Index of every page on this site: llms.txt
All skills
google-gemini avatar

/specgenerator

@eecccfc
by google-geminigoogle-gemini/gemini-cli109k stars
14,968
Run it yourself

Generates a structured Workable Spec JSON to guide a Developer Worker.

  • 1 file
  • 3.9 KB
  • Updated 4 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/google-gemini/gemini-cli/specgenerator

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈21 tokens for metadata: the name and description. ≈974 when used: this file.

Description uses 1.1% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈87 characters, or 1.1%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Spec Generator Instructions

Extract key technical details from the issue and organize them according to the following strict JSON schema.

Critical Rules:

  1. Codebase Verification: Rely on file paths and locations found during your codebase exploration. Ensure all files mentioned in files_to_modify actually exist in the repository. Do not make up file paths.
  2. Target File Selection: List all source code files in files_to_modify where code changes belong.
    • Fix config or state issues early at their setup/hook entrypoint rather than refactoring low-level utilities.
    • Strictly do NOT list test files or files that were only inspected without requiring code changes.
  3. Strict JSON Escaping: Ensure the generated output is standard, valid JSON. In JSON string values (such as summary fields or verification steps), do NOT escape single quotes with backslashes. Write them directly as ' (not \\').

[!IMPORTANT] The output MUST strictly adhere to this schema. Deviations (like putting objects inside arrays instead of strings) will break the downstream automated code generation pipeline.

The final workable_spec object must conform strictly to this JSON Schema specification. Every field listed below is strictly required and must be populated:

{
  "type": "object",
  "properties": {
    "issue_id": {
      "type": "string",
      "description": "The specific GitHub issue identifier in the canonical format: {owner}/{repo}#{number} (e.g., google/gemini-cli#245)."
    },
    "summary": {
      "type": "object",
      "description": "A deep technical summary of the issue.",
      "properties": {
        "problem": {
          "type": "string",
          "description": "Concise statement of the problem."
        },
        "root_cause": {
          "type": "string",
          "description": "Analysis of the underlying cause of the bug."
        },
        "context": {
          "type": "string",
          "description": "Any additional technical context or background."
        }
      }
    },
    "implementation_plan": {
      "type": "object",
      "description": "Details required for code implementation of the fix.",
      "properties": {
        "files_to_modify": {
          "type": "array",
          "description": "List of source code files requiring changes relative to the repository root (e.g. ['src/cli.ts']). Strictly do NOT include test files (*.test.ts, *.spec.ts) here; test files must go into testing_strategy.test_file.",
          "items": {
            "type": "string"
          }
        },
        "steps": {
          "type": "array",
          "description": "Ordered step-by-step instructions to implement the fix. Each step must be a simple, flat string description. Do not nest objects inside this array.",
          "items": {
            "type": "string"
          }
        }
      }
    },
    "testing_strategy": {
      "type": "object",
      "description": "Instructions for validating the fix.",
      "properties": {
        "test_file": {
          "type": "string",
          "description": "Path to the relevant test file relative to the repository root (e.g., 'tests/cli.test.ts')."
        },
        "expected_behavior": {
          "type": "string",
          "description": "Description of how the system should behave after the fix."
        },
        "verification_steps": {
          "type": "array",
          "description": "Specific steps to add or modify in the test file.",
          "items": {
            "type": "string"
          }
        },
        "framework": {
          "type": "string",
          "description": "Testing framework used.",
          "enum": ["Vitest", "N/A"]
        }
      }
    }
  }
}

Do not include any metadata like spam assessment or effort tags in this spec. Keep it focused entirely on instructions for code generation and testing.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at eecccfc. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 10 hours ago.

Activeupdated 4 months ago

README badge

README badge for google-gemini/gemini-cli/specgenerator