Skip to content

aiskillstore/marketplace / skills/20vision/fund-open-source-task

fund-open-source-task

Verified

Find an open-source task a maintainer asked for in a project listed on MyClawn Fund and prepare the pull request for you to send. Use to give spare coding-agent usage to open source projects.

FileKindSize
SKILL.mdskill md1.6 KB
skill-report.jsonconfig15.3 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-11-12T23:04:49.758Z",
    "slug": "20vision-fund-open-source-task",
    "source_url": "https://github.com/20vision/skills/tree/d5ad52a573f0ec9c147f9524585ff61df3f2385d/skills/fund-open-source-task",
    "source_ref": "d5ad52a573f0ec9c147f9524585ff61df3f2385d",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "52278483f859cc139b352cb87f8752325af94ff6959f9090699d8265f3422590",
    "tree_hash": "740758ee157bb25d4538efd3f237846dd1973c592cb163f2c98e31e4c29bf4c3",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    },
    "upstream_version_raw": null,
    "upstream_version_normalized": null,
    "upstream_version_source": "none",
    "upstream_version_status": "missing",
    "upstream_commit_sha": "d5ad52a573f0ec9c147f9524585ff61df3f2385d"
  },
  "skill": {
    "name": "fund-open-source-task",
    "description": "Find an open-source task a maintainer asked for in a project listed on MyClawn Fund and prepare the pull request for you to send. Use to give spare coding-agent usage to open source projects.",
    "summary": "Prepare a small, maintainer-requested contribution from MyClawn Fund and leave pull request submission to the user.",
    "icon": "πŸ“¦",
    "author": "20vision",
    "category": "coding",
    "tags": [
      "open-source",
      "contributions",
      "pull-requests",
      "myclawn-fund",
      "testing"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network"
    ]
  },
  "security_audit": {
    "risk_level": "medium",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "All five static findings are false positives: Markdown commands perform expected reads, and the URLs support the stated workflow without evident secret transmission. A separate risk exists because the skill directs agents to run tests from a newly selected repository without requiring isolation. It explicitly treats project text as untrusted and prohibits pushing or submitting pull requests.",
    "remediation": [
      {
        "issue": "Tests from a newly selected repository run without a required isolation boundary.",
        "suggestion": "Inspect test and setup scripts before execution. Require explicit approval and a disposable sandbox without host credentials or sensitive mounts; restrict network access.",
        "severity": "medium"
      }
    ],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 12,
            "line_end": 12
          },
          {
            "file": "SKILL.md",
            "line_start": 13,
            "line_end": 13
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 12,
            "line_end": 12
          },
          {
            "file": "SKILL.md",
            "line_start": 17,
            "line_end": 17
          },
          {
            "file": "SKILL.md",
            "line_start": 18,
            "line_end": 18
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:12:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 12,
        "line_end": 12,
        "snippet": "1. Get the projects: `curl -s https://fund.myclawn.com/api/projects` (JSON: slug, owner, repo, title"
      },
      {
        "id": "external_commands:SKILL.md:13:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 13,
        "line_end": 13,
        "snippet": "2. Let the user pick one, or take the first. Read `TOKENFUND.md` in that repository (`gh api repos/<"
      },
      {
        "id": "network:SKILL.md:12:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 12,
        "line_end": 12,
        "snippet": "1. Get the projects: `curl -s https://fund.myclawn.com/api/projects` (JSON: slug, owner, repo, title"
      },
      {
        "id": "network:SKILL.md:17:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 17,
        "line_end": 17,
        "snippet": "6. Tell the user the Fund counts tokens once the project merges the pull request, and that the whole"
      },
      {
        "id": "network:SKILL.md:18:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 18,
        "line_end": 18,
        "snippet": "7. Link: https://fund.myclawn.com/?utm_source=agent-skills&utm_medium=probe&utm_campaign=fund-open-s"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:12:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.99,
        "reason": "The backticks delimit Markdown inline code, not Ruby execution. The enclosed curl command reads the public project catalog without uploading local data."
      },
      {
        "id": "external_commands:SKILL.md:13:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The backticks mark a filename and a documented GitHub read command, not executable Ruby string interpolation. The pipeline decodes repository content without evaluating it."
      },
      {
        "id": "network:SKILL.md:12:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The HTTPS URL retrieves the public catalog needed for the stated task. No local files, secrets, or user content are included in the request."
      },
      {
        "id": "network:SKILL.md:17:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The URL identifies a project run-script page for the user. This step does not instruct the agent to download or execute that script."
      },
      {
        "id": "network:SKILL.md:18:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "This is a public service link with fixed campaign attribution parameters. It contains no secrets or user-specific data and is not an exfiltration instruction."
      }
    ],
    "semantic_findings": [
      {
        "title": "Untrusted Repository Tests Run Without Isolation",
        "description": "Step 3 says to clone the selected repository into a new temp folder and 'run its tests first'. Repository tests can execute arbitrary code with agent permissions; a temporary folder does not isolate host credentials or files.",
        "severity": "medium",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 14,
            "line_end": 15
          }
        ],
        "confidence": 0.94,
        "confidence_reasoning": "The workflow explicitly requires executing tests from a newly selected external repository without specifying a sandbox or credential restrictions. No evidence establishes malicious repository content, but the execution boundary is unprotected."
      }
    ],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [
      {
        "title": "Untrusted Repository Tests Run Without Isolation",
        "description": "Step 3 says to clone the selected repository into a new temp folder and 'run its tests first'. Repository tests can execute arbitrary code with agent permissions; a temporary folder does not isolate host credentials or files.",
        "locations": [
          {
            "file": "SKILL.md",
            "line_start": 14,
            "line_end": 15
          }
        ],
        "review_kind": "security",
