Agent skill

Ecosystem Analysis

by prime-radiant-inc in prime-radiant-inc/greenfield

Layer 1 skill for SDK and ecosystem analysis. An agent skill from prime-radiant-inc/greenfield.

Apache-2.0Auto-check passedTesting & QA

Install Ecosystem Analysis

skills CLI
$ npx skills add prime-radiant-inc/greenfield --skill ecosystem-analysis -a claude-code

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

GitHub CLI
$ gh skill install prime-radiant-inc/greenfield ecosystem-analysis --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/prime-radiant-inc/greenfield.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ecosystem-analysis .claude/skills/ecosystem-analysis && 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
ecosystem-analysis
GitHub stars
292
Token cost
~2.9k tokens
SKILL.md length
982 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
Apache-2.0

At a glance

Layer 1 skill for SDK and ecosystem analysis. An agent skill from prime-radiant-inc/greenfield.

  • Works in 2 steps: Target's documentation -- "Client… → Package registries -- search for the…
  • Tasks that involve Integration testing
  • SKILL.md covers When to Use This Mode, Source Origin, Agents and SDK Discovery Strategy, plus 6 more sections
  • Reaches npmjs.com and github.com

What it does

Ecosystem Analysis is an agent skill from prime-radiant-inc/greenfield. Layer 1 skill for SDK and ecosystem analysis. SDK discovery strategy, behavioral extraction methodology, integration test mining, output formats. Loaded by the analyzer agent for SDK and ecosystem work.

Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Integration testing. The repository describes itself as: A Claude Code plugin that reverse-engineers clean behavioral specs, test vectors, and acceptance criteria from any codebase, producing a provenance trail so a fresh team can… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Integration testing

Example prompts

  • “/ecosystem-analysis”

Requirements

  • Python 3

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Target's documentation -- "Client Libraries", "SDKs", "Getting Started" pages
  2. Package registries -- search for the target name on

What it can do on your machine

Read from SKILL.md and the folder at commit 6e6d4b4. 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 dot and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • npmjs.com
    • github.com
    • pypi.org
    • crates.io
    • search.maven.org
    • nuget.org
    • rubygems.org
    • pkg.go.dev
    • hex.pm
    • packagist.org

    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

Ecosystem Analysis loads about 2.9k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 982 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

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 prime-radiant-inc/greenfield at commit 6e6d4b4, republished under its Apache-2.0 licence (© prime-radiant-inc). 982 words, ~2,890 tokens.

Download SKILL.mdSave it as .claude/skills/ecosystem-analysis/SKILL.md (or your agent's skills folder).
name
ecosystem-analysis
description
Layer 1 skill for SDK and ecosystem analysis. SDK discovery strategy, behavioral extraction methodology, integration test mining, output formats. Loaded by the analyzer agent for SDK and ecosystem work.

Ecosystem Analysis

Extract behavioral specifications from third-party SDKs, client libraries, and ecosystem tooling. Every SDK that consumes the target's APIs encodes behavioral assumptions in executable logic -- the strongest form of specification.

When to Use This Mode

Use SDK/Ecosystem mode when the target product has:

  • Public APIs consumed by third-party client libraries
  • Official SDKs published on package registries
  • Community-maintained client libraries on GitHub/GitLab
  • Open-source integrations or plugins that interact with the target

This mode runs independently of all other intelligence sources. It requires no source code access, no runtime execution, and no container. It needs only network access to package registries and code hosting platforms.

Targets without a public SDK or third-party client ecosystem get no useful signal from this mode — skip it.

Source Origin

SDK analysis draws only from published artifacts — client libraries on package registries, open-source community integrations, and the examples in official documentation. Nothing in this mode reads the target's source code; all inputs are material the target's vendor has already published for third-party developers to consume.

All SDK-derived intelligence is public origin and goes to workspace/public/ecosystem/.

