the business case for replacing our homegrown support ticket router at Northwind. Today 40 agents each spend about 20 minutes a day manually re-routing misassigned tickets (from a two-week time study). Loaded agent cost is $45/hour. Options on the table: build a ML router (estimate 3 engineers for 2 quarters), buy a vendor tool (Vendor X quoted $60k/year, year-two price unknown), or keep things as they are. The same 3 engineers would otherwise ship the self-serve billing portal. The VP of Support decides by November 15.",
+      "assertions": [
+        "The first lines state the ask — option, cost, benefit range, and the November 15 deadline — in under 40 words",
+        "Option 0 (do nothing) is present and costed using the user's 40 agents x 20 min/day x $45/hour figures",
+        "Every benefit is a re-runnable calculation with formula, sourced inputs, and a confidence tag (high/medium/low)",
+        "Outputs such as ROI and payback are ranges with a stated lean, not single-point figures like '327% ROI'",
+        "Each option shows build, run, and opportunity cost, with the displaced work named as the self-serve billing portal",
+        "The vendor's unknown year-two price is called out as an unknown or flagged assumption, not filled with an invented number",
+        "Names the flip-assumption that would reverse the recommendation, with a de-risking step if its confidence is low",
+        "Recommends exactly one option and states the runner-up's strongest argument fairly"
+      ]
+    }
+  ]
+}

package/packs/solution-architect/pack.json

@@ -18,5 +18,48 @@
     "verification": "adr-generator returns an ADR with context, the options considered with their trade-offs, the decision, and its consequences.",
     "recovery": "If adr-generator does not activate, ask for it by name (\"use adr-generator\") and check that its folder exists in your skills folder (`~/.claude/skills/` by default)."
   },
-  "requires": ["core"]
+  "requires": ["core"],
+  "journey": {
+    "when": "You have an agreed requirement and need to decide how to build it, then record that decision.",
+    "you_bring": [
+      "the ratified requirement or PRD",
+      "known constraints: traffic, data, compliance, existing systems",
+      "the options you are weighing, if you already have them"
+    ],
+    "time": "1–3 hours",
+    "steps": [
+      {
+        "skill": "nfr-spec",
+        "you_do": "Describe the feature or system and what you know about load, data and users.",
+        "you_get": "Every non-functional category set to a measurable target, an explicit n/a, or a tagged default."
+      },
+      {
+        "skill": "design-doc",
+        "you_do": "Give it the requirement and the NFR targets.",
+        "you_get": "A design doc with problem, goals and non-goals, options considered, the recommended approach, risks and rollout."
+      },
+      {
+        "skill": "architecture-diagrams",
+        "you_do": "Ask for diagrams of the recommended approach from the design doc.",
+        "you_get": "Mermaid, PlantUML or C4 diagrams that must agree with the doc."
+      },
+      {
+        "skill": "threat-model",
+        "you_do": "Hand it the design doc and diagrams.",
+        "you_get": "A STRIDE threat model with assets and trust boundaries, attack scenarios at each boundary crossing, and ranked, verifiable mitigations."
+      },
+      {
+        "skill": "council-review",
+        "you_do": "Put the design and threat model in front of the review panel.",
+        "you_get": "Independent positions from each seat, the named cruxes, and a Chair's verdict that records dissent and what would change the decision.",
+        "decide": "Gate G1: PROCEED or PROCEED WITH CONDITIONS moves on; REVISE sends you back to the design doc; SPLIT or RECONSIDER leaves the loop."
+      },
+      {
+        "skill": "adr-generator",
+        "you_do": "Ask for the ADR once the panel has agreed, including any conditions it set.",
+        "you_get": "An ADR in MADR or Nygard format with context, the options and why each was rejected, the decision and its consequences."
+      }
+    ],
+    "you_end_with": "NFR targets, a design doc with matching diagrams, a threat model, the panel's verdict, and an ADR that carries its conditions."
+  }
 }

package/packs/solution-architect/skills/tech-comparison-matrix/evals/eval_queries.json

@@ -0,0 +1,30 @@
+[
+  {
+    "query": "Postgres vs DynamoDB for our multi-tenant OLTP store — build me a weighted matrix",
+    "should_trigger": true
+  },
+  {
+    "query": "We're choosing between Snowflake and Databricks; score them against our criteria",
+    "should_trigger": true
+  },
+  {
+    "query": "Compare three observability vendors and recommend one for our team",
+    "should_trigger": true
+  },
+  {
+    "query": "Which frontend framework should we pick — React, Vue, or Svelte — for this app? Show the scoring",
+    "should_trigger": true
+  },
+  {
+    "query": "Write the business case for whether to invest in a data platform at all",
+    "should_trigger": false
+  },
+  {
+    "query": "Record the decision to adopt Kafka as an architecture decision record",
+    "should_trigger": false
+  },
+  {
+    "query": "Write a design doc proposing the new event-driven architecture for review",
+    "should_trigger": false
+  }
+]

package/packs/solution-architect/skills/tech-comparison-matrix/evals/evals.json

@@ -0,0 +1,18 @@
+{
+  "skill_name": "tech-comparison-matrix",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Help us pick a message broker: Kafka (self-managed), Amazon Kinesis, or RabbitMQ. Use case: order-event streaming for a multi-tenant SaaS app at Acme, about 5k events/sec at peak, consumers need replay for up to 7 days, ordering per tenant matters. Hard constraints: we run on AWS, and the platform team is two people with no capacity to run self-hosted clusters on call.",
+      "assertions": [
+        "Uses 8 to 10 criteria spanning capability fit, operational, cost, and risk, and names any criteria deliberately excluded",
+        "Shows a 1-5 weight for every criterion with the weight tied in writing to the use case or constraints (e.g. operational burden weighted high because the platform team is two people)",
+        "Every score has a one-line justification, and every 5 and every 1 is explained",
+        "Totals are computed as sum(weight x score), and a gap under 5% between the top options is called out",
+        "Ties are allowed where options genuinely don't differ; scores are not uniformly 3/5",
+        "The recommendation is one sentence and says what would change the answer; if it isn't the top scorer, the override is explained",
+        "Numbers that are estimates are marked 'rough' or 'directional'; no benchmarks are invented beyond the figures in the prompt"
+      ]
+    }
+  ]
+}

package/packs/sre-oncall/pack.json

@@ -18,5 +18,37 @@
     "verification": "runbook-generator returns a runbook with rollback commands, the common incidents and what to do for each, and an escalation path. Facts you did not give it are marked missing, not invented.",
     "recovery": "If runbook-generator does not activate, ask for it by name (\"use runbook-generator\") and check that its folder exists in your skills folder (`~/.claude/skills/` by default)."
   },
-  "requires": ["core"]
+  "requires": ["core"],
+  "journey": {
+    "when": "You are getting a service ready to run, handling an incident, or writing it up afterwards; you can join at whichever stage you are in.",
+    "you_bring": [
+      "the service: what it does, where it runs, what it depends on, who gets paged",
+      "during or after an incident: the timeline, the Slack thread or pager log, and the known impact",
+      "facts only; the skills mark anything you leave out as missing rather than guessing it"
+    ],
+    "steps": [
+      {
+        "skill": "observability-plan",
+        "you_do": "Describe the service and its main user journeys.",
+        "you_get": "SLIs and SLOs with error budgets, burn-rate alerts split into page and ticket, and a metrics, logs and traces plan with a cardinality and cost budget."
+      },
+      {
+        "skill": "runbook-generator",
+        "you_do": "Give it the service details and the alerts from the plan.",
+        "you_get": "A runbook with deploy and rollback steps, what to do for each common incident, escalation, SLOs, dashboards and dependencies, with unknown facts marked missing."
+      },
+      {
+        "skill": "incident-comms",
+        "you_do": "During an incident, say what users are seeing and what stage you are in (detect, mitigate or resolve).",
+        "you_get": "Separate updates for the status page, internal stakeholders and execs, each leading with user impact and naming the next update time, with no guessed cause or ETA."
+      },
+      {
+        "skill": "postmortem-generator",
+        "you_do": "Paste the incident thread, pager timeline and notes once it is over.",
+        "you_get": "A blameless postmortem with quantified impact, a UTC timeline showing detection and mitigation gaps, contributing factors, up to eight action items, and runbook deltas phrased as edits.",
+        "decide": "Gate G3, a human call: PROCEED closes it, PROCEED WITH CONDITIONS closes it with named follow-ups, REVISE sends the deltas back to the runbook."
+      }
+    ],
+    "you_end_with": "An observability plan, a runbook tied to its alerts, the incident updates you sent, and a postmortem whose deltas go back into the runbook."
+  }
 }

package/packs/sre-oncall/skills/capacity-cost-model/evals/eval_queries.json

@@ -0,0 +1,30 @@
+[
+  {
+    "query": "What will this service cost to run at 10x our current tenants?",
+    "should_trigger": true
+  },
+  {
+    "query": "Size capacity and estimate the AWS bill for our launch next quarter",
+    "should_trigger": true
+  },
+  {
+    "query": "Our cloud bill jumped — model what's driving it and where the next cliff is",
+    "should_trigger": true
+  },
+  {
+    "query": "Build a cost-per-request model for the new ingestion pipeline",
+    "should_trigger": true
+  },
+  {
+    "query": "Should we build or buy a search platform? Write the business case",
+    "should_trigger": false
+  },
+  {
+    "query": "Set the latency and availability targets for the search service",
+    "should_trigger": false
+  },
+  {
+    "query": "Plan the cutover sequence for moving search from Elasticsearch to OpenSearch",
+    "should_trigger": false
+  }
+]

package/packs/sre-oncall/skills/capacity-cost-model/evals/evals.json

@@ -0,0 +1,19 @@
+{
+  "skill_name": "capacity-cost-model",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Model the run cost for our new document-search service at Northwind on AWS. Demand: 1,200 active tenants today, growing about 8% a month; average 15 searches/sec, peak 60/sec weekday mornings. Each tenant indexes about 2 GB. We'll use OpenSearch, ECS Fargate for the API, and CloudWatch for logs. There are dev and staging environments too. What will it cost now and at 3x and 10x?",
+      "assertions": [
+        "Sizes from the demand driver (tenants and searches/sec, with the 8%/month growth curve), not from a chosen instance count",
+        "Every cost line is a unit price x quantity, with the unit price's source and date tagged",
+        "Expresses unit economics (e.g. cost per active tenant per month), not just a bare monthly total",
+        "Egress, observability (CloudWatch logs), and non-prod (dev and staging) lines are present or explicitly marked n/a",
+        "States average and peak load separately and makes the headroom/target-utilization choice explicit with reasoning",
+        "Projects 1x/3x/10x and names at least one scaling cliff (e.g. an OpenSearch tier or shard step) rather than extrapolating linearly",
+        "Outputs are low/expected/high ranges with a lean, and the cost-per-tenant trend at scale is checked and flagged if it rises",
+        "Does not invent demand figures or services beyond those in the prompt; unknown inputs are stated as assumptions"
+      ]
+    }
+  ]
+}

