New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Pure Lsp Execute

by finos in finos/legend-engine

Runs exactly ONE existing Pure function by path (signature, mangled id or bare path) through the running Legend Pure LSP bridge, without a go() wrapper, and returns its typed value in returnValue.

Apache-2.0Auto-check passed

Install Pure Lsp Execute

skills CLI
$ npx skills add finos/legend-engine --skill pure-lsp-execute -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install finos/legend-engine pure-lsp-execute --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/finos/legend-engine.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/pure-dev/skills/pure-lsp-execute .claude/skills/pure-lsp-execute && rm -rf skills-src

Use ~/.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/

Facts

Skill name
pure-lsp-execute
GitHub stars
112
Token cost
~883 tokens
SKILL.md length
363 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
Apache-2.0

At a glance

Runs exactly ONE existing Pure function by path (signature, mangled id or bare path) through the running Legend Pure LSP bridge, without a go() wrapper, and returns its typed value in returnValue.

  • The user wants to run a specific function
  • SKILL.md covers Result, Options, PCT tests and Whole package or file, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • A single <<test.Test

What it does

Pure Lsp Execute is an agent skill from finos/legend-engine. Runs exactly ONE existing Pure function by path (signature, mangled id or bare path) through the running Legend Pure LSP bridge, without a go() wrapper, and returns its typed value in returnValue. Also runs every test in a package or .pure file serially with --package/--source. For 2 or more functions or tests, use pure-lsp-execute-parallel instead, never a shell loop of this command. Use when the user wants to run a specific function, a single <<test.Test or <<PCT.test, or the result of a Pure function.

Its SKILL.md is about 880 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is Apache-2.0.

When your agent uses it

  • The user wants to run a specific function
  • A single <<test.Test
  • The result of a Pure function

Example prompts

  • “/pure-lsp-execute”

What it can do on your machine

Read from SKILL.md and the folder at commit 00108b7. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    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

Pure Lsp Execute loads about 883 tokens when it runs. Until then it costs about 133 tokens; SKILL.md has 363 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~133
When it runs · the whole SKILL.md, loaded when a task matches
~883

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 finos/legend-engine at commit 00108b7, republished under its Apache-2.0 licence (© finos). 363 words, ~883 tokens.

Download SKILL.mdSave it as .claude/skills/pure-lsp-execute/SKILL.md (or your agent's skills folder).
name
pure-lsp-execute
description
Runs exactly ONE existing Pure function by path (signature, mangled id or bare path) through the running Legend Pure LSP bridge, without a go() wrapper, and returns its typed value in returnValue. Also runs every test in a package or .pure file serially with --package/--source. For 2 or more functions or tests, use pure-lsp-execute-parallel instead, never a shell loop of this command. Use when the user wants to run a specific function, a single <<test.Test>> or <<PCT.test>>, or the result of a Pure function.

Execute one function via the LSP bridge

Needs a running bridge (pure-lsp health). Use only the pure-lsp CLI, never curl; see references/lsp-devloop-usage-rules.md.

More than one function or test? Use pure-lsp-execute-parallel. Never loop this command in a shell for. Keep serial runs for tests that write to the shared H2 backend. For a quick snippet you are editing in welcome.pure, use pure-lsp-go.

bash
pure-lsp execute 'my::pkg::testFoo():Boolean[1]'

function is a signature, a mangled id (my::pkg::testFoo__Boolean_1_) or a bare path (zero-arg shapes only).

Result

output is only what the function printed. returnValue holds the function's value, so primitives, enums and collections of them need no print(). Also returned: returnKind (primitive|enum|collection|empty|complex), returnType, returnSize, returnTruncated (over 1000 elements). A complex return (Class instance, Relation, lambda) has a null value; print() what you need. String[1] returns a scalar, String[*] an array even with one element.