Agents

AgentPurposeOutput
sdk-analyzerDiscover and analyze SDK source code for behavioral assumptionsworkspace/public/ecosystem/sdks/
integration-test-minerExtract test vectors from SDK test suites and fixturesworkspace/public/ecosystem/tests/

Run sdk-analyzer first (it produces the SDK inventory), then integration-test-miner (it uses the inventory to find test suites).

SDK Discovery Strategy

dot
digraph sdk_discovery {
    rankdir=TB;

    "Start SDK discovery" [shape=doublecircle];
    "Search target docs for SDK links" [shape=box];
    "Search package registries" [shape=box];
    "Search GitHub/GitLab for client libraries" [shape=box];
    "Classify each SDK: official vs community" [shape=box];
    "Is it a wrapper SDK?" [shape=diamond];
    "Is it stale (>2 years)?" [shape=diamond];
    "Add to SDK inventory" [shape=box];
    "Exclude from analysis" [shape=ellipse];
    "Extract behavioral claims from SDK source" [shape=box];
    "Mine integration tests for test vectors" [shape=box];
    "Build cross-SDK consensus report" [shape=box];
    "Discovery complete" [shape=doublecircle];

    "Start SDK discovery" -> "Search target docs for SDK links";
    "Search target docs for SDK links" -> "Search package registries";
    "Search package registries" -> "Search GitHub/GitLab for client libraries";
    "Search GitHub/GitLab for client libraries" -> "Classify each SDK: official vs community";
    "Classify each SDK: official vs community" -> "Is it a wrapper SDK?";
    "Is it a wrapper SDK?" -> "Exclude from analysis" [label="yes"];
    "Is it a wrapper SDK?" -> "Is it stale (>2 years)?" [label="no"];
    "Is it stale (>2 years)?" -> "Exclude from analysis" [label="yes"];
    "Is it stale (>2 years)?" -> "Add to SDK inventory" [label="no"];
    "Add to SDK inventory" -> "Extract behavioral claims from SDK source";
    "Extract behavioral claims from SDK source" -> "Mine integration tests for test vectors";
    "Mine integration tests for test vectors" -> "Build cross-SDK consensus report";
    "Build cross-SDK consensus report" -> "Discovery complete";
}
Discovery Sources (Priority Order)
  1. Target's documentation -- "Client Libraries", "SDKs", "Getting Started" pages
  2. Package registries -- search for the target name on:
RegistryLanguageSearch Pattern
npmJavaScript/TypeScripthttps://www.npmjs.com/search?q={target}
PyPIPythonhttps://pypi.org/search/?q={target}
crates.ioRusthttps://crates.io/search?q={target}
Maven CentralJava/Kotlinhttps://search.maven.org/search?q={target}
NuGetC#/.NEThttps://www.nuget.org/packages?q={target}
RubyGemsRubyhttps://rubygems.org/search?query={target}
pkg.go.devGohttps://pkg.go.dev/search?q={target}
Hex.pmElixirhttps://hex.pm/packages?search={target}
PackagistPHPhttps://packagist.org/?query={target}
  1. GitHub/GitLab -- search topics, code search for import statements
  2. Web search -- '{target} SDK', '{target} client library'
SDK Classification

For each discovered SDK, record: name, language, type (official/community), version, repository URL, package registry URL, last updated date, downloads/stars, maintainer, target API version, license.

Prioritization
  1. Official SDKs first -- maintained by the target's organization, most accurate
  2. Most-downloaded community SDKs -- download count correlates with community vetting
  3. Recently updated over stale -- packages >2 years old may target deprecated APIs
  4. Multiple languages -- analyzing the same API from 3+ languages provides cross-language corroboration
Exclusion Criteria
  • Wrapper SDKs that depend on another SDK (check dependencies). Not independent sources.
  • Stale packages last updated >2 years ago. May reflect deprecated API versions.
  • Minimal wrappers with few stars/downloads and negligible behavioral content.

