Claude Automation Recommender
anthropics/claude-plugins-official
Scans a codebase and suggests which Claude Code hooks, subagents, skills, plugins and MCP servers fit its stack, without changing any files.
Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for…
Install Lc Curate Context
$ npx skills add cyberchitta/llm-context.py --skill lc-curate-context -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cyberchitta/llm-context.py lc-curate-context --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cyberchitta/llm-context.py.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/llm_context/lc_resources/skills/lc-curate-context .claude/skills/lc-curate-context && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "lc-curate-context" agent skill from https://github.com/cyberchitta/llm-context.py/tree/main/src/llm_context/lc_resources/skills/lc-curate-context into .claude/skills/lc-curate-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lc-curate-context", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cyberchitta/llm-context.py/tree/main/src/llm_context/lc_resources/skills/lc-curate-contextType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cyberchitta/llm-context.py --skill lc-curate-context -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cyberchitta/llm-context.py lc-curate-context --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberchitta/llm-context.py.git skills-src && mkdir -p .agents/skills && cp -r skills-src/src/llm_context/lc_resources/skills/lc-curate-context .agents/skills/lc-curate-context && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "lc-curate-context" agent skill from https://github.com/cyberchitta/llm-context.py/tree/main/src/llm_context/lc_resources/skills/lc-curate-context into .agents/skills/lc-curate-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lc-curate-context", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cyberchitta/llm-context.py --skill lc-curate-context -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cyberchitta/llm-context.py lc-curate-context --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberchitta/llm-context.py.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/src/llm_context/lc_resources/skills/lc-curate-context .cursor/skills/lc-curate-context && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "lc-curate-context" agent skill from https://github.com/cyberchitta/llm-context.py/tree/main/src/llm_context/lc_resources/skills/lc-curate-context into .cursor/skills/lc-curate-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lc-curate-context", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cyberchitta/llm-context.py.git --path src/llm_context/lc_resources/skills/lc-curate-context--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cyberchitta/llm-context.py --skill lc-curate-context -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cyberchitta/llm-context.py lc-curate-context --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberchitta/llm-context.py.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/src/llm_context/lc_resources/skills/lc-curate-context .gemini/skills/lc-curate-context && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "lc-curate-context" agent skill from https://github.com/cyberchitta/llm-context.py/tree/main/src/llm_context/lc_resources/skills/lc-curate-context into .gemini/skills/lc-curate-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lc-curate-context", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cyberchitta/llm-context.py lc-curate-contextInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cyberchitta/llm-context.py --skill lc-curate-context -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cyberchitta/llm-context.py.git skills-src && mkdir -p .github/skills && cp -r skills-src/src/llm_context/lc_resources/skills/lc-curate-context .github/skills/lc-curate-context && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "lc-curate-context" agent skill from https://github.com/cyberchitta/llm-context.py/tree/main/src/llm_context/lc_resources/skills/lc-curate-context into .github/skills/lc-curate-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lc-curate-context", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cyberchitta/llm-context.py --skill lc-curate-context -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cyberchitta/llm-context.py lc-curate-context --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberchitta/llm-context.py.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/src/llm_context/lc_resources/skills/lc-curate-context .opencode/skills/lc-curate-context && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "lc-curate-context" agent skill from https://github.com/cyberchitta/llm-context.py/tree/main/src/llm_context/lc_resources/skills/lc-curate-context into .opencode/skills/lc-curate-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lc-curate-context", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
lc-curate-context- GitHub stars
- 307
- Token cost
- ~1.5k tokens
- SKILL.md length
- 823 words
- Files
- 6
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for…
- Works in 7 steps: Understand the task in concrete file… → Pick the narrowest sensible baseline… → Put files you expect to edit in… → …
- Tasks that involve Subagents
- SKILL.md covers Workflow, Pick the Baseline First, Full vs Excerpted and Verify with lc-preview, plus 5 more sections
- Calls claude
What it does
Lc Curate Context is an agent skill from cyberchitta/llm-context.py. Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing files for a sub-agent, or when a rule selects too much or too little.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `COMMANDS.md`, `EXAMPLES.md` and `PATTERNS.md`).
It sits in Agent Workflows, covering Subagents. It works with Model Context Protocol. The repository describes itself as: Share code with LLMs via Model Context Protocol or clipboard. Rule-based customization enables easy switching between different tasks (like code review and documentation)… The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Subagents
Example prompts
- “/lc-curate-context”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Understand the task in concrete file terms.
- Pick the narrowest sensible baseline filter (see below).
- Put files you expect to edit in full-files.
- Put callers, dependencies, and large reference files in excerpted-files.
