generate-project-skill skill
✓ VerifiedGenerates or updates a compact, searchable Agent Skill directory from a software project's workflows, boundaries, and conventions.
- GitHub stars
- 331
- Files
- 2
- Last commit
- Oct 10, 2026
- License
- MIT
- Allowed tools
- —
What does the generate-project-skill skill do?
generate-project-skill generates or updates a compact, searchable Agent Skill directory from a software project's workflows, boundaries, and conventions.
Summary generated from the skill's SKILL.md.
About the generate-project-skill skill
Software maintainers who want to create or update a compact, searchable Agent Skill directory can use this tool to automate the documentation of their project's internal logic. By inspecting project instructions, decision records, manifests, and build configurations, the skill extracts essential workflows, boundaries, and conventions. It identifies critical commands for testing, linting, building, and releasing, while mapping out entry points like main modules or binaries.
An agent should load this skill when it needs to generate a structured directory containing a SKILL.md file, architecture references, and automation scripts. The process relies on filesystem and shell access to navigate directories and run search commands like rg. It carefully avoids sensitive or heavy data by skipping version control, dependency folders, generated outputs, and files larger than 512 KB. The resulting output provides a portable way for different agents to understand a codebase without needing a prior index.
What an agent can do with it
- 1Automate skill directory creationGenerate a new directory containing a SKILL.md and reference files based on an existing software project.
- 2Map project entry pointsIdentify and list all declared entry points such as modules, types, and binaries from a project manifest.
- 3Ensure cross-agent portabilityVerify that the generated skill works across different agents like Claude Code or Gemini CLI by testing specific tasks.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the generate-project-skill skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the generate-project-skill skill in Plugin
/plugin marketplace add skilld-dev/skilld /plugin install skilld@skilld
Install the generate-project-skill skill in Claude Code
~/.claude/skills/generate-project-skill/SKILL.md
$ npx degit skilld-dev/skilld/skills/generate-project-skill ~/.claude/skills/generate-project-skillInstall the generate-project-skill skill in Claude Code (project)
.claude/skills/generate-project-skill/SKILL.md
$ npx degit skilld-dev/skilld/skills/generate-project-skill .claude/skills/generate-project-skillInstall the generate-project-skill skill in Codex
~/.agents/skills/generate-project-skill/SKILL.md
$ npx degit skilld-dev/skilld/skills/generate-project-skill ~/.agents/skills/generate-project-skillInstall the generate-project-skill skill in Gemini CLI
~/.gemini/skills/generate-project-skill/SKILL.md
$ npx degit skilld-dev/skilld/skills/generate-project-skill ~/.gemini/skills/generate-project-skillInstall the generate-project-skill skill in Claude.ai
npx degit skilld-dev/skilld/skills/generate-project-skill generate-project-skill && zip -r generate-project-skill.zip generate-project-skill # claude.ai → Customize → Skills → + → Create skill → Upload a skill → generate-project-skill.zip
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work · What to fix for more points
- Source repository linked and reachableskilld-dev/skilld/skills/generate-project-skill is public and reachablegithub.com/skilld-dev/skilld/tree/HEAD/skills/generate-proje ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-10-10github.com/skilld-dev/skilld/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/skilld-dev/skilld/blob/HEAD/skills/generate-proje ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/skilld-dev/skilld/blob/HEAD/skills/generate-proje ↗Pass
- SKILL.md follows the Agent Skills formatthe description does not say when to use the skillgithub.com/skilld-dev/skilld/blob/HEAD/skills/generate-proje ↗Finding
SKILL.md
View on GitHubGenerate a project Skill
Create a compact, searchable Skill from the project itself. This Skill is for maintainers who author a draft Skill they own.
Inputs
Use the project directory or prepared project source. Ask for the destination only when the request does not provide one.
Inspect
- Read project instructions and decision records first.
- Read manifests, exported entry points, and build configuration.
- Find the test, lint, typecheck, build, and release commands.
- Trace the main public workflows through their real entry points.
- Note generated directories and files an Agent must not edit.
- Check recent changes when they explain current conventions.
Project navigation
The Skill must let an Agent find any part of the project without a prior index.
- Name the project from its manifest. Use the directory name when no manifest names it.
- List the entry points the manifest declares, such as
main,module,types,exports, andbin. - List the source and documentation directories an Agent reads most.
- Use project-relative paths for every file pointer.
- Never add a generated directory prefix to a project-relative path.
- Give search commands the Agent can repeat, scoped to those directories.
- Prefer
rgfor search. Name the directories to skip in the command. - Tell the Agent when project changes require a new Skill run.
Write the search commands so their results point at real project files.
Skip these paths while collecting project files:
- version-control data, such as
.git - dependency directories, such as
node_modulesandvendor - generated output, such as
dist,build,target,.output,.nuxt, and.next - caches and reports, such as
coverage - credential files, such as
.envand any private key
Skip any file larger than 512 KB. Do not follow symbolic links while collecting project files.
Output
Write one directory whose name matches the Skill name.
The directory must contain SKILL.md.
Use references/ for architecture details and command guides.
Use scripts/ only for reusable automation.
The SKILL.md frontmatter contains name and description. It may also contain license, compatibility, metadata, and allowed-tools.
If the project declares a license, copy its identifier into license. Never infer a license.
Include compatibility only for specific tool, runtime, network, or product requirements, at most 500 characters.
Omit it for general guidance. Do not repeat the package name, tested version, or implementation details.
metadata maps string keys to string values. allowed-tools is an experimental space-separated string of pre-approved tools.
Use lowercase letters, numbers, and single hyphens in the name.
Keep the name at 64 characters or fewer.
Cross-Agent portability
Keep one source Skill for Claude Code, Codex, Gemini CLI, and other compatible Agents. Their discovery paths differ. Keep installation instructions outside the generated Skill. The Agent Skills specification defines the shared format.
- Describe capabilities, such as reading files or running a command, instead of provider-specific tool names.
- Ask for inputs explicitly. Do not require
$ARGUMENTS, dynamic context injection, hooks, or a specific subagent API. - State the project root as the working directory for project commands. Resolve bundled references and scripts from the Skill directory instead.
- Name required runtimes, binaries, network access, and credentials beside the step that needs them.
- If a required capability is unavailable, report the missing capability and stop that dependent step. Never invent evidence or silently skip a required check.
Check one matching task, one unrelated task, and one missing-input task. Use a fresh session for each Agent the user asks to support when those Agents are available. Record the Agent version, model, task, observed output, and any required permission. Separate format validation, discovery, activation, and task completion in the report. If an Agent is unavailable, report that path untested. Valid frontmatter alone does not prove portability.
Quality checks
- Describe when the Skill applies.
- Do not explain the language, framework, or tools. The reader already knows them.
- Use project terms exactly.
- Point to source files instead of copying them.
- Run project commands only when they add useful evidence.
- Record the observed command and outcome.
- Include repeatable search commands for project source and documentation.
- Keep file pointers rooted at the real project directory.
- Separate rules from optional guidance.
- Remove stale, inferred, or duplicated instructions.
- Link each reference from
SKILL.md.
For a direct run, show the generated files for user review. Do not replace an existing Skill until the user approves it. Do not claim that the Skill passed Harness checks.
Files in this skill
2generate-project-skill skill questions
How do I install the generate-project-skill skill in Claude Code?
Run npx degit skilld-dev/skilld/skills/generate-project-skill ~/.claude/skills/generate-project-skill. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the generate-project-skill skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What files should be excluded when collecting project files for the Skill?
The process skips version control data, dependency directories, generated output, caches, reports, credential files, and any file larger than 512 KB.
How should the generated Skill handle project navigation?
The Skill enables an Agent to find any part of the project without a prior index by using project-relative paths, listing entry points, and providing repeatable search commands like rg.
What is the required output structure for the generated Skill?
The output is a single directory matching the Skill name containing a SKILL.md file, with references/ for architecture and scripts/ for reusable automation.