package/packs/stakeholder-comms/pack.json

@@ -18,5 +18,43 @@
     "verification": "exec-summary returns a one-page summary that a time-poor reader can act on in 30 seconds, written without jargon.",
     "recovery": "If exec-summary does not activate, ask for it by name (\"use exec-summary\") and check that its folder exists in your skills folder (`~/.claude/skills/` by default)."
   },
-  "requires": ["core"]
+  "requires": ["core"],
+  "journey": {
+    "when": "You need to turn a long document or a meeting into something a non-technical or time-poor audience can act on.",
+    "you_bring": [
+      "the long document, such as a design doc or proposal",
+      "notes or a transcript from the meeting where it was discussed",
+      "who the audience is, such as a steering committee or an exec sponsor"
+    ],
+    "time": "30–60 minutes",
+    "steps": [
+      {
+        "skill": "decision-log",
+        "you_do": "Paste the meeting notes, thread or transcript.",
+        "you_get": "A structured log of decisions, action items, owners and due dates you can paste into a doc or tracker."
+      },
+      {
+        "skill": "audience-profile",
+        "you_do": "Say who will read it, in your own words.",
+        "you_get": "The audience archetype with its rules: length, density, tone, must-have sections and things to never include."
+      },
+      {
+        "skill": "exec-summary",
+        "you_do": "Hand it the long document, the decisions, and the audience profile.",
+        "you_get": "A one-page summary a time-poor reader can act on in 30 seconds, without jargon."
+      },
+      {
+        "skill": "doc-critique",
+        "you_do": "Run it on the summary before it goes out.",
+        "you_get": "A verdict and severity-tagged findings, such as a missing Ask, each with a suggested fix.",
+        "decide": "Ship, ship with the listed changes, or rewrite."
+      },
+      {
+        "skill": "output-hygiene",
+        "you_do": "Run it on the final version.",
+        "you_get": "The text with machine artifacts stripped and any prose tells quoted with rewrites."
+      }
+    ],
+    "you_end_with": "A decision log with owners and dates, and a reviewed one-page summary ready to send."
+  }
 }

package/packs/stakeholder-comms/skills/guide-builder/evals/eval_queries.json

@@ -0,0 +1,34 @@
+[
+  {
+    "query": "Write setup instructions for getting our service running locally from these notes",
+    "should_trigger": true
+  },
+  {
+    "query": "Turn this architecture description into an onboarding walkthrough for new engineers",
+    "should_trigger": true
+  },
+  {
+    "query": "Document these webhook events and payloads for the developers who'll consume them",
+    "should_trigger": true
+  },
+  {
+    "query": "Make a quickstart guide out of this messy README",
+    "should_trigger": true
+  },
+  {
+    "query": "Write the on-call runbook with escalation and rollback for the billing service",
+    "should_trigger": false
+  },
+  {
+    "query": "Draft a design proposal with options and trade-offs for the new billing architecture",
+    "should_trigger": false
+  },
+  {
+    "query": "Summarize this 20-page spec for the executive team",
+    "should_trigger": false
+  },
+  {
+    "query": "Here's a raw Slack thread — structure it into a brief first",
+    "should_trigger": false
+  }
+]

package/packs/stakeholder-comms/skills/guide-builder/evals/evals.json

@@ -0,0 +1,18 @@
+{
+  "skill_name": "guide-builder",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Turn these notes into a guide for new engineers getting our Acme billing service running locally:\n\n- need docker + node 20\n- clone acme/billing, cp .env.example .env, set STRIPE_KEY to a test key\n- docker compose up -d postgres\n- npm ci then npm run migrate\n- npm run dev, it listens on 4000\n- if migrate fails it's usually postgres not up yet",
+      "assertions": [
+        "States the detected style (setup guide) up front with a one-line why and an invitation to redirect",
+        "Prerequisites are listed before the first step, and placeholders like <YOUR_STRIPE_TEST_KEY> are unmistakable and listed once up front",
+        "Each numbered step contains one action — 'npm ci then npm run migrate' is split into separate steps",
+        "Every command block is complete, paste-able, and followed by an expected result or verification (e.g. the service answers on port 4000)",
+        "Leads with the outcome rather than backstory, and pushes troubleshooting (migrate failing because postgres isn't up) to the end",
+        "No forward references that break top-to-bottom reading",
+        "Missing facts (e.g. the repo URL host or how to get a Stripe test key) are flagged as NEEDS INPUT rather than invented"
+      ]
+    }
+  ]
+}