- Run lc-preview -r . Read the exact Full files / Excerpted files lists, then Referenced but not selected.
- Tighten until the selection is minimal and sufficient.
- Generate the real output once before handing the rule off — lc-context -r — and confirm it contains file bodies, not just a tree.
What it can do on your machine
Read from SKILL.md and the folder at commit 6ab2ff1. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
claude
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Lc Curate Context loads about 1.5k tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 823 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from cyberchitta/llm-context.py at commit 6ab2ff1, republished under its Apache-2.0 licence (© cyberchitta). 823 words, ~1,483 tokens.
Download SKILL.mdSave it as
.claude/skills/lc-curate-context/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- lc-curate-context
- description
- Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing files for a sub-agent, or when a rule selects too much or too little.
Context Descriptor Creation
Three jobs, in order: decide what a task needs, verify the decision against the codebase, pack it for whoever is reading.
The first is not "gather a lot of relevant code" — it is to produce the smallest full-file and excerpted-file set that is still enough to finish the task. The second is what lc-preview is for, and it is not optional: a rule that looks right and omits the module its edit targets call will fail quietly. The third depends on the consumer, and getting it wrong is also quiet — see "Packing for a Sub-Agent".
Workflow
- Understand the task in concrete file terms.
- Pick the narrowest sensible baseline filter (see below).
- Put files you expect to edit in
full-files. - Put callers, dependencies, and large reference files in
excerpted-files. - Run
lc-preview -r <rule>. Read the exactFull files/Excerpted fileslists, thenReferenced but not selected. - Tighten until the selection is minimal and sufficient.
- Generate the real output once before handing the rule off —
lc-context -r <rule>— and confirm it contains file bodies, not just a tree.
Pick the Baseline First
Start narrow unless you have a reason not to.
| Baseline | Use when |
|---|---|
lc/flt-no-files | Surgical task; you know the likely files; you want exact control over membership. Default for task rules. |
flt-repo-base or lc/flt-base | Broad project slice; the task spans a subsystem; the repo already has a disciplined baseline filter. |
If lc-preview shows unexpected full files, the baseline is too broad.
Full vs Excerpted
Full — files you expect to edit; small configs or templates that control the behaviour; compact integration points where exact code matters.
Excerpted — callers and dependencies; large modules where structure is enough; reference implementations and surrounding architecture.
Move a file from excerpted to full only when the exact body matters.
Verify with lc-preview
Read Summary, then Full files, then Excerpted files, and ask:
- Are all expected edit targets in
Full files? - Did anything unrelated leak into
Full files? - Are context files in
Excerpted filesrather thanFull files? - Is the total small enough for the task?
Do not trust a rule until the exact file lists look right.
Referenced but not selected
lc-preview also lists files that define symbols your selection uses but which the rule does not include, ranked by how many. This is the check for the failure the file lists cannot show you: a rule that looks tidy but omits the module its edit targets actually call.
Add the ones the task needs. Leave the rest — they stay reachable through lc-missing, and pulling in everything reachable is how a minimal rule turns into the whole repo. Matching is by symbol name, so a common name may point at the wrong file; treat the list as a hint, not a checklist.
Show full SKILL.md (358 more words)Show less
Packing for a Sub-Agent
A rule is also how you hand a task to a disposable child agent. The dispatcher writes the prompt; llm-context supplies the files.
lc-context -r tmp-prm-auth -a | claude -p 'Your task here'-r is what routes output to stdout; without it lc-context copies to the clipboard instead. This is the difference between a working pipe and an empty one — see COMMANDS.md.
Three things decide whether the pack is usable:
-ais not optional. It tells the pack its reader is an agent with a shell, so the fetch instructions render aslc-missingcommands the child runs itself. The default renders MCP tool calls it has no server for;-ntrenders shell commands addressed to "the user", which it will not act on. Run the child from the repo root so those commands resolve.- The pack is always partial. The file listing is filtered by the repo's
.gitignorefiles and by the rule'soverview-filesignores before anything is even marked excluded, so files exist that the listing never mentions. A tooled child will find them. That is expected, not a contradiction. - Whole-files passes should check the header, not the rule. The generated context states how many files are full, outlined, and excerpted. If a pass depends on complete files with no excerpts, assert the outlined and excerpted counts are zero in the output rather than trusting that a filter is still configured.
See PATTERNS.md "Pack for a disposable sub-agent" for the rule shape.
Path Rules
In rule patterns, paths start with /, relative to project root:
- "/src/llm_context/rule.py"
- "/tests/test_outliner.py"Preview and generated context show namespaced paths like /{project-name}/src/....
File Naming
tmp-prm-<name>.md— temporary task ruleprm-<name>.md— reusable prompt ruleflt-<name>.md— reusable filter primitive
Feedback
Log whenever something here is awkward, buggy, missing, surprising, or took more work than it should.
- Don't filter — the maintainer triages. Patterns only emerge from honest individual observations.
- Write it to the field-notes destination declared in the project's
CLAUDE.md. If the project declares none, say so once and move on. - Log first; worry about whether it generalizes later.
References
COMMANDS.md— CLI and MCP command referenceSYNTAX.md— rule file schema and field detailsPATTERNS.md— reusable rule shapesEXAMPLES.md— worked examples from this repoTROUBLESHOOTING.md— failure cases
© cyberchitta, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files in src/llm_context/lc_resources/skills/lc-curate-context of cyberchitta/llm-context.py.
- SKILL.md
- COMMANDS.md
- EXAMPLES.md
- PATTERNS.md
- SYNTAX.md
- TROUBLESHOOTING.md
Open the folder on GitHubat commit 6ab2ff1
Compare with similar skills
Lc Curate Context next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Lc Curate Context this skillcyberchitta/llm-context.py | 307 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Claude Automation Recommenderanthropics/claude-plugins-official | 38k | 3 repos | ~2.7k | Automated safety check: Notes | Apache-2.0 | |
| CC Workflow Studio AI Editorbreaking-brake/cc-wf-studio | 5.4k | — | ~561 | Automated safety check: Pass | Custom licence | |
| Agent Deckasheshgoplani/agent-deck | 1.1k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Clone App Pat Proper-simmons/clone-app-pat-pro-public | 259 | — | ~1.9k | Automated safety check: Notes | None | |
| Bootstrapinfragate/capa | 724 | — | ~5.9k | Automated safety check: Pass | MIT |
Similar skills
- Official
CC Workflow Studio AI Editor
breaking-brake/cc-wf-studio
Creates and edits visual agent workflows in CC Workflow Studio through conversation, with the agent reading and writing the canvas over MCP.
Agent Deck
asheshgoplani/agent-deck
agent-deck, the terminal session manager for AI coding agents.
Clone App Pat Pro
per-simmons/clone-app-pat-pro-public
Clones any web app pixel-for-pixel from a URL. An agent skill from per-simmons/clone-app-pat-pro-public.
Bootstrap
infragate/capa
Capify an existing project. An agent skill from infragate/capa.
Puppetmaster Agent Orchestration
professorpalmer/Puppetmaster
Operates and supervises Puppetmaster, a multi-agent orchestrator, through its MCP tools or CLI, picking the right verb for edits, reviews, audits and long-running jobs.
Related
Works with
Categories
Questions about Lc Curate Context
What does Lc Curate Context do?
Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for…. py. Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch.
When should I use Lc Curate Context?
Lc Curate Context fits situations like: tasks that involve Subagents.
How do I install Lc Curate Context in Claude Code?
Run `npx skills add cyberchitta/llm-context.py --skill lc-curate-context -a claude-code`. Or copy the skill folder (src/llm_context/lc_resources/skills/lc-curate-context in cyberchitta/llm-context.py) into .claude/skills/lc-curate-context in your project. Claude Code loads it when a task matches its description.
How do I install Lc Curate Context in Codex?
Run `npx skills add cyberchitta/llm-context.py --skill lc-curate-context -a codex`. Or copy the skill folder (src/llm_context/lc_resources/skills/lc-curate-context in cyberchitta/llm-context.py) into .agents/skills/lc-curate-context in your project. Codex loads it when a task matches its description.
Can I use Lc Curate Context in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cyberchitta/llm-context.py --skill lc-curate-context -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lc-curate-context, .gemini/skills/lc-curate-context, .github/skills/lc-curate-context and .opencode/skills/lc-curate-context in your project.
What does Lc Curate Context need to run?
Going by SKILL.md and its folder, Lc Curate Context needs the command-line tools its instructions call (claude).
Does Lc Curate Context access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Lc Curate Context safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Lc Curate Context use?
Lc Curate Context is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Lc Curate Context use?
About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Lc Curate Context?
Skills that share tags, products or a category with Lc Curate Context: Claude Automation Recommender (anthropics/claude-plugins-official, 38k stars), CC Workflow Studio AI Editor (breaking-brake/cc-wf-studio, 5.4k stars), Agent Deck (asheshgoplani/agent-deck, 1.1k stars) and Clone App Pat Pro (per-simmons/clone-app-pat-pro-public, 259 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Lc Curate Context?
cyberchitta (a GitHub organization) maintains it in cyberchitta/llm-context.py, which has 307 GitHub stars. The repository was last updated on August 26, 2026.
Source: cyberchitta/llm-context.py on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.