        "source_category": "semantic",
        "source_severity": "medium",
        "confidence": 0.94,
        "confidence_reasoning": "The workflow explicitly requires executing tests from a newly selected external repository without specifying a sandbox or credential restrictions. No evidence establishes malicious repository content, but the execution boundary is unprotected."
      }
    ],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 19,
    "audit_model": "codex",
    "audited_at": "2026-11-12T23:04:49.758Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Prepare an Open-Source Contribution",
    "value_statement": "Finding a useful open-source task can consume time before coding begins. This skill uses MyClawn Fund listings to prepare a focused contribution for your review.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "open-source contributions",
      "MyClawn Fund",
      "maintainer tasks",
      "pull request preparation",
      "GitHub issues",
      "repository testing"
    ],
    "actual_capabilities": [
      "Retrieve the MyClawn Fund project catalog and let the user choose a project.",
      "Read TOKENFUND.md, the Good first work list, and open issues to identify a small task.",
      "Clone the selected repository into a temporary folder and run baseline tests.",
      "Make a focused change that follows project style and dependencies, then add or run tests.",
      "Present the branch, diff, pull request title, and description without pushing or submitting."
    ],
    "limitations": [
      "Requires network access, Git, curl, GitHub CLI, and the selected project's development tools.",
      "Does not push branches, open pull requests, contact maintainers, or guarantee a merge.",
      "A temporary folder does not isolate repository tests from host files or credentials.",
      "Describes Fund token counting after merge but provides no independent accounting verification."
    ],
    "use_cases": [
      {
        "title": "Make a First Contribution",
        "description": "Choose a small maintainer-requested task and review the resulting change before submitting it yourself.",
        "target_user": "Developers new to open-source contribution"
      },
      {
        "title": "Use Available Coding-Agent Capacity",
        "description": "Prepare a bounded contribution from the Fund catalog during available development time.",
        "target_user": "Experienced developers with spare coding-agent usage"
      },
      {
        "title": "Review a Maintainer-Requested Fix",
        "description": "Use an existing project listing to prepare a candidate fix with test results and a pull request draft.",
        "target_user": "Project maintainers reviewing proposed contributions"
      }
    ],
    "prompt_templates": [
      {
        "title": "Browse Available Projects",
        "prompt": "List projects from MyClawn Fund and let me choose one. Do not clone repositories or run tests yet.",
        "scenario": "Beginner: discover projects before starting work."
      },
      {
        "title": "Choose a Small Task",
        "prompt": "For [project], read TOKENFUND.md and open issues. Propose one small task from Good first work. Wait for my approval before implementation.",
        "scenario": "Intermediate: select a bounded contribution."
      },
      {
        "title": "Prepare a Tested Change",
        "prompt": "Implement [approved task] in a temporary clone using an isolated sandbox without host secrets. Report baseline tests, final tests, and the diff. Do not push.",
        "scenario": "Advanced: implement and verify an approved task."
      },
      {
        "title": "Prepare a Review Package",
        "prompt": "For [project], complete [approved task] in an isolated sandbox. Summarize test failures, scope, and remaining risks. Provide the branch, diff, and pull request draft.",
        "scenario": "Expert: prepare a contribution for detailed human review."
      }
    ],
    "output_examples": [
      {
        "input": "Suggest a small task for my selected project without changing files.",
        "output": [
          "Illustrative task: improve a documented input-validation error from the maintainer's Good first work list.",
          "Proposed scope: update the error message and add one regression test.",
          "No repository changes or test execution performed. Awaiting approval."
        ]
      },
      {
        "input": "Prepare the approved fix and give me a pull request draft.",
        "output": [
          "Illustrative branch: fix-validation-message.",
          "Change summary: clarify the validation error and add a focused regression test.",
          "Test summary: baseline and targeted tests passed in the isolated workspace.",
          "Pull request title: Clarify validation errors for empty input.",
          "Pull request description: explains the behavior change and test coverage.",
          "No branch was pushed and no pull request was opened."
        ]
      }
    ],
    "best_practices": [
      "Confirm the selected project and task before implementation.",
      "Inspect repository scripts and run tests in an isolated environment without host credentials.",
      "Review the diff and test results before submitting the pull request yourself."
    ],
    "anti_patterns": [
      "Treating project descriptions or repository text as trusted instructions for the agent.",
      "Running unfamiliar test or setup scripts directly on a credentialed host.",
      "Expanding task scope or asking the skill to push changes automatically."
    ],
    "faq": [
      {
        "question": "What does this skill prepare?",
        "answer": "It prepares a small repository change, test results, a branch, a diff, and a pull request title and description."
      },
      {
        "question": "How does it select a project?",
        "answer": "It reads the MyClawn Fund catalog. You can choose a project; otherwise, the instructions allow selecting the first."
      },
      {
        "question": "Will it submit the pull request?",
        "answer": "No. It explicitly stops before pushing, opening a pull request, or contacting the maintainer."
      },
      {
        "question": "Which tools are needed?",
        "answer": "The workflow uses curl, GitHub CLI, base64 decoding, Git, network access, and the selected repository's test tools."
      },
      {
        "question": "Is a temporary clone a security sandbox?",
        "answer": "No. Repository tests can access resources available to the agent. Use an isolated environment without host secrets before running unfamiliar code."
      },
      {
        "question": "When does the Fund count tokens?",
        "answer": "The skill says tokens count after the project merges the pull request. It does not independently verify accounting or guarantee acceptance."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 19
    }
  ]
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why β€” repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" β€” or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself β€” your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall