skilldrop-cli 0.9.0 → 0.9.1

package/skills/db-schema-design/evals/eval_queries.json

@@ -0,0 +1,34 @@
+[
+  {
+    "query": "Design the database schema for this feature",
+    "should_trigger": true
+  },
+  {
+    "query": "What tables, keys, and indexes do I need for these queries?",
+    "should_trigger": true
+  },
+  {
+    "query": "Should this be relational or document, given our access patterns?",
+    "should_trigger": true
+  },
+  {
+    "query": "Model the data layer for this access pattern list",
+    "should_trigger": true
+  },
+  {
+    "query": "Write a data contract for the table our consumers read",
+    "should_trigger": false
+  },
+  {
+    "query": "Draft the OpenAPI contract for the service",
+    "should_trigger": false
+  },
+  {
+    "query": "Diagram our system architecture",
+    "should_trigger": false
+  },
+  {
+    "query": "Plan the migration from the old schema",
+    "should_trigger": false
+  }
+]

package/skills/db-schema-design/evals/evals.json

@@ -0,0 +1,16 @@
+{
+  "skill_name": "db-schema-design",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Design the schema for an order-history feature. Queries: fetch one order by id, list a customer's orders newest-first, and report daily totals by region.",
+      "assertions": [
+        "Access patterns are listed before the schema, with frequency and selectivity",
+        "The paradigm choice is justified against those access patterns — relational-by-default needs no defence, every move past it does",
+        "Keys and partitioning are justified by the actual queries; a random UUIDv4 clustered primary key is not used without a stated reason",
+        "Every index maps to a real predicate from the listed queries rather than being speculative",
+        "Denormalization, where proposed, names the read it serves and the write cost it adds"
+      ]
+    }
+  ]
+}

package/skills/decision-log/evals/eval_queries.json

@@ -0,0 +1,34 @@
+[
+  {
+    "query": "Extract the decisions and action items from these meeting notes",
+    "should_trigger": true
+  },
+  {
+    "query": "Turn this Slack thread into a decision log with owners and due dates",
+    "should_trigger": true
+  },
+  {
+    "query": "What did we actually decide in this transcript, and who owns what?",
+    "should_trigger": true
+  },
+  {
+    "query": "Give me a structured log of decisions from this design review",
+    "should_trigger": true
+  },
+  {
+    "query": "Write an ADR for the decision we made",
+    "should_trigger": false
+  },
+  {
+    "query": "Summarize this meeting for executives",
+    "should_trigger": false
+  },
+  {
+    "query": "Draft the design doc for what we agreed",
+    "should_trigger": false
+  },
+  {
+    "query": "Critique the quality of this decision log",
+    "should_trigger": false
+  }
+]

package/skills/decision-log/evals/evals.json

@@ -0,0 +1,17 @@
+{
+  "skill_name": "decision-log",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Pull the decisions and action items out of this design-review transcript. [transcript: mixed opinions, a couple of agreed decisions, some unowned follow-ups, and relative dates like 'next Friday']",
+      "assertions": [
+        "Opinions are not promoted to decisions — only items the group acknowledged appear as decisions",
+        "Ownership is never invented; items with no named owner are flagged unowned rather than assigned",
+        "The source column quotes the discussion verbatim in a short snippet, not a paraphrase",
+        "Action items are written in active voice",
+        "Relative dates are converted to absolute dates, marked when inferred",
+        "The output is a structured table the user can paste into a doc or tracker"
+      ]
+    }
+  ]
+}

package/skills/deck-builder/evals/eval_queries.json

@@ -0,0 +1,34 @@
+[
+  {
+    "query": "Build me a PowerPoint from this content",
+    "should_trigger": true
+  },
+  {
+    "query": "Generate a .pptx deck for this exec presentation",
+    "should_trigger": true
+  },
+  {
+    "query": "Turn this into actual slides I can present, with our brand colors",
+    "should_trigger": true
+  },
+  {
+    "query": "I need a real deck file, not an outline",
+    "should_trigger": true
+  },
+  {
+    "query": "Just outline the slides — I'll build the deck myself",
+    "should_trigger": false
+  },
+  {
+    "query": "Write a one-page summary for executives",
+    "should_trigger": false
+  },
+  {
+    "query": "Which audience archetype should I target and what are its rules?",
+    "should_trigger": false
+  },
+  {
+    "query": "Critique the deck I already made",
+    "should_trigger": false
+  }
+]

package/skills/deck-builder/evals/evals.json

@@ -0,0 +1,17 @@
+{
+  "skill_name": "deck-builder",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Build a .pptx from this content for an exec audience, using our brand palette (navy/white).",
+      "assertions": [
+        "A real .pptx file is produced, not an outline",
+        "The title slide carries a real title, subtitle, presenter, and date — never left blank",
+        "Section dividers appear sparingly, at most one every 4-5 content slides",
+        "Big-number layouts use only numbers the user supplied; no statistic is invented for emphasis",
+        "Bullet density matches the stated audience rather than a fixed default",
+        "The requested palette is applied rather than the default theme"
+      ]
+    }
+  ]
+}

package/skills/design-doc/evals/eval_queries.json

@@ -0,0 +1,34 @@
+[
+  {
+    "query": "Draft a design doc for this feature",
+    "should_trigger": true
+  },
+  {
+    "query": "Write a Google-style engineering design document from this brief",
+    "should_trigger": true
+  },
+  {
+    "query": "I need a technical design with goals, non-goals, alternatives, and rollout",
+    "should_trigger": true
+  },
+  {
+    "query": "Turn this feature brief into a design doc the team can review",
+    "should_trigger": true
+  },
+  {
+    "query": "Write an ADR recording this one decision",
+    "should_trigger": false
+  },
+  {
+    "query": "Draft the product requirements document for this feature",
+    "should_trigger": false
+  },
+  {
+    "query": "Critique the design doc I already wrote",
+    "should_trigger": false
+  },
+  {
+    "query": "Split this epic into user stories",
+    "should_trigger": false
+  }
+]

package/skills/design-doc/evals/evals.json

@@ -0,0 +1,17 @@
+{
+  "skill_name": "design-doc",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Draft a design doc for a notification service that consumes domain events and delivers email and push notifications for about 1M events/day.",
+      "assertions": [
+        "Non-goals are real scope boundaries a reader might otherwise assume are in scope, not throat-clearing",
+        "Each alternative carries a two-sentence what-it-is and why-we-didn't-pick-it",
+        "Every risk has a mitigation, not a bare list of concerns",
+        "Goals are stated with measurable targets rather than adjectives",
+        "The rollout section names stages and what would halt it",
+        "Facts not supplied by the user are marked as open questions rather than invented"
+      ]
+    }
+  ]
+}

package/skills/devils-advocate/evals/eval_queries.json

@@ -0,0 +1,38 @@
+[
+  {
+    "query": "Review this code I just wrote before I merge it",
+    "should_trigger": true
+  },
+  {
+    "query": "Anything I might have missed in this implementation?",
+    "should_trigger": true
+  },
+  {
+    "query": "Adversarially review this diff for edge cases and broken assumptions",
+    "should_trigger": true
+  },
+  {
+    "query": "I just finished the feature and the tests pass — is it ready to ship?",
+    "should_trigger": true
+  },
+  {
+    "query": "Find the bugs a staff engineer would push back on in review",
+    "should_trigger": true
+  },
+  {
+    "query": "Critique this design document",
+    "should_trigger": false
+  },
+  {
+    "query": "Convene multiple senior personas to deliberate this architecture decision",
+    "should_trigger": false
+  },
+  {
+    "query": "Implement this ticket from its acceptance criteria",
+    "should_trigger": false
+  },
+  {
+    "query": "Run the full gate and reviewers and tell me if this is safe to merge",
+    "should_trigger": false
+  }
+]

package/skills/devils-advocate/evals/evals.json

@@ -0,0 +1,19 @@
+{
+  "skill_name": "devils-advocate",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Here's the payment-retry handler I just finished — it retries failed charges up to 3 times with exponential backoff, and the tests pass. Review it before I open the PR.",
+      "assertions": [
+        "Every finding has a reproducible scenario a senior engineer can replay mentally — named input, current behavior, expected behavior",
+        "Every finding cites file:line, not just a section or function name",
+        "Severity is calibrated — blockers do not outnumber majors; inflated findings are demoted",
+        "Findings are grouped by the four lenses (edge cases, assumptions, staff-engineer pushback, test-coverage gaps), skipping lenses that do not apply rather than padding",
+        "Test-coverage gaps name the concrete missing test case, not 'add more tests'",
+        "Assertion theater is called out — tests that execute the code without asserting the behavior",
+        "Output ends with a 'what's solid' section so the author knows what not to touch",
+        "The review scopes to the change under review, never sweeping the whole codebase"
+      ]
+    }
+  ]
+}

package/skills/doc-critique/evals/eval_queries.json

@@ -0,0 +1,38 @@
+[
+  {
+    "query": "Critique this design doc before I share it",
+    "should_trigger": true
+  },
+  {
+    "query": "Review this ADR and tell me where it's weak",
+    "should_trigger": true
+  },
+  {
+    "query": "Is this runbook actually good? Give me a structured critique",
+    "should_trigger": true
+  },
+  {
+    "query": "Score this exec summary against a quality bar",
+    "should_trigger": true
+  },
+  {
+    "query": "Review my document and give me severity-tagged findings with fixes",
+    "should_trigger": true
+  },
+  {
+    "query": "Review this pull request for bugs",
+    "should_trigger": false
+  },
+  {
+    "query": "Write a new ADR for this decision",
+    "should_trigger": false
+  },
+  {
+    "query": "Get five senior personas to deliberate whether we should do this",
+    "should_trigger": false
+  },
+  {
+    "query": "Summarize this document for executives",
+    "should_trigger": false
+  }
+]

package/skills/doc-critique/evals/evals.json

@@ -0,0 +1,17 @@
+{
+  "skill_name": "doc-critique",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Critique this design doc before I circulate it to the team. [design doc: a TL;DR full of adjectives, an approach section that says 'industry standard', no SLOs, and a one-line rollout plan]",
+      "assertions": [
+        "Every finding quotes the document verbatim rather than paraphrasing it — the quoted snippet is the audit trail",
+        "Findings are local and anchored to a section, not global judgments like 'the tone is off'",
+        "Severity is calibrated — blockers do not outnumber majors",
+        "Fixes are paste-able: when the fix is 'add a section', the critique shows what that section should contain",
+        "The critique reviews whether the doc made its case, and does not re-debate the underlying technical topic",
+        "The document archetype is identified and the critique is run against that archetype's quality bar"
+      ]
+    }
+  ]
+}

package/skills/exec-summary/evals/eval_queries.json

@@ -0,0 +1,34 @@
+[
+  {
+    "query": "Summarize this design doc for our executives",
+    "should_trigger": true
+  },
+  {
+    "query": "I need a one-page summary of this long proposal for a non-technical stakeholder",
+    "should_trigger": true
+  },
+  {
+    "query": "Give me the 30-second version of this technical document",
+    "should_trigger": true
+  },
+  {
+    "query": "Compress this into something our COO will actually read",
+    "should_trigger": true
+  },
+  {
+    "query": "Build me a PowerPoint of this",
+    "should_trigger": false
+  },
+  {
+    "query": "Outline the slides for this presentation",
+    "should_trigger": false
+  },
+  {
+    "query": "What should I change about how I present to a board audience?",
+    "should_trigger": false
+  },
+  {
+    "query": "Critique this document against its quality bar",
+    "should_trigger": false
+  }
+]

package/skills/exec-summary/evals/evals.json

@@ -0,0 +1,17 @@
+{
+  "skill_name": "exec-summary",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Compress this 14-page platform-migration design doc into a one-page summary for our non-technical COO.",
+      "assertions": [
+        "Fits one page and leads with the decision or ask, not background",
+        "Numbers are quantified where available; where they aren't, the summary says 'directional' rather than inventing precision",
+        "A non-engineer meets no unexplained technical term in the first paragraph",
+        "No internal team-speak (OKRs, swimlanes, north-star metric) survives into the summary",
+        "Nothing is asserted that isn't supported by the source document",
+        "The output is prose a reader can scan in ~30 seconds — not slides and not a deck outline"
+      ]
+    }
+  ]
+}

package/skills/figma-diagrams/evals/eval_queries.json

@@ -0,0 +1,34 @@
+[
+  {
+    "query": "List the frames in our Figma file",
+    "should_trigger": true
+  },
+  {
+    "query": "Read this Figma file structure via the API",
+    "should_trigger": true
+  },
+  {
+    "query": "Post a comment on this Figma frame",
+    "should_trigger": true
+  },
+  {
+    "query": "Convert this FigJam connector graph into a diagram spec",
+    "should_trigger": true
+  },
+  {
+    "query": "Draw an architecture diagram in Mermaid from this description",
+    "should_trigger": false
+  },
+  {
+    "query": "Reverse-engineer our architecture from the repo",
+    "should_trigger": false
+  },
+  {
+    "query": "Build a PowerPoint deck from this content",
+    "should_trigger": false
+  },
+  {
+    "query": "Audit this UI for accessibility issues",
+    "should_trigger": false
+  }
+]

package/skills/figma-diagrams/evals/evals.json

@@ -0,0 +1,15 @@
+{
+  "skill_name": "figma-diagrams",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "List the pages and frames in this Figma file and post a comment on the checkout frame.",
+      "assertions": [
+        "The token is read from the FIGMA_TOKEN environment variable and never logged or passed on the command line",
+        "Output is filtered to pages, frames, and groups (about three levels) and summarized rather than dumping raw JSON",
+        "Before posting any comment, the exact comment text and target frame are shown for confirmation",
+        "The skill states clearly when FIGMA_TOKEN is missing rather than failing opaquely"
+      ]
+    }
+  ]
+}

package/skills/incident-comms/evals/eval_queries.json

@@ -0,0 +1,34 @@
+[
+  {
+    "query": "Draft a status page update for this ongoing incident",
+    "should_trigger": true
+  },
+  {
+    "query": "We're live in an incident — I need customer, internal, and exec updates",
+    "should_trigger": true
+  },
+  {
+    "query": "Write the customer-facing comms while we investigate",
+    "should_trigger": true
+  },
+  {
+    "query": "How do I tell stakeholders about this outage right now?",
+    "should_trigger": true
+  },
+  {
+    "query": "Write the blameless postmortem now that it's resolved",
+    "should_trigger": false
+  },
+  {
+    "query": "Generate the runbook for this service",
+    "should_trigger": false
+  },
+  {
+    "query": "Summarize this technical doc for executives",
+    "should_trigger": false
+  },
+  {
+    "query": "Extract decisions and action items from the incident channel",
+    "should_trigger": false
+  }
+]

package/skills/incident-comms/evals/evals.json

@@ -0,0 +1,16 @@
+{
+  "skill_name": "incident-comms",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "We're 20 minutes into a live incident — checkout is failing for about 30% of users, cause not yet confirmed. Draft the customer, internal, and exec updates.",
+      "assertions": [
+        "Each message's first sentence is reader-facing impact, not an internal symptom or architecture detail",
+        "Every message names the next-update time, or marks it [set HH:MM] when unknown",
+        "No unconfirmed cause is stated and no commitment is made that might need retracting",
+        "The three audiences (customer status page, internal stakeholders, exec) get genuinely different messages rather than one text reused",
+        "Nothing is asserted beyond what the operator supplied"
+      ]
+    }
+  ]
+}

package/skills/nfr-spec/evals/eval_queries.json

@@ -0,0 +1,34 @@
+[
+  {
+    "query": "What are the non-functional requirements for this service?",
+    "should_trigger": true
+  },
+  {
+    "query": "Sweep the NFRs — latency, availability, privacy, accessibility, operability",
+    "should_trigger": true
+  },
+  {
+    "query": "Set performance and availability targets for this feature",
+    "should_trigger": true
+  },
+  {
+    "query": "We keep forgetting the -ilities; give me the full NFR ledger",
+    "should_trigger": true
+  },
+  {
+    "query": "Write the functional requirements and user stories",
+    "should_trigger": false
+  },
+  {
+    "query": "Draft the OpenAPI contract for this service",
+    "should_trigger": false
+  },
+  {
+    "query": "Design the dashboards, SLOs, and alerts we should build",
+    "should_trigger": false
+  },
+  {
+    "query": "Model the capacity and cost for this workload",
+    "should_trigger": false
+  }
+]

package/skills/nfr-spec/evals/evals.json

@@ -0,0 +1,16 @@
+{
+  "skill_name": "nfr-spec",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Sweep the non-functional requirements for our new checkout service.",
+      "assertions": [
+        "Every category in the catalog lands in one of three states — a target, not-applicable with a reason, or a tagged default; silence in any category is a failure",
+        "Every target states a percentile, a load condition, and how it will be verified — a latency number with no load condition is rejected",
+        "The availability target matches the honest answer to what an hour of downtime costs, not a marketing instinct",
+        "Privacy and retention are given concrete periods rather than 'per policy'",
+        "The output is a reviewable ledger covering all categories, not a prose paragraph about quality"
+      ]
+    }
+  ]
+}

package/skills/observability-plan/evals/eval_queries.json

@@ -0,0 +1,34 @@
+[
+  {
+    "query": "Design an observability plan for this service",
+    "should_trigger": true
+  },
+  {
+    "query": "What SLIs and SLOs should we define, and what should page us?",
+    "should_trigger": true
+  },
+  {
+    "query": "Set up burn-rate alerting with error budgets",
+    "should_trigger": true
+  },
+  {
+    "query": "We alert on CPU and it's useless — design symptom-based alerting",
+    "should_trigger": true
+  },
+  {
+    "query": "Sweep the full non-functional requirements catalog",
+    "should_trigger": false
+  },
+  {
+    "query": "Write the operational runbook for the on-call team",
+    "should_trigger": false
+  },
+  {
+    "query": "Model our capacity and infrastructure cost",
+    "should_trigger": false
+  },
+  {
+    "query": "Write the postmortem for last week's outage",
+    "should_trigger": false
+  }
+]

package/skills/observability-plan/evals/evals.json

@@ -0,0 +1,16 @@
+{
+  "skill_name": "observability-plan",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Design the observability plan for our checkout service — what should we measure, alert on, and page for?",
+      "assertions": [
+        "SLIs measure user experience as good-over-valid events, not resource utilization",
+        "Latency SLIs are threshold counts at a percentile, never averages",
+        "Every SLO carries an error budget stated in human terms plus a policy for when it is spent",
+        "Pages are symptom-based, actionable, and runbook-linked; anything not actionable is a ticket, not a page",
+        "The plan makes a deliberate metrics-vs-logs-vs-traces choice rather than proposing everything"
+      ]
+    }
+  ]
+}

package/skills/postmortem-generator/evals/eval_queries.json

@@ -0,0 +1,34 @@
+[
+  {
+    "query": "Write a blameless postmortem for this incident",
+    "should_trigger": true
+  },
+  {
+    "query": "Turn this pager timeline and Slack thread into a postmortem",
+    "should_trigger": true
+  },
+  {
+    "query": "We resolved the outage — document what happened and why",
+    "should_trigger": true
+  },
+  {
+    "query": "Generate the incident review doc with impact and action items",
+    "should_trigger": true
+  },
+  {
+    "query": "We're still in the incident — draft the customer update",
+    "should_trigger": false
+  },
+  {
+    "query": "Extract the decisions and owners from this thread",
+    "should_trigger": false
+  },
+  {
+    "query": "Write the runbook so this is handled better next time",
+    "should_trigger": false
+  },
+  {
+    "query": "Summarize the incident for the executive team",
+    "should_trigger": false
+  }
+]

package/skills/postmortem-generator/evals/evals.json

@@ -0,0 +1,17 @@
+{
+  "skill_name": "postmortem-generator",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Write the postmortem from this pager timeline and Slack thread for last Tuesday's checkout outage.",
+      "assertions": [
+        "Impact is quantified — duration, users or requests affected, SLO burn, revenue where known — or explicitly marked [missing]; 'significant impact' is rejected",
+        "No person is named in a causal sentence; roles appear only in response actions",
+        "Detection and mitigation gaps are computed and stated as numbers",
+        "The timeline is in UTC",
+        "Contributing factors are listed rather than a single root cause",
+        "Action items carry owners as roles and are derived from the contributing factors"
+      ]
+    }
+  ]
+}