Behavioral Extraction Methodology

What SDKs Reveal
CategoryWhat to Look ForHow to Find It
API SurfaceEndpoint URLs, HTTP methods, URL patternsHTTP method calls, URL string literals, route constants
Request SchemasField names, types, required/optional, constraintsObject construction near HTTP calls, TypeScript interfaces, validation logic
Response SchemasParsed fields, types, structureResponse type definitions, JSON deserialization, field access patterns
AuthenticationToken types, header names, credential flowsAuthorization header, auth middleware, constructor parameters
Error HandlingError codes, types, response formatCustom exception classes, error parsing, status code handling
Retry/BackoffRetryable codes, backoff algorithm, retry headersRetry loops, Retry-After parsing, backoff calculation
VersioningAPI version in URL or headersVersion strings in paths, version headers
PaginationCursor/offset patterns, page sizeIterator classes, after/cursor/limit parameters
StreamingSSE/WebSocket, event types, terminationSSE parsing, WebSocket handling, [DONE] signals
TimeoutsDefault values, timeout configurationClient construction defaults, timeout override mechanisms
Extraction Rules
  • One claim per extraction. Do not combine multiple behavioral observations into a single claim.
  • Cite the specific file and line. ref=https://github.com/org/repo/blob/v1.0.0/src/client.ts#L42
  • Distinguish required from optional. If a field is only sent conditionally, it is optional.
  • Record defaults. If the SDK uses a default value for a parameter, that default is behavioral intelligence.
  • Note constraints. Validation logic reveals constraints (min/max, allowed values, format requirements).
Show full SKILL.md (365 more words)Show less
Confidence Rules
  • Single SDK claim = inferred. One SDK author's assumption is not confirmed.
  • 2+ SDKs agree = confirmed. Independent implementations reaching the same conclusion is strong evidence.
  • SDKs disagree = both remain inferred. Record both claims with a disagreement note.
  • Wrapper SDKs do not count for consensus. They are not independent sources.

Integration Test Mining

Test Classification
TypeValueCharacteristics
Integration testsHIGHCall the real target API or use recorded responses
Fixture-based testsHIGHESTContain recorded HTTP interactions (literal target responses)
Unit tests (mocked)LOWMock the target's responses; reveal SDK assumptions only
Where to Find Tests
  • Test directories: test/, tests/, __tests__/, spec/, specs/, test_*/, *_test/, integration/
  • Test frameworks: check package.json (Jest, Mocha, Vitest), setup.py/pyproject.toml (pytest), Cargo.toml (cargo test), pom.xml (JUnit)
  • Fixture formats: VCR cassettes (.yml in cassettes/), Polly recordings, nock fixtures (.json), httpretty recordings
What to Extract from Each Test
  1. The behavioral claim -- what does this test prove about the target?
  2. Concrete input -- HTTP method, path, headers, body
  3. Expected output -- status code, headers, body structure, specific values
  4. Provenance -- test file path and line number
Test Vector Format
markdown
### TV-SDK-{NNN}: {descriptive name}

**Source:** {sdk-name}, {file}:{line}
<!-- cite: source=sdk-analysis, ref={url}, confidence=inferred, agent=integration-test-miner -->

**Input:**
[JSON: method, path, headers, body]

**Expected Output:**
[JSON: status, headers, body]

**Behavioral claim:** {what this test proves}

Output Structure

workspace/public/ecosystem/
+-- sdk-inventory.md              # All SDKs discovered
+-- sdks/
|   +-- {sdk-name}/
|       +-- analysis.md           # Full behavioral extraction
+-- tests/
|   +-- test-inventory.md         # All test suites found
|   +-- extracted-vectors.md      # Test cases as behavioral claims
|   +-- fixtures/
|       +-- {sdk-name}/           # Analyzed fixture content
+-- consensus.md                  # Multi-SDK agreement/disagreement