Options

  • Edited files compile first as one atomic batch, and the function runs only if it succeeds: pure-lsp execute 'my::pkg::t():Boolean[1]' Main.pure Helper.pure
  • String[1] parameters: --arg a --arg b, in order; name a signature or mangled id. String is the only supported parameter type; take other things as a String and resolve in Pure (an enum via extractEnumValue). One parameterised function over many argument sets: the invocations payload in pure-lsp-execute-parallel, as pure-sql-e2e does.
  • Setup/teardown around the function: --before my::pkg::setUp --after my::pkg::tearDown. <<test.BeforePackage>> hooks do not run on a direct execute, so grep the test's file for the hook and pass it as --before.
Show full SKILL.md (126 more words)Show less

PCT tests

A <<PCT.test>> takes the adapter function, so it needs its mangled id and --pct-adapter. The id is always <fqn>_Function_1__Boolean_1_:

bash
pure-lsp execute 'meta::pure::functions::relation::tests::extend::testSimpleExtendFloat_Function_1__Boolean_1_' --pct-adapter DuckDB

--pct-adapter accepts the adapter's path, simple name or display name; paths are in references/pct-adapters.md. Never run --source/--package just to find one test's id; that executes every test in the scope. For a whole package's PCT tests use --package <pkg> --pct-only --pct-adapter <path>; no ids needed.

Whole package or file

bash
pure-lsp execute --package meta::pure::functions::collection::tests
pure-lsp execute --source path/to/MyTests.pure

Flags, hook bracketing and the 30-test cap: references/test-scopes.md.

Notes

  • Compiles and runs against the whole loaded session, so an unrelated compile error fails this call too.
  • Runs interpreted unless the backend server is wired in; see pure-lsp-go "Execution routing".
  • On failure read output and error in full; the useful part is not always at the top.

© finos, 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

Just SKILL.md in plugins/pure-dev/skills/pure-lsp-execute of finos/legend-engine.

Open the folder on GitHubat commit 00108b7

Compare with similar skills

Pure Lsp Execute 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.

Pure Lsp Execute compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pure Lsp Execute this skillfinos/legend-engine112—~883Automated safety check: PassApache-2.0
Lspcode-yeongyu/oh-my-openagent70k—~304Automated safety check: PassCustom licence
Executealirezarezvani/claude-skills28k—~831Automated safety check: PassMIT
Debugging Executionsn8n-io/n8n207k—~2.6kAutomated safety check: PassCustom licence
Performing Serverless Function Security Reviewmukul975/Anthropic-Cybersecurity-Skills34k—~3.1kAutomated safety check: PassApache-2.0
Azure Functionsdavila7/claude-code-templates32k2 repos~344Automated safety check: PassMIT

Similar skills

  • Lsp

    code-yeongyu/oh-my-openagent

    A skill your agent uses when Codex needs language-server diagnostics, definitions, references, symbols, or rename safety checks in the current workspace.

    70k GitHub stars~304 tokensUpdated today
    Auto-check passed

  • Execute

    alirezarezvani/claude-skills

    /cs:execute <decision — Generate a 90-day execution plan with weekly milestones, DRIs, and check-in cadence from an approved decision.

    28k GitHub stars~831 tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed

  • Debugging Executions

    n8n-io/n8n

    Official

    Debug failed or wrong-output workflow executions using executions tools.

    207k GitHub stars~2.6k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Performing Serverless Function Security Review

    mukul975/Anthropic-Cybersecurity-Skills

    Performing security reviews of serverless functions across AWS Lambda, Azure Functions, and GCP Cloud Functions to identify overly permissive execution roles, insecure environment variables…

    34k GitHub stars~3.1k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed

  • Azure Functions

    davila7/claude-code-templates

    Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns.

    32k GitHub starsUsed in 2 repos~344 tokens
    Backend & APIsAuto-check passed

  • Ulw Execute

    code-yeongyu/oh-my-openagent

    Executes a written ulw-plan work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents.

