Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Public It Project Procedure Check

ASecurity

전산 업무의 공공 정보화사업 절차 점검 절차. 내부 public-it-project-procedure-review capability를 사용하며 draft-only 경계를 지킵니다.

3 stars
0 votes
0 copies
0 views
Added 9/24/2026
ai-agentspythongo

Security Analysis

A100/100

Scanned 9/24/2026

$npx -y skills add vertexsquad/k-gov-skills --skill public-it-project-procedure-check --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Public It Project Procedure Check?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Public It Project Procedure Check
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vertexsquad-public-it-project-procedure-check/badge)](https://www.skillsdirectory.com/skills/vertexsquad-public-it-project-procedure-check)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: public-it-project-procedure-check
description: "전산 업무의 공공 정보화사업 절차 점검 절차. 내부 public-it-project-procedure-review capability를 사용하며 draft-only 경계를 지킵니다."
metadata:
  domain: "전산"
  capability: "public-it-project-procedure-review"
  runtime_contract: "kgov/public-it-project-procedure-review/v1"
  operation: "kgov/public-it-project-procedure-review/review-case/v1"
  role: "additional"
---

<!-- generated from catalog/domain-skills.json; do not edit -->

# 공공 정보화사업 절차 점검

- Domain: **전산**
- 내부 capability: `public-it-project-procedure-review`
- 실행 상태: `fixture-verified` / live smoke `not-run`
- 실행 경계: `draft-only`
- Reference Skill: 없음

## Runtime binding

- Contract: `kgov/public-it-project-procedure-review/v1`
- Operation: `kgov/public-it-project-procedure-review/review-case/v1`
- Fixed input: `{"argv": ["--fixture"]}`
- Output fields: `manual_review_required`, `fact_count`, `source_ref_count`, `review_type`, `receipt_assurance`, `source_output_mode`, `basic_identifier_scan`, `manual_review_reasons`, `prohibited_decisions`, `required_checks`, `source_assurance_levels`, `accepted`, `status`, `permitted_output`