Provenance

All citations use source=sdk-analysis. Ref format for GitHub-hosted SDKs:

ref=https://github.com/{org}/{repo}/blob/{version}/{file}#{line}

For package registry sources:

ref=https://www.npmjs.com/package/{name}/v/{version}

Initial confidence is inferred (single SDK). Escalates to confirmed through:

  • Multi-SDK consensus (2+ independent SDKs agree)
  • Cross-mode corroboration (docs, runtime observation, or source code analysis confirms the SDK claim)

Challenges and Mitigations

ChallengeMitigation
Outdated SDKsRecord version and date; prefer latest versions; cross-reference with other sources
SDK bugsAnalyze multiple SDKs; bugs in one are unlikely in independent implementations
Private/internal SDKsSkip entirely; analyze only publicly available code
Large SDK codebasesFocus on API client layer; ignore utilities, build scripts, docs generators
Auto-generated SDKsStill valuable (generated from an OpenAPI spec); look for hand-written patches
Wrapper SDKsIdentify by checking dependencies; exclude from consensus

Integration with Pipeline

SDK findings flow to Layer 2 synthesis:

  • feature-discoverer reads SDK inventory to understand API scope
  • architecture-analyst reads SDK analyses for API architecture and resource hierarchy
  • api-extractor reads SDK analyses for complete API surface and schemas
  • analysis-synthesizer merges SDK findings with other intelligence sources

SDK test vectors flow to Layer 4:

  • test-vector-generator incorporates SDK-mined vectors into the project's test vector suite

© prime-radiant-inc, 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 skills/ecosystem-analysis of prime-radiant-inc/greenfield.

Open the folder on GitHubat commit 6e6d4b4

Compare with similar skills

Ecosystem Analysis 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.

Ecosystem Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ecosystem Analysis this skillprime-radiant-inc/greenfield292—~2.9kAutomated safety check: PassApache-2.0
Plugin Testingpolyipseity/obsidian-terminal951—~828Automated safety check: PassAGPL-3.0
Create Modulecartography-cncf/cartography4.1k—~2.5kAutomated safety check: PassApache-2.0
Td Integration Testmarcus/td251—~1.2kAutomated safety check: PassMIT
Integration E2E Testingshinpr/claude-code-workflows694—~3.5kAutomated safety check: PassMIT
JS-in-HTML Testingliaohch3/claude-tap3.3k—~924Automated safety check: PassMIT

Similar skills

  • Plugin Testing

    polyipseity/obsidian-terminal

    Skill for testing Obsidian plugin features in this repository.

    951 GitHub stars~828 tokensUpdated 6 days ago
    Testing & QAAuto-check passed
  • Create Module

    cartography-cncf/cartography

    Author a new Cartography intel module end-to-end (entry point, sync GET/TRANSFORM/LOAD/CLEANUP, declarative data model, integration test, schema docs).

    4.1k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check passed
  • Write integration tests for the td-sync admin API using the TestHarness in internal/api/testharnesstest.go.

    251 GitHub stars~1.2k tokensUpdated 9 days ago
    Testing & QAAuto-check passed
  • Integration E2E Testing

    shinpr/claude-code-workflows

    Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria.

    694 GitHub stars~3.5k tokensUpdated 8 days ago
    Testing & QAAuto-check passed
  • JS-in-HTML Testing

    liaohch3/claude-tap

    Tests JavaScript embedded in an HTML file in two layers: pytest checks of the logic ported to Python, and Playwright runs in a real browser for the DOM.

    3.3k GitHub stars~924 tokensUpdated today
    Testing & QAAuto-check passed
  • Add Acceptance Test

    talkincode/toughradius

    Write CI-executable acceptance/integration tests for protocol or end-to-end changes (TR-F022).

    691 GitHub stars~827 tokensUpdated yesterday
    Testing & QAAuto-check passed

More from prime-radiant-inc/greenfield

All 21 skills in this repo
  • Reverse Engineering Analysis Pipeline

    prime-radiant-inc/greenfield

    Master methodology for reverse-engineering a codebase into behavioral specs with cited evidence, reading every line across source, binaries, docs, runtime and git history.

    292 GitHub stars~3.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Community Intelligence Research

    prime-radiant-inc/greenfield

    Mines tutorials, forums, reviews, issues and changelogs for observed product behavior, using six search channels and consensus analysis.

    292 GitHub stars~4.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Containerized Target Execution

    prime-radiant-inc/greenfield

    Runs untrusted analysis targets inside Docker or Podman containers with memory, CPU and process limits, covering image builds, lifecycle, command execution and cleanup.

    292 GitHub stars~2.1k tokensUpdated 2 mo ago
    Auto-check passed
  • API Contract Detection

    prime-radiant-inc/greenfield

    Finds OpenAPI, GraphQL, Protobuf and JSON Schema files in a codebase and extracts behavioral claims from them as part of a reverse-engineering workflow.

    292 GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Documentation Research Methodology

    prime-radiant-inc/greenfield

    Method for extracting behavioral specifications from a product's public documentation: tiered search order, claim extraction rules, output structure, stop criteria and gap analysis.

    292 GitHub stars~4.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Fidelity Validation

    prime-radiant-inc/greenfield

    Cross-validates sanitized output specs against raw source specs to detect lost behavioral detail, dropped constants, missing features, or diluted precision.

    292 GitHub stars~1.8k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Ecosystem Analysis

What does Ecosystem Analysis do?

Layer 1 skill for SDK and ecosystem analysis. An agent skill from prime-radiant-inc/greenfield. Ecosystem Analysis is an agent skill from prime-radiant-inc/greenfield. Layer 1 skill for SDK and ecosystem analysis.

When should I use Ecosystem Analysis?

Ecosystem Analysis fits situations like: tasks that involve Integration testing.

How do I install Ecosystem Analysis in Claude Code?

Run `npx skills add prime-radiant-inc/greenfield --skill ecosystem-analysis -a claude-code`. Or copy the skill folder (skills/ecosystem-analysis in prime-radiant-inc/greenfield) into .claude/skills/ecosystem-analysis in your project. Claude Code loads it when a task matches its description.

How do I install Ecosystem Analysis in Codex?

Run `npx skills add prime-radiant-inc/greenfield --skill ecosystem-analysis -a codex`. Or copy the skill folder (skills/ecosystem-analysis in prime-radiant-inc/greenfield) into .agents/skills/ecosystem-analysis in your project. Codex loads it when a task matches its description.

Can I use Ecosystem Analysis 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 prime-radiant-inc/greenfield --skill ecosystem-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ecosystem-analysis, .gemini/skills/ecosystem-analysis, .github/skills/ecosystem-analysis and .opencode/skills/ecosystem-analysis in your project.

What does Ecosystem Analysis need to run?

SKILL.md names no scripts, command-line tools or credentials: Ecosystem Analysis is instructions for the agent only. Our summary lists: Python 3.

Does Ecosystem Analysis access the network?

SKILL.md names 10 domains. In commands or code: npmjs.com, github.com, pypi.org, crates.io, search.maven.org, nuget.org, rubygems.org, pkg.go.dev, hex.pm and packagist.org; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Ecosystem Analysis 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 Ecosystem Analysis use?

Ecosystem Analysis 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 Ecosystem Analysis use?

About 2.9k tokens (SKILL.md is roughly 12k 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 Ecosystem Analysis?

Skills that share tags, products or a category with Ecosystem Analysis: Plugin Testing (polyipseity/obsidian-terminal, 951 stars), Create Module (cartography-cncf/cartography, 4.1k stars), Td Integration Test (marcus/td, 251 stars) and Integration E2E Testing (shinpr/claude-code-workflows, 694 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ecosystem Analysis?

prime-radiant-inc (a GitHub organization) maintains it in prime-radiant-inc/greenfield, which has 292 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on August 6, 2026.

Source: prime-radiant-inc/greenfield on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.