    70k GitHub stars~6.3k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from finos/legend-engine

All 15 skills in this repo

  • Pure Backend Start

    finos/legend-engine

    Starts (or confirms) the standalone legend-engine backend - engine Server + H2 + local metadata server on fixed ports 9095/9092 - so a Pure LSP started with -Dlegend.test.

    112 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

  • Pure Chain Update

    finos/legend-engine

    Procedure for git-syncing and rebuilding a local legend-pure + legend-engine checkout, in dependency order, with pinned dependency versions resynced.

    112 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed

  • Pure Code Style

    finos/legend-engine

    Reformats a .pure file (or a block of Pure code) to a consistent house style: 2-space indentation with no column-aligned hanging indents, tight colons in type annotations, spaced pipes on…

    112 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed

  • Pure Lsp Check

    finos/legend-engine

    Compiles/checks a single .pure file against the already-running Legend Pure LSP bridge and reports diagnostics (errors/warnings) in under a second, as a fast alternative to a full mvn test/mvn…

    112 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

  • Pure Lsp Connect

    finos/legend-engine

    Attaches the pure-lsp HTTP bridge to an LSP daemon that is ALREADY running (e.g.

    112 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

  • Pure Lsp Execute Parallel

    finos/legend-engine

    Runs 2 to 30 Pure functions or tests concurrently on the warm LSP daemon via pure-lsp execute-parallel, or every test in a package or .pure file with --package/--source.

    112 GitHub stars~927 tokensUpdated yesterday
    Auto-check passed

Questions about Pure Lsp Execute

What does Pure Lsp Execute do?

Runs exactly ONE existing Pure function by path (signature, mangled id or bare path) through the running Legend Pure LSP bridge, without a go() wrapper, and returns its typed value in returnValue. Pure Lsp Execute is an agent skill from finos/legend-engine. Runs exactly ONE existing Pure function by path (signature, mangled id or bare path) through the running Legend Pure LSP bridge, without a go() wrapper, and returns its typed value in returnValue.

When should I use Pure Lsp Execute?

Pure Lsp Execute fits situations like: the user wants to run a specific function; A single <<test.Test; the result of a Pure function.

How do I install Pure Lsp Execute in Claude Code?

Run `npx skills add finos/legend-engine --skill pure-lsp-execute -a claude-code`. Or copy the skill folder (plugins/pure-dev/skills/pure-lsp-execute in finos/legend-engine) into .claude/skills/pure-lsp-execute in your project. Claude Code loads it when a task matches its description.

How do I install Pure Lsp Execute in Codex?

Run `npx skills add finos/legend-engine --skill pure-lsp-execute -a codex`. Or copy the skill folder (plugins/pure-dev/skills/pure-lsp-execute in finos/legend-engine) into .agents/skills/pure-lsp-execute in your project. Codex loads it when a task matches its description.

Can I use Pure Lsp Execute 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 finos/legend-engine --skill pure-lsp-execute -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pure-lsp-execute, .gemini/skills/pure-lsp-execute, .github/skills/pure-lsp-execute and .opencode/skills/pure-lsp-execute in your project.

What does Pure Lsp Execute need to run?

SKILL.md names no scripts, command-line tools or credentials: Pure Lsp Execute is instructions for the agent only.

Does Pure Lsp Execute 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 Pure Lsp Execute 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 Pure Lsp Execute use?

Pure Lsp Execute 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 Pure Lsp Execute use?

About 883 tokens (SKILL.md is roughly 3.5k 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 Pure Lsp Execute?

Skills that share tags, products or a category with Pure Lsp Execute: Lsp (code-yeongyu/oh-my-openagent, 70k stars), Execute (alirezarezvani/claude-skills, 28k stars), Debugging Executions (n8n-io/n8n, 207k stars) and Performing Serverless Function Security Review (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pure Lsp Execute?

finos (a GitHub organization) maintains it in finos/legend-engine, which has 112 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 7, 2026.

Source: finos/legend-engine on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.