aicraftbook/aicraftbook-skills / skills/blueprint-probe
blueprint-probe
VerifiedReviews a proposed AI automation or agent workflow before it is built, for reliability, failure handling, data flow and privacy, prompt-injection exposure, human approval, cost and needless complexity. Use when someone shares a workflow plan, diagram, n8n/Make/Zapier export or agent design and asks "is this a good design", "what could go wrong", "review my automation" or "how do I make this production-ready".
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 721 B |
| LICENSE | other | 1.0 KB |
| README.md | markdown | 9.9 KB |
| SKILL.md | skill md | 3.8 KB |
| evals/independent-2026-10-21.json | config | 91.1 KB |
| evals/results-2026-10-21.json | config | 12.4 KB |
| evals/tasks.json | config | 4.5 KB |
| examples/requests.md | markdown | 772 B |
| references/checklist.md | markdown | 3.8 KB |
| skill.json | config | 1.2 KB |
evals/results-2026-10-21.json
View on GitHub{
"skill": "blueprint-probe",
"date": "2026-10-21",
"model": "sonnet",
"repeats": 3,
"method": "Each task run headless with Claude Code in a fresh empty folder, tools limited to Skill, Read, Glob; no MCP servers; project settings only. Baseline has no skill; the skill run has the skill in .claude/skills/. Scores are the share of the task's regular-expression checks passed (evals/tasks.json). The checks were written by the skill's author and test whether named issues and safe behaviours appear, not overall answer quality. Recorded under the earlier identifier \"automation-architecture-review\"; the instructions are the same except the title line.",
"claudeCodeVersion": "2.1.303 (Claude Code)",
"baseline": {
"runs": 9,
"errors": 0,
"meanScore": 0.8888888888888888,
"meanOutputTokens": 1773.2222222222222,
"meanDurationMs": 20064.666666666668,
"skillInvokedRuns": 0,
"byTask": {
"lead-autoreply-sms": {
"meanScore": 0.8333333333333334,
"runs": 3
},
"autonomous-support-agent": {
"meanScore": 0.8333333333333334,
"runs": 3
},
"over-engineered-digest": {
"meanScore": 1,
"runs": 3
}
}
},
"withSkill": {
"runs": 9,
"errors": 0,
"meanScore": 1,
"meanOutputTokens": 2652.1111111111113,
"meanDurationMs": 30290.222222222223,
"skillInvokedRuns": 9,
"byTask": {
"lead-autoreply-sms": {
"meanScore": 1,
"runs": 3
},
"autonomous-support-agent": {
"meanScore": 1,
"runs": 3
},
"over-engineered-digest": {
"meanScore": 1,
"runs": 3
}
}
},
"runs": [
{
"task": "autonomous-support-agent",
"condition": "baseline",
"repeat": 1,
"ok": true,
"passed": [
"injection-refunds",
"approval",
"least-privilege",
"cap",
"audit"
],
"failed": [
"severity"
],
"score": 0.8333333333333334,
"skillInvoked": false,
"durationMs": 23689,
"inputTokens": 2,
"outputTokens": 1291,
"cacheReadTokens": 2570,
"costUsdEstimate": 0.034927,
"turns": 1,
"answerFile": "evals/runs/2026-10-21/autonomous-support-agent-baseline-1.md"
},
{
"task": "autonomous-support-agent",
"condition": "baseline",
"repeat": 2,
"ok": true,
"passed": [
"injection-refunds",
"approval",
"least-privilege",
"cap",
"audit"
],
"failed": [
"severity"
],
"score": 0.8333333333333334,
"skillInvoked": false,
"durationMs": 16261,
"inputTokens": 2,
"outputTokens": 1324,
"cacheReadTokens": 2570,
"costUsdEstimate": 0.035209000000000004,
"turns": 1,
"answerFile": "evals/runs/2026-10-21/autonomous-support-agent-baseline-2.md"
},
{
"task": "autonomous-support-agent",
"condition": "baseline",
"repeat": 3,
"ok": true,
"passed": [
"injection-refunds",
"approval",
"least-privilege",
"cap",
"audit"
],
"failed": [
"severity"
],
"score": 0.8333333333333334,
"skillInvoked": false,
"durationMs": 15452,
"inputTokens": 2,
"outputTokens": 1444,
"cacheReadTokens": 2570,
"costUsdEstimate": 0.036441,
"turns": 1,
"answerFile": "evals/runs/2026-10-21/autonomous-support-agent-baseline-3.md"
},
{
"task": "autonomous-support-agent",
"condition": "skill",
"repeat": 1,
"ok": true,
"passed": [
"injection-refunds",
"approval",
"least-privilege",
"cap",
"audit",
"severity"
],
"failed": [],
"score": 1,
"skillInvoked": true,
"durationMs": 40266,
"inputTokens": 6,
"outputTokens": 2941,
"cacheReadTokens": 20201,
"costUsdEstimate": 0.0658741,
"turns": 4,
"answerFile": "evals/runs/2026-10-21/autonomous-support-agent-skill-1.md"
},
{
"task": "autonomous-support-agent",
"condition": "skill",
"repeat": 2,
"ok": true,
"passed": [
"injection-refunds",
"approval",
"least-privilege",
"cap",
"audit",
"severity"
],
"failed": [],
"score": 1,
"skillInvoked": true,
"durationMs": 32541,
"inputTokens": 6,
"outputTokens": 2754,
"cacheReadTokens": 20206,
"costUsdEstimate": 0.0640646,
"turns": 4,
"answerFile": "evals/runs/2026-10-21/autonomous-support-agent-skill-2.md"
},
{
"task": "autonomous-support-agent",
"condition": "skill",
"repeat": 3,
"ok": true,
"passed": [
"injection-refunds",
"approval",
"least-privilege",
"cap",
"audit",
"severity"
],
"failed": [],
"score": 1,
"skillInvoked": true,
"durationMs": 24752,
"inputTokens": 4,
"outputTokens": 2462,
"cacheReadTokens": 10717,
"costUsdEstimate": 0.053395700000000004,
"turns": 3,
"answerFile": "evals/runs/2026-10-21/autonomous-support-agent-skill-3.md"
},
{
"task": "lead-autoreply-sms",
"condition": "baseline",
"repeat": 1,
"ok": true,
"passed": [
"human-approval",
"duplicates",
"prompt-injection",
"pii",
"sms-consent",
"output-validation",
"no-invented-prices"
],
"failed": [
"severity"
],
"score": 0.875,
"skillInvoked": false,
"durationMs": 23165,
"inputTokens": 2,
"outputTokens": 2437,
"cacheReadTokens": 2570,
"costUsdEstimate": 0.046615000000000004,
"turns": 1,
"answerFile": "evals/runs/2026-10-21/lead-autoreply-sms-baseline-1.md"
},
{
"task": "lead-autoreply-sms",
"condition": "baseline",
"repeat": 2,
"ok": true,
"passed": [
"human-approval",
"duplicates",
"prompt-injection",
"pii",
"sms-consent",
"output-validation",
"no-invented-prices"
],
"failed": [
"severity"
],
"score": 0.875,
"skillInvoked": false,
"durationMs": 24870,
"inputTokens": 2,
"outputTokens": 2767,
"cacheReadTokens": 2570,
"costUsdEstimate": 0.049947000000000005,
"turns": 1,
"answerFile": "evals/runs/2026-10-21/lead-autoreply-sms-baseline-2.md"
},
{
"task": "lead-autoreply-sms",
"condition": "baseline",
"repeat": 3,
"ok": true,
"passed": [
"human-approval",
"duplicates",
"prompt-injection",
"sms-consent",
"output-validation",
"no-invented-prices"
],
"failed": [
"pii",
"severity"
],
"score": 0.75,
"skillInvoked": false,
"durationMs": 26842,
"inputTokens": 2,
"outputTokens": 2198,
"cacheReadTokens": 2570,
"costUsdEstimate": 0.044261,
"turns": 1,
"answerFile": "evals/runs/2026-10-21/lead-autoreply-sms-baseline-3.md"
},
{
"task": "lead-autoreply-sms",
"condition": "skill",
"repeat": 1,
"ok": true,
"passed": [
"human-approval",
"duplicates",
"prompt-injection",
"pii",
"sms-consent",
"output-validation",
"no-invented-prices",
"severity"
],
"failed": [],
"score": 1,
"skillInvoked": true,
"durationMs": 25111,
"inputTokens": 4,
"outputTokens": 2545,
"cacheReadTokens": 10784,
"costUsdEstimate": 0.054492399999999996,
"turns": 3,
"answerFile": "evals/runs/2026-10-21/lead-autoreply-sms-skill-1.md"
},
{
"task": "lead-autoreply-sms",
"condition": "skill",
"repeat": 2,
"ok": true,
"passed": [
"human-approval",
"duplicates",
"prompt-injection",
"pii",
"sms-consent",
"output-validation",
"no-invented-prices",
"severity"
],
"failed": [],
"score": 1,
"skillInvoked": true,
"durationMs": 30648,
"inputTokens": 6,
"outputTokens": 2959,
"cacheReadTokens": 20358,
"costUsdEstimate": 0.0663938,
"turns": 4,
"answerFile": "evals/runs/2026-10-21/lead-autoreply-sms-skill-2.md"
},
{
"task": "lead-autoreply-sms",
"condition": "skill",
"repeat": 3,
"ok": true,
"passed": [
"human-approval",
"duplicates",
"prompt-injection",
"pii",
"sms-consent",
"output-validation",
"no-invented-prices",
"severity"
],
"failed": [],
"score": 1,
"skillInvoked": true,
"durationMs": 28280,
"inputTokens": 6,
"outputTokens": 2653,
"cacheReadTokens": 20351,
"costUsdEstimate": 0.0632691,
"turns": 4,
"answerFile": "evals/runs/2026-10-21/lead-autoreply-sms-skill-3.md"
},
{
"task": "over-engineered-digest",
"condition": "baseline",
"repeat": 1,
"ok": true,
"passed": [
"category-lookup",
"template-format",
"simplify",
"failure-alert",
"cost"
],
"failed": [],
"score": 1,
"skillInvoked": false,
"durationMs": 16250,
"inputTokens": 2,
"outputTokens": 1568,
"cacheReadTokens": 2570,
"costUsdEstimate": 0.037833,
"turns": 1,
"answerFile": "evals/runs/2026-10-21/over-engineered-digest-baseline-1.md"
},
{
"task": "over-engineered-digest",
"condition": "baseline",
"repeat": 2,
"ok": true,
"passed": [
"category-lookup",
"template-format",
"simplify",
"failure-alert",
"cost"
],
"failed": [],
"score": 1,
"skillInvoked": false,
"durationMs": 18180,
"inputTokens": 2,
"outputTokens": 1576,
"cacheReadTokens": 2570,
"costUsdEstimate": 0.037901000000000004,
"turns": 1,
"answerFile": "evals/runs/2026-10-21/over-engineered-digest-baseline-2.md"
},
{
"task": "over-engineered-digest",
"condition": "baseline",
"repeat": 3,
"ok": true,
"passed": [
"category-lookup",
"template-format",
"simplify",
"failure-alert",
"cost"
],
"failed": [],
"score": 1,
"skillInvoked": false,
"durationMs": 15873,
"inputTokens": 2,
"outputTokens": 1354,
"cacheReadTokens": 2570,
"costUsdEstimate": 0.035693,
"turns": 1,
"answerFile": "evals/runs/2026-10-21/over-engineered-digest-baseline-3.md"
},
{
"task": "over-engineered-digest",
"condition": "skill",
"repeat": 1,
"ok": true,
"passed": [
"category-lookup",
"template-format",
"simplify",
"failure-alert",
"cost"
],
"failed": [],
"score": 1,
"skillInvoked": true,
"durationMs": 26680,
"inputTokens": 6,
"outputTokens": 2300,
"cacheReadTokens": 20290,
"costUsdEstimate": 0.059552999999999995,
"turns": 4,
"answerFile": "evals/runs/2026-10-21/over-engineered-digest-skill-1.md"
},
{
"task": "over-engineered-digest",
"condition": "skill",
"repeat": 2,
"ok": true,
"passed": [
"category-lookup",
"template-format",
"simplify",
"failure-alert",
"cost"
],
"failed": [],
"score": 1,
"skillInvoked": true,
"durationMs": 29633,
"inputTokens": 6,
"outputTokens": 2779,
"cacheReadTokens": 20301,
"costUsdEstimate": 0.0644321,
"turns": 4,
"answerFile": "evals/runs/2026-10-21/over-engineered-digest-skill-2.md"
},
{
"task": "over-engineered-digest",
"condition": "skill",
"repeat": 3,
"ok": true,
"passed": [
"category-lookup",
"template-format",
"simplify",
"failure-alert",
"cost"
],
"failed": [],
"score": 1,
"skillInvoked": true,
"durationMs": 34701,
"inputTokens": 6,
"outputTokens": 2476,
"cacheReadTokens": 20286,
"costUsdEstimate": 0.0613646,
"turns": 4,
"answerFile": "evals/runs/2026-10-21/over-engineered-digest-skill-3.md"
}
],
"recordedAs": "automation-architecture-review"
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |