open-supports-install
Skill4 starsChanged 6 months agoMITView on GitHub
Install or update open_supports packages for a project (-t) or user-wide (-g), one package (-n) or from a list, by using scripts/install-open-supports.sh.
In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- dot_claude/CLAUDE.mdCLAUDE.md
- dot_claude_legacy/CLAUDE.mdCLAUDE.md
- cache-designSkill
- db-schema-designSkill
- go-new-moduleSkill
- go-perf-diagnoseSkill
- mq-designSkill
- rpc-designSkill
- system-design-docSkill
- npm-codex-enotempty-repairSkill
- middleware-opsSkill
- github-releaseSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Use this Skill when the user asks to install, update, vendor, or inspect open_supports/ packages for a project.
- Very specific: line 16
Read the target project's .claude/open_supports_name_list.txt.
- Very specific: line 17
Read this repository's open_supports/README.md.
- Distinctive: line 21
Default to the current working directory as the target project when the user does not specify a target.
- Distinctive: line 24
Run from the rule source repository:
- Distinctive: line 59
If a custom list file is requested:
- Very specific: line 65
If a custom open_supports/ source root is requested:
- Distinctive: line 73
After the command finishes, report:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Open Supports Install
Use this Skill when the user asks to install, update, vendor, or inspect
open_supports/ packages for a project.
Pre-read
Before running commands:
- Read the target project's
.claude/open_supports_name_list.txt. - Read this repository's
open_supports/README.md.
Procedure
Default to the current working directory as the target project when the user does not specify a target.
Run from the rule source repository:
sh scripts/install-open-supports.sh -t /path/to/projectUseful modes:
sh scripts/install-open-supports.sh -t /path/to/project --dry-run
sh scripts/install-open-supports.sh -t /path/to/project --skills-only
sh scripts/install-open-supports.sh -t /path/to/project --no-skills
sh scripts/install-open-supports.sh -t /path/to/project -FInstall a single package instead of a list (arguments after --):
sh scripts/install-open-supports.sh -t /path/to/project -n colbymchenry/codegraph -- --target=claude --location=local {PROJECT_DIR}User-level (global) install: replace -t <project> with -g. It reads
~/.claude/open_supports_name_list.txt by default, runs install scripts from this
repository without vendoring, generates no wrapper Skill, rejects -F and
--skills-only, and refuses the whole list if any entry has {PROJECT_DIR},
--local, or --location=local. Always run --dry-run first and ask before a
real global install, because it changes user-level configuration:
sh scripts/install-open-supports.sh -g --dry-runTo copy the repository's global list to ~/.claude/ and install it in one step,
use sh scripts/install-claude-project.sh -g -d (drop -d after confirming).
If a custom list file is requested:
sh scripts/install-open-supports.sh -t /path/to/project -l /path/to/open_supports_name_list.txtIf a custom open_supports/ source root is requested:
sh scripts/install-open-supports.sh -t /path/to/project -s /path/to/open_supportsReporting
After the command finishes, report:
- which packages were vendored or reused;
- which wrapper Skills were generated or reused;
- which install scripts ran successfully;
- any
missing,no_script,failed, orconflictcounts; - the next command the user should run if the script reported manual follow-up.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

