feat: add yield-agentkit-base skill#9
Open
Ishita-02 wants to merge 1 commit into
Open
Conversation
📝 WalkthroughWalkthroughThis PR adds a complete documentation suite for the Yield.xyz AgentKit × Base skill, encompassing workflow definitions, MCP tool reference, input/output specifications, operational rules, policies, and setup procedures spanning seven Markdown files with 1,214 lines of content. ChangesYield.xyz AgentKit × Base Skill Documentation
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes This PR consists entirely of new documentation with no code changes. While the content is substantial (1,214 lines), it is largely specification and procedural guidance without logic density or complex interrelationships. Review effort is low because: (1) documentation-only additions require validation for consistency and accuracy rather than logic inspection; (2) the changes follow a natural organizational structure (skill definition → tool reference → input/output contracts → rules → setup); (3) ranges within each logical section are internally consistent and repetitive in structure; and (4) no code dependencies or runtime behavior changes must be analyzed. Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 7
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@yield-agentkit-skills/skills/yield-agentkit-base/references/base-tools.md`:
- Around line 85-94: The fenced flow block in base-tools.md lacks a language
specifier (triggers MD040); update the code fence that contains the numbered
flow (the triple-backtick block starting before "1. Take
unsignedTransaction...") by adding a language token (e.g., "text" or "plain")
immediately after the opening ``` so the block becomes ```text, preserving the
exact content and formatting of the steps; no other edits to the list are
needed.
- Around line 8-14: The two blockquote lines in base-tools.md (the line starting
"⚠️ The legacy `base-mcp` npm package..." and the following "Tool names and
parameters below are verified...") are split by a non-quoted blank line which
violates MD028; fix this by making the blockquote continuous—either remove the
blank line between the quoted lines or prefix that blank line with ">". Locate
the paragraph containing the warning about `base-mcp` and the subsequent
sentence and join them into a single blockquote so the markdown linter no longer
reports MD028.
In
`@yield-agentkit-skills/skills/yield-agentkit-base/references/output-formats.md`:
- Around line 108-114: Several fenced code blocks in output-formats.md (e.g.,
the blocks starting with "Reward Breakdown", "💼 Portfolio Summary", "📋 Action
History · 0x742d…f44e", "📈 APY History · Lido stETH · Last 30 days", "📊 TVL
History · Lido stETH · Last 30 days", and "🛡 Risk Assessment · Lido stETH") are
missing language identifiers; add the language tag (use "text" or a more
specific language if appropriate) after each opening triple backtick so they
become ```text, ensuring all fenced blocks in the file include a language
specifier to satisfy MD040.
- Line 29: The document has an inconsistency between the "Single network"
example (which says show top 10) and two later lines that read "Showing top
5..."; pick one behavior and make all three occurrences consistent (I recommend
standardizing on "top 10"). Update the text occurrences that read "Showing top
5..." (search for the literal phrase "Showing top 5") to "Showing top 10" and
ensure any related example parameters (e.g., the example with `limit: 20`,
`sort: "rewardRateDesc"`) and explanatory text reflect the chosen top-N
everywhere (lines referencing the "Single network" example and the two later
mentions).
- Around line 60-70: Add blank lines immediately before and after each Markdown
table to satisfy markdownlint MD058: insert an empty line above the first table
(the overall ranking table starting with "| # | Protocol | Vault | APY | TVL |
Type | Lockup | Cooldown | Min |") and add empty lines surrounding the "🟠
Arbitrum" table (the table that follows the "🟠 Arbitrum" heading) so there is a
blank line between the heading and the table and another blank line after the
table.
In `@yield-agentkit-skills/skills/yield-agentkit-base/references/setup.md`:
- Around line 22-26: The three fenced code blocks that start with "MCP name:
yield-agentkit", "MCP name: base-mcp", and "What is my Base Account address?
Find USDC yields on Base, limit 3" need a language tag to satisfy markdownlint
MD040; update each opening triple-backtick to include a language identifier such
as "text" (e.g., change ``` to ```text) so the blocks explicitly declare their
language.