<!-- kgov-runtime-binding:start -->
```json
{
  "binding": {
    "contract_id": "kgov/public-it-project-procedure-review/v1",
    "fixed_input": {
      "argv": [
        "--fixture"
      ]
    },
    "operation": "kgov/public-it-project-procedure-review/review-case/v1"
  },
  "example_result": {
    "accepted": true,
    "basic_identifier_scan": "no-match-not-proof-of-redaction",
    "fact_count": 1,
    "manual_review_reasons": [
      "caller-declared-source",
      "license-unverified",
      "redistribution-link-only"
    ],
    "manual_review_required": true,
    "permitted_output": "procedure-review-draft-only",
    "prohibited_decisions": [
      "automatic-procurement-start",
      "automatic-acceptance",
      "institution-rule-assumption"
    ],
    "receipt_assurance": "caller-declared-not-live-retrieval-proof",
    "required_checks": [
      "project-stage-identification",
      "required-deliverables",
      "approval-owner-and-current-rule"
    ],
    "review_type": "project-stage-check",
    "source_assurance_levels": [
      "caller-declared"
    ],
    "source_output_mode": "link-only",
    "source_ref_count": 1,
    "status": "admitted-pending-human-review"
  },
  "exit_codes": {
    "input_error": 2,
    "policy_blocked": 3,
    "review_blocked": 1,
    "success": 0,
    "upstream_error": 4
  },
  "fixture_argv": [
    "--fixture"
  ],
  "input_schema": {
    "additionalProperties": false,
    "properties": {
      "argv": {
        "items": {
          "type": "string"
        },
        "type": "array"
      }
    },
    "required": [
      "argv"
    ],
    "type": "object"
  },
  "module": "kgov_runtime.capabilities.public_it_project_procedure_review",
  "network_mode": "none",
  "output_schema": {
    "additionalProperties": false,
    "properties": {
      "accepted": {
        "const": true,
        "type": "boolean"
      },
      "basic_identifier_scan": {
        "const": "no-match-not-proof-of-redaction",
        "type": "string"
      },
      "fact_count": {
        "minimum": 0,
        "type": "integer"
      },
      "manual_review_reasons": {
        "items": {
          "enum": [
            "caller-declared-source",
            "policy-outcome-manual-review",
            "license-unverified",
            "redistribution-link-only"
          ],
          "type": "string"
        },
        "type": "array"
      },
      "manual_review_required": {
        "const": true,
        "type": "boolean"
      },
      "permitted_output": {
        "const": "procedure-review-draft-only",
        "type": "string"
      },
      "prohibited_decisions": {
        "items": {
          "type": "string"
        },
        "type": "array"
      },
      "receipt_assurance": {
        "enum": [
          "policy-matched-not-cryptographic-authenticity-proof",
          "caller-declared-not-live-retrieval-proof"
        ],
        "type": "string"
      },
      "required_checks": {
        "items": {
          "type": "string"
        },
        "type": "array"
      },
      "review_type": {
        "enum": [
          "deliverable-check",
          "project-stage-check"
        ],
        "type": "string"
      },
      "source_assurance_levels": {
        "items": {
          "enum": [
            "caller-declared",
            "policy-verified-not-authenticity-proof"
          ],
          "type": "string"
        },
        "type": "array"
      },
      "source_output_mode": {
        "enum": [
          "projected-records",
          "link-only"
        ],
        "type": "string"
      },
      "source_ref_count": {
        "minimum": 0,
        "type": "integer"
      },
      "status": {
        "const": "admitted-pending-human-review",
        "type": "string"
      }
    },
    "required": [
      "manual_review_required",
      "fact_count",
      "source_ref_count",
      "review_type",
      "receipt_assurance",
      "source_output_mode",
      "basic_identifier_scan",
      "manual_review_reasons",
      "prohibited_decisions",
      "required_checks",
      "source_assurance_levels",
      "accepted",
      "status",
      "permitted_output"
    ],
    "type": "object"
  },
  "schema_status": "active",
  "source_output_mode": "none",
  "source_policy_ids": []
}
```
<!-- kgov-runtime-binding:end -->

## 업무별 추가 체크

- 기획·사전검토·조달·구축·검수·운영 단계 식별
- 단계별 필수 산출물과 승인 주체 확인
- 기관별 적용 규정의 최신성을 담당자가 재확인

## 절차

1. 전체 저장소 checkout이 필요합니다. Skill 디렉터리만 복사해서 실행하지 않습니다. 클라이언트와 모든 명령은 `kgov_runtime/`, `docs/`, `tests/`가 있는 저장소 루트에서 실행하고, 루트 기준 `docs/capabilities/public-it-project-procedure-review/procedure.md`와 `docs/capabilities/public-it-project-procedure-review/runtime-contract.md`를 먼저 읽습니다.
2. `python3 -m kgov_runtime.capabilities.public_it_project_procedure_review --fixture`로 합성 fixture 계약을 검증합니다. 이는 사용자가 제공한 파일을 읽거나 검증한 결과가 아닙니다.
3. 제공된 로컬 입력은 procedure의 실제 입력 절차와 제한에 따라 별도로 검사합니다. 파일이 없거나 읽을 수 없으면 차단 상태를 보고하고 fixture로 대신 검증했다고 주장하지 않습니다.
4. live 실행은 capability manifest의 credential·proxy·허용 host 경계를 충족할 때만 수행합니다.
5. 기관별 적용 규정, 사업 단계 확정, 결재와 조달 착수는 담당 공무원이 승인
6. fixture 성공, 로컬 입력 검사, URL 도달, live 검증을 서로 다른 증거로 보고합니다.

## 금지

- 이 Skill을 근거로 원본 변경·제출·결재·발송을 자동 수행하지 않습니다.
- 비밀값이나 원문 개인정보를 로그·결과·fixture에 남기지 않습니다.
- 내부 capability를 별도 top-level `skills/` 제품 표면으로 복제하지 않습니다.

Attribution

vertexsquadvertexsquad
View sourceSee grades on GitHubMore from vertexsquad →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →