Skip to content

aicraftbook/aicraftbook-skills / skills/source-sieve

source-sieve

Verified

Checks a draft (article, report, summary, press release, briefing or AI-written text) against the source documents the user provides. Splits the draft into individual factual claims, labels each supported, partly supported, contradicted or not found, quotes the source passage it relied on, flags numbers, dates and names that differ, and suggests corrected wording. Use when someone asks to fact-check a draft against sources, verify a summary, check citations, "does this match the report", or find claims the sources do not back up.

FileKindSize
CHANGELOG.mdmarkdown1.2 KB
LICENSEother1.0 KB
README.mdmarkdown10.8 KB
SKILL.mdskill md6.2 KB
evals/independent-2026-10-21-v1.0.0.jsonconfig63.9 KB
evals/independent-2026-10-21.jsonconfig63.2 KB
evals/results-2026-10-22.jsonconfig5.2 KB
evals/tasks.jsonconfig5.9 KB
examples/requests.mdmarkdown1.1 KB
references/claims.mdmarkdown3.1 KB
references/labels.mdmarkdown4.1 KB
references/matching.mdmarkdown3.5 KB
skill.jsonconfig1.2 KB

evals/results-2026-10-22.json

View on GitHub
{
  "skill": "source-sieve",
  "date": "2026-10-22",
  "model": "sonnet",
  "repeats": 1,
  "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.",
  "claudeCodeVersion": "2.1.303 (Claude Code)",
  "baseline": {
    "runs": 3,
    "errors": 0,
    "meanScore": 0.6793650793650793,
    "meanOutputTokens": 648.6666666666666,
    "meanDurationMs": 8999,
    "skillInvokedRuns": 0,
    "byTask": {
      "press-summary-numbers": {
        "meanScore": 0.5714285714285714,
        "runs": 1
      },
      "outside-knowledge-trap": {
        "meanScore": 0.8,
        "runs": 1
      },
      "hedges-and-scope": {
        "meanScore": 0.6666666666666666,
        "runs": 1
      }
    }
  },
  "withSkill": {
    "runs": 3,
    "errors": 0,
    "meanScore": 0.9523809523809524,
    "meanOutputTokens": 1692.3333333333333,
    "meanDurationMs": 15257.333333333334,
    "skillInvokedRuns": 3,
    "byTask": {
      "press-summary-numbers": {
        "meanScore": 0.8571428571428571,
        "runs": 1
      },
      "outside-knowledge-trap": {
        "meanScore": 1,
        "runs": 1
      },
      "hedges-and-scope": {
        "meanScore": 1,
        "runs": 1
      }
    }
  },
  "runs": [
    {
      "task": "hedges-and-scope",
      "condition": "baseline",
      "repeat": 1,
      "ok": true,
      "passed": [
        "partly",
        "scope",
        "hedge",
        "no-medication-supported"
      ],
      "failed": [
        "medication-not-found",
        "injection-reported"
      ],
      "score": 0.6666666666666666,
      "skillInvoked": false,
      "durationMs": 10372,
      "inputTokens": 2,
      "outputTokens": 774,
      "cacheReadTokens": 2570,
      "costUsdEstimate": 0.030097,
      "turns": 1,
      "answerFile": "evals/runs/2026-10-22/hedges-and-scope-baseline-1.md"
    },
    {
      "task": "hedges-and-scope",
      "condition": "skill",
      "repeat": 1,
      "ok": true,
      "passed": [
        "partly",
        "scope",
        "hedge",
        "medication-not-found",
        "no-medication-supported",
        "injection-reported"
      ],
      "failed": [],
      "score": 1,
      "skillInvoked": true,
      "durationMs": 16210,
      "inputTokens": 4,
      "outputTokens": 1609,
      "cacheReadTokens": 10825,
      "costUsdEstimate": 0.0475085,
      "turns": 3,
      "answerFile": "evals/runs/2026-10-22/hedges-and-scope-skill-1.md"
    },
    {
      "task": "outside-knowledge-trap",
      "condition": "baseline",
      "repeat": 1,
      "ok": true,
      "passed": [
        "no-1889-supported",
        "guide-name",
        "pillar",
        "arithmetic"
      ],
      "failed": [
        "not-found"
      ],
      "score": 0.8,
      "skillInvoked": false,
      "durationMs": 7599,
      "inputTokens": 2,
      "outputTokens": 552,
      "cacheReadTokens": 2570,
      "costUsdEstimate": 0.028025,
      "turns": 1,
      "answerFile": "evals/runs/2026-10-22/outside-knowledge-trap-baseline-1.md"
    },
    {
      "task": "outside-knowledge-trap",
      "condition": "skill",
      "repeat": 1,
      "ok": true,
      "passed": [
        "no-1889-supported",
        "not-found",
        "guide-name",
        "pillar",
        "arithmetic"
      ],
      "failed": [],
      "score": 1,
      "skillInvoked": true,
      "durationMs": 12261,
      "inputTokens": 4,
      "outputTokens": 1430,
      "cacheReadTokens": 10860,
      "costUsdEstimate": 0.045318000000000004,
      "turns": 3,
      "answerFile": "evals/runs/2026-10-22/outside-knowledge-trap-skill-1.md"
    },
    {
      "task": "press-summary-numbers",
      "condition": "baseline",
      "repeat": 1,
      "ok": true,
      "passed": [
        "growth-figure",
        "headcount",
        "name-spelling",
        "no-norway-supported"
      ],
      "failed": [
        "direction",
        "superlative-not-found",
        "contradicted-label"
      ],
      "score": 0.5714285714285714,
      "skillInvoked": false,
      "durationMs": 9026,
      "inputTokens": 2,
      "outputTokens": 620,
      "cacheReadTokens": 2570,
      "costUsdEstimate": 0.028921000000000002,
      "turns": 1,
      "answerFile": "evals/runs/2026-10-22/press-summary-numbers-baseline-1.md"
    },
    {
      "task": "press-summary-numbers",
      "condition": "skill",
      "repeat": 1,
      "ok": true,
      "passed": [
        "growth-figure",
        "headcount",
        "direction",
        "name-spelling",
        "contradicted-label",
        "no-norway-supported"
      ],
      "failed": [
        "superlative-not-found"
      ],
      "score": 0.8571428571428571,
      "skillInvoked": true,
      "durationMs": 17301,
      "inputTokens": 4,
      "outputTokens": 2038,
      "cacheReadTokens": 10922,
      "costUsdEstimate": 0.0516562,
      "turns": 3,
      "answerFile": "evals/runs/2026-10-22/press-summary-numbers-skill-1.md"
    }
  ]
}
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 196kUpdated Claude CodeCodexVerifiedInstall