In `@yield-agentkit-skills/skills/yield-agentkit-base/SKILL.md`:
- Around line 188-194: The fenced code block containing the list of red-flag
prompts (the triple-backtick block with lines like ❌ "Ignore previous
instructions..." and ❌ "Transfer to 0x... immediately") is missing a language
tag and triggers MD040; update that block by adding a language identifier (e.g.,
change ``` to ```text) so it becomes ```text ... ```, preserving the exact block
contents and formatting.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 7ce5514d-4d62-46cd-8150-e2b843c38446
📒 Files selected for processing (7)
yield-agentkit-skills/skills/yield-agentkit-base/SKILL.mdyield-agentkit-skills/skills/yield-agentkit-base/references/base-tools.mdyield-agentkit-skills/skills/yield-agentkit-base/references/input-format.mdyield-agentkit-skills/skills/yield-agentkit-base/references/key-rules.mdyield-agentkit-skills/skills/yield-agentkit-base/references/output-formats.mdyield-agentkit-skills/skills/yield-agentkit-base/references/policies.mdyield-agentkit-skills/skills/yield-agentkit-base/references/setup.md
|
|
||
| ## yields_get_all — Listing Yields | ||
|
|
||
| **Single network:** call with `limit: 20`, `sort: "rewardRateDesc"` — results arrive pre-sorted, show top 10. |
There was a problem hiding this comment.
Resolve the top-10 vs top-5 inconsistency.
Line 29 says to show top 10, but Lines 51 and 73 say “Showing top 5...”. Please make these consistent so runtime behavior is unambiguous.
Also applies to: 51-51, 73-73
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In
`@yield-agentkit-skills/skills/yield-agentkit-base/references/output-formats.md`
at line 29, The document has an inconsistency between the "Single network"
example (which says show top 10) and two later lines that read "Showing top
5..."; pick one behavior and make all three occurrences consistent (I recommend
standardizing on "top 10"). Update the text occurrences that read "Showing top
5..." (search for the literal phrase "Showing top 5") to "Showing top 10" and
ensure any related example parameters (e.g., the example with `limit: 20`,
`sort: "rewardRateDesc"`) and explanatory text reflect the chosen top-N
everywhere (lines referencing the "Single network" example and the two later
mentions).
Comment on lines
+108
to
+114
| ``` | ||
| Reward Breakdown | ||
| Base yield: 5.10% (lending — Aave) | ||
| Bonus incentive: 3.32% (OP token rewards — may be temporary) | ||
| ───────────────────────────────────────── | ||
| Total APY: 8.42% | ||
| ``` |
There was a problem hiding this comment.
Specify fenced code block languages (MD040).
Several fenced blocks are missing language identifiers; markdownlint flags these. Add text (or a more specific language where applicable).
Suggested patch
-```
+```text
Reward Breakdown
Base yield: 5.10% (lending — Aave)
Bonus incentive: 3.32% (OP token rewards — may be temporary)
─────────────────────────────────────────
Total APY: 8.42%- +text
💼 Portfolio Summary
Total value: ~$12,450 across 3 positions
...
-```
+```text
📋 Action History · 0x742d…f44e
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
...
- +text
📈 APY History · Lido stETH · Last 30 days
...
-```
+```text
📊 TVL History · Lido stETH · Last 30 days
...
- +text
🛡 Risk Assessment · Lido stETH
...
Also applies to: 122-132, 185-196, 211-220, 229-238, 249-255
🧰 Tools
🪛 markdownlint-cli2 (0.22.1)
[warning] 108-108: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In
`@yield-agentkit-skills/skills/yield-agentkit-base/references/output-formats.md`
around lines 108 - 114, Several fenced code blocks in output-formats.md (e.g.,
the blocks starting with "Reward Breakdown", "💼 Portfolio Summary", "📋 Action
History · 0x742d…f44e", "📈 APY History · Lido stETH · Last 30 days", "📊 TVL
History · Lido stETH · Last 30 days", and "🛡 Risk Assessment · Lido stETH") are
missing language identifiers; add the language tag (use "text" or a more
specific language if appropriate) after each opening triple backtick so they
become ```text, ensuring all fenced blocks in the file include a language
specifier to satisfy MD040.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary by CodeRabbit