Skip to content

dongshuyan/compass-skills / skills/assess-interview-candidate

assess-interview-candidate

Verified

根据候选人简历与岗位要求生成可审计的后台评估、简明的候选人介绍、按岗位重要性排列的简历疑点、12–18 道可直接照读的面试题,以及支持重点标记和本机保存的离线 HTML。用于招聘方准备结构化面试、核验岗位能力和记录回答。不要用于求职者模拟面试、私人背景调查、心理或人格诊断、从敏感属性推断表现,或自动录用、淘汰、排序候选人。

FileKindSize
SKILL.mdskill md17.9 KB
agents/openai.yamlconfig329 B
assets/candidate-assessment-template.htmlother35.5 KB
evals/evals.jsonconfig11.1 KB
references/agent-portability.mdmarkdown3.5 KB
references/evidence-and-inference-policy.mdmarkdown7.8 KB
references/job-modeling.mdmarkdown3.8 KB
references/privacy-and-fairness-cn.mdmarkdown7.1 KB
references/research-and-identity-policy.mdmarkdown4.0 KB
references/role-adapter-ai-llm-engineering.mdmarkdown5.7 KB
references/schema-evidence-ledger.jsonconfig6.2 KB
references/schema-interview-blueprint.jsonconfig5.6 KB
references/schema-interviewer-report.jsonconfig13.7 KB
references/schema-job-model.jsonconfig4.5 KB
references/schema-source-record.jsonconfig9.5 KB
references/scoring-and-coverage.mdmarkdown9.5 KB
references/structured-interview-methods.mdmarkdown4.8 KB
references/workflow-contract.mdmarkdown14.7 KB
scripts/calculate_interview_score.pyscript15.5 KB
scripts/create_candidate_case.pyscript3.6 KB
scripts/derive_timeline_age.pyscript9.9 KB
scripts/normalize_inputs.pyscript9.0 KB
scripts/prepare_candidate_photo.pyscript12.4 KB
scripts/render_candidate_report.pyscript5.3 KB
scripts/validate_candidate_report.pyscript10.1 KB
scripts/validate_case_contract.pyscript28.3 KB
scripts/validate_evidence_ledger.pyscript15.2 KB
scripts/validate_interviewer_report_data.pyscript35.4 KB
scripts/validate_source_log.pyscript21.4 KB
tests/test_candidate_profile_enrichment.pyscript40.3 KB
tests/test_interviewer_report.pyscript34.1 KB
tests/test_public_package.pyscript7.0 KB

references/schema-evidence-ledger.json

View on GitHub
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://local.skills.example/assess-interview-candidate/schema-evidence-ledger.json",
  "title": "Candidate Evidence Ledger",
  "type": "object",
  "additionalProperties": false,
  "required": ["schema_version", "case_id", "items"],
  "properties": {
    "schema_version": {"type": "string", "pattern": "^[0-9]+\\.[0-9]+\\.[0-9]+$"},
    "case_id": {"$ref": "#/$defs/nonEmptyString"},
    "items": {"type": "array", "items": {"$ref": "#/$defs/evidenceItem"}},
    "metadata": {"type": "object", "additionalProperties": true}
  },
  "$defs": {
    "nonEmptyString": {"type": "string", "minLength": 1},
    "confidence": {"enum": ["low", "medium", "high", "unknown"]},
    "starovField": {
      "type": "object",
      "additionalProperties": false,
      "required": ["value", "status"],
      "properties": {
        "value": {"type": ["string", "null"]},
        "status": {"enum": ["explicit", "inferred", "missing"]}
      }
    },
    "location": {
      "type": "object",
      "additionalProperties": false,
      "required": ["document", "locator"],
      "properties": {
        "document": {"$ref": "#/$defs/nonEmptyString"},
        "locator": {"$ref": "#/$defs/nonEmptyString"},
        "page": {"type": ["integer", "null"], "minimum": 1}
      }
    },
    "confidenceSet": {
      "type": "object",
      "additionalProperties": false,
      "required": ["extraction", "mapping", "ability"],
      "properties": {
        "extraction": {"$ref": "#/$defs/confidence"},
        "mapping": {"$ref": "#/$defs/confidence"},
        "ability": {"$ref": "#/$defs/confidence"}
      }
    },
    "evidenceItem": {
      "type": "object",
      "additionalProperties": false,
      "required": [
        "id", "claim", "claim_type", "excerpt", "location", "capability_ids",
        "importance_tier", "evidence_origin", "evidence_status", "truth_status", "starov", "confidence",
        "alternative_explanations", "remaining_gaps", "verification_questions",
        "high_impact", "human_confirmed", "scoring_eligible"
      ],
      "properties": {
        "id": {"$ref": "#/$defs/nonEmptyString"},
        "claim": {"$ref": "#/$defs/nonEmptyString"},
        "claim_type": {"enum": ["achievement", "responsibility", "skill", "credential", "timeline", "publication", "patent", "open_source", "other"]},
        "excerpt": {"$ref": "#/$defs/nonEmptyString"},
        "location": {"$ref": "#/$defs/location"},
        "capability_ids": {"type": "array", "minItems": 1, "items": {"$ref": "#/$defs/nonEmptyString"}},
        "importance_tier": {"enum": ["gate", "critical", "supporting", "differentiator"]},
        "evidence_origin": {"enum": ["resume", "public_professional", "public_social", "interview", "work_sample"]},
        "evidence_status": {"enum": ["externally_corroborated", "strong_self_report", "partially_specified", "claim_only", "contradicted", "indeterminate"]},
        "truth_status": {"enum": ["verified", "self_report", "contradicted", "indeterminate"]},
        "starov": {
          "type": "object",
          "additionalProperties": false,
          "required": ["situation", "task", "action", "result", "ownership", "verification"],
          "properties": {
            "situation": {"$ref": "#/$defs/starovField"},
            "task": {"$ref": "#/$defs/starovField"},
            "action": {"$ref": "#/$defs/starovField"},
            "result": {"$ref": "#/$defs/starovField"},
            "ownership": {"$ref": "#/$defs/starovField"},
            "verification": {"$ref": "#/$defs/starovField"}
          }
        },
        "method_or_artifact": {"type": ["string", "null"]},
        "metric_context": {"type": ["string", "null"]},
        "scale_and_constraints": {"type": ["string", "null"]},
        "source_ids": {"type": "array", "items": {"$ref": "#/$defs/nonEmptyString"}},
        "confidence": {"$ref": "#/$defs/confidenceSet"},
        "alternative_explanations": {"type": "array", "items": {"$ref": "#/$defs/nonEmptyString"}},
        "remaining_gaps": {"type": "array", "items": {"$ref": "#/$defs/nonEmptyString"}},
        "verification_questions": {"type": "array", "items": {"$ref": "#/$defs/nonEmptyString"}},
        "high_impact": {"type": "boolean"},
        "human_confirmed": {"type": "boolean"},
        "scoring_eligible": {"type": "boolean", "description": "Public social-media evidence must be false."},
        "notes": {"type": ["string", "null"]}
      },
      "allOf": [
        {
          "if": {"properties": {"scoring_eligible": {"const": true}}, "required": ["scoring_eligible"]},
          "then": {
            "properties": {
              "evidence_origin": {"enum": ["interview", "work_sample"]},
              "human_confirmed": {"const": true}
            }
          }
        },
        {
          "if": {"properties": {"evidence_origin": {"const": "public_social"}}, "required": ["evidence_origin"]},
          "then": {"properties": {"scoring_eligible": {"const": false}}}
        },
        {
          "if": {"properties": {"evidence_origin": {"enum": ["public_professional", "public_social"]}}, "required": ["evidence_origin"]},
          "then": {"required": ["source_ids"], "properties": {"source_ids": {"minItems": 1}}}
        },
        {
          "if": {"not": {"properties": {"truth_status": {"const": "verified"}}, "required": ["truth_status"]}},
          "then": {"properties": {"verification_questions": {"minItems": 1}}}
        },
        {
          "if": {"properties": {"high_impact": {"const": true}}, "required": ["high_impact"]},
          "then": {
            "properties": {
              "alternative_explanations": {"minItems": 2},
              "verification_questions": {"minItems": 1}
            }
          }
        },
        {
          "if": {"properties": {"evidence_status": {"const": "externally_corroborated"}}, "required": ["evidence_status"]},
          "then": {
            "required": ["source_ids"],
            "properties": {
              "truth_status": {"const": "verified"},
              "source_ids": {"minItems": 1}
            }
          }
        },
        {
          "if": {"properties": {"evidence_status": {"const": "contradicted"}}, "required": ["evidence_status"]},
          "then": {"properties": {"truth_status": {"const": "contradicted"}}}
        }
      ]
    }
  }
}
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: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated 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: 194kUpdated Claude CodeCodexVerifiedInstall