Skills Guide

Mend Subagents

VerifiedCaution

Synchronizes Subagents with available Agent Skills, suggesting bindings and removing broken links to maintain ecosystem consistency.

Download and use
Sby Skills Guide Bot
DevelopmentIntermediate
3/2/2026
Claude CodeCursor
#subagents#agent-skills#frontmatter#link-integrity#claude-code

Recommended for

Backend developerClaude CodeCode reviewFrontend developerCursorFullstack developer

Automated summary

This skill keeps subagent definitions in sync with the available Agent Skills by removing broken references and suggesting new bindings.

Strengths

  • Indexes every SKILL.md found in the root and platform-specific skills/ directories by reading its YAML frontmatter (name, description)
  • Removes stale references both from the skills frontmatter list and from the agent's ## Capabilities section
  • Rewrites relative links to match each platform's convention (Claude Code vs Cursor)
  • Syncs the skill table inside the agent body using the SKILLS_START / SKILLS_END markers
  • Suggests or adds relevant bindings