grimoire-pendle

franalgaba/grimoire · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/franalgaba/grimoire --skill grimoire-pendle
0 commentsdiscussion
summary

Fetch Pendle SDK metadata and validate routing configuration via CLI commands.

  • Query supported chains, aggregators, markets, assets, and market token details from Pendle's hosted API
  • Six command categories: info , chains , supported-aggregators , markets , assets , and market-tokens with filtering by chain, activity status, and asset type
  • Supports JSON and table output formats; configurable API base URL via flag or environment variable
  • Preflight validation available through grimoi
skill.md

Grimoire Pendle Skill

Use this skill to inspect Pendle metadata and preflight Pendle routing configuration before running spells.

Preferred invocations:

  • grimoire venue pendle ...
  • npx -y @grimoirelabs/cli venue pendle ... (no-install)
  • bun run packages/cli/src/index.ts venue pendle ... (repo-local)
  • grimoire-pendle ... (direct binary from @grimoirelabs/venues)

Recommended preflight:

  • grimoire venue doctor --adapter pendle --chain 1 --rpc-url <rpc> --json

Commands

  • grimoire venue pendle info [--base-url <url>] [--format <auto|json|table>]
  • grimoire venue pendle chains [--base-url <url>] [--format <auto|json|table>]
  • grimoire venue pendle supported-aggregators --chain <id> [--base-url <url>] [--format <auto|json|table>]
  • grimoire venue pendle markets [--chain <id>] [--active <true|false>] [--base-url <url>] [--format <auto|json|table>]
  • grimoire venue pendle assets [--chain <id>] [--type <PT|YT|LP|SY>] [--base-url <url>] [--format <auto|json|table>]
  • grimoire venue pendle market-tokens --chain <id> --market <address> [--base-url <url>] [--format <auto|json|table>]

Examples

grimoire venue pendle info --format table
grimoire venue pendle chains
grimoire venue pendle supported-aggregators --chain 1 --format json
grimoire venue pendle markets --chain 1 --active true --format table
grimoire venue pendle assets --chain 8453 --type PT --format table
grimoire venue pendle market-tokens --chain 8453 --market 0x... --format json

Authoring Workflow

Pendle requires a market-first approach. Do NOT write a Pendle spell without first querying available markets.

  1. Query markets for the target chain and underlying:

    grimoire venue pendle markets --chain 1 --active true --format json
    
  2. Pick a market — note its address and expiry. Each market has specific PT/YT/SY tokens.

  3. Query market tokens to get the exact token addresses:

    grimoire venue pendle market-tokens --chain 1 --market 0x... --format json
    
  4. Write the spell using token addresses from step 3:

    pendle.add_liquidity(0x<SY_address>, params.amount) with (max_slippage=100)
    

Common mistakes

  • pendle.deposit(USDC, ...) — Pendle has no deposit action. Use add_liquidity, mint_py, mint_sy, or swap.
  • Using token symbols without addresses — PT/YT/SY tokens are auto-resolved via the Pendle API, but standard tokens like USDC need raw amounts in the token's smallest unit.
  • Missing enable_aggregator — Some routes require an aggregator. If no route is found, retry with enable_aggregator=true in the with() clause.

Supported actions

Action Description Input Output
swap Swap between any Pendle tokens Single token Single token
add_liquidity Add single-sided liquidity Underlying/SY LP token
remove_liquidity Remove single-sided liquidity LP token Underlying/SY
mint_py Mint PT + YT from underlying Underlying/SY PT + YT
redeem_py Redeem PT + YT to underlying PT + YT Underlying/SY
mint_sy Wrap underlying into SY Underlying SY
redeem_sy Unwrap SY to underlying SY Underlying

Metric Surface (Spell Comparisons)

Pendle exposes quote_out for route output comparisons:

pendle_out = metric("quote_out", pendle, USDC, "asset_out=DAI,amount=1000000,slippage_bps=1000")

Selector fields:

  • required: asset_out
  • optional: amount (defaults to 1 unit of input asset), slippage_bps, enable_aggregator

Spell Constraints

When writing Pendle actions in .spell files, use with clauses:

pendle.swap(PT_TOKEN, SY_TOKEN, params.amount) with (
  max_slippage=100,
  require_quote=true,
)
Constraint Type Description
max_slippage integer (bps) Maximum slippage, validated as integer in [0, 10000], converted to decimal for API
min_output integer (wei) Minimum output amount floor
require_quote boolean Fail if Pendle API quote fails
max_gas integer (wei) Gas estimate cap

Pendle swap only supports mode: exact_in. exact_out is not supported.

When the Pendle API returns multiple routes, the adapter selects the first (best) route and emits a warning via onWarning. This is logged in non-JSON CLI runs.

PT/YT/SY Token Resolution

Pendle PT, YT, and SY tokens (e.g. PT_FXSAVE, YT_EETH, SY_WSTETH) are automatically resolved via the Pendle API at build time. You can use these symbols directly in spells without providing explicit addresses:

pendle.swap(PT_FXSAVE, USDC, params.amount) with (max_slippage=100)

The adapter converts underscore-delimited names (e.g. PT_FXSAVE) to the Pendle API format and picks the best match. If multiple expiries exist, the first (nearest) is selected.

To target a specific expiry or disambiguate, use the full 0x address instead:

pendle.swap(0xb1e926428ebec4421cce1ec6d9ff65d27f4b4bb6, USDC, params.amount)

Use grimoire venue pendle assets --chain <id> --type PT to discover available tokens and addresses.

Notes

  • Default API base URL is https://api-v2.pendle.finance/core.
  • Override base URL with --base-url or PENDLE_API_BASE_URL.
  • Use --format json for automation and nested payloads.
  • Pendle swap currently supports mode: exact_in only.
  • Aggregators are disabled by default in adapter actions unless explicitly enabled.
  • For Pendle token outputs (assetOut, outputs), use bare address literals (0x...) and not quoted strings (\"0x...\").
  • Quoted address-like token values trigger validator code QUOTED_ADDRESS_LITERAL.
  • max_slippage is validated as integer bps in [0, 10000] and converted to decimal (bps / 10000) before API requests.
how to use grimoire-pendle

How to use grimoire-pendle on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your development machine
  • Node.js version 16.0+ with npm package manager (verify with node --version)
  • Active project directory or workspace where you want to add grimoire-pendle
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/franalgaba/grimoire --skill grimoire-pendle

The skills CLI fetches grimoire-pendle from GitHub repository franalgaba/grimoire and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/grimoire-pendle

Reload or restart Cursor to activate grimoire-pendle. Access the skill through slash commands (e.g., /grimoire-pendle) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

User Story & Requirements Generation

Create detailed user stories, acceptance criteria, and feature specs

Example

Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios

Reduce spec writing time by 50%, ensure comprehensive coverage

Competitive Analysis

Research competitors, compare features, identify gaps

Example

Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities

Complete competitive research in 2 hours instead of 2 days

Roadmap Prioritization

Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs

Example

Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale

Make data-driven prioritization decisions faster

Stakeholder Communication

Draft PRDs, status updates, and stakeholder presentations

Example

Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement

Save 3-5 hours/week on communication overhead

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client
  • Access to product documentation and roadmap tools (Jira, Notion, etc.)
  • Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
  • Stakeholder contact information and communication channels

Time Estimate

30-60 minutes to see productivity improvements

Installation Steps

  1. 1.Install product management skill
  2. 2.Start with user story generation for known feature
  3. 3.Progress to competitive analysis: research 2-3 competitors
  4. 4.Use for roadmap prioritization: apply RICE/ICE scoring
  5. 5.Draft stakeholder communications and refine based on feedback
  6. 6.Build template library for recurring PM tasks
  7. 7.Share effective prompts with product team

Common Pitfalls

  • Not validating competitive research—verify facts before sharing
  • Accepting user stories without involving engineering team
  • Over-relying on frameworks without qualitative judgment
  • Not customizing outputs to company culture and communication style
  • Skipping stakeholder validation of generated requirements

Best Practices

✓ Do

  • +Validate research and competitive analysis with real data
  • +Collaborate with engineering when generating technical requirements
  • +Customize frameworks and templates to your company context
  • +Use skill for first drafts, refine with stakeholder input
  • +Document successful prompt patterns for PM tasks
  • +Combine AI efficiency with human judgment and intuition

✗ Don't

  • Don't publish competitive analysis without fact-checking
  • Don't finalize user stories without engineering review
  • Don't make prioritization decisions solely on AI scoring
  • Don't skip customer validation of generated requirements
  • Don't ignore company-specific context and culture

💡 Pro Tips

  • Provide context: company goals, constraints, customer feedback
  • Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
  • Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
  • Use skill for 70% generation + 30% customization to company needs

When to Use This

✓ Use When

Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.

✗ Avoid When

Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.

Learning Path

  1. 1Basic: user stories, feature specs, status updates
  2. 2Intermediate: competitive analysis, prioritization frameworks, PRDs
  3. 3Advanced: product strategy, go-to-market planning, OKR setting
  4. 4Expert: product vision, market positioning, business model innovation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.662 reviews
  • Noah Wang· Dec 20, 2024

    I recommend grimoire-pendle for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Mia Khan· Dec 20, 2024

    We added grimoire-pendle from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • Ama Huang· Dec 16, 2024

    grimoire-pendle has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Ama Patel· Dec 16, 2024

    Keeps context tight: grimoire-pendle is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Noah Ndlovu· Dec 12, 2024

    grimoire-pendle reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Noah White· Dec 8, 2024

    Keeps context tight: grimoire-pendle is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Henry Menon· Dec 8, 2024

    Registry listing for grimoire-pendle matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Ama Kim· Nov 11, 2024

    Useful defaults in grimoire-pendle — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Kwame Diallo· Nov 7, 2024

    Solid pick for teams standardizing on skills: grimoire-pendle is focused, and the summary matches what you get after install.

  • Ama Sanchez· Nov 3, 2024

    Registry listing for grimoire-pendle matched our evaluation — installs cleanly and behaves as described in the markdown.

showing 1-10 of 62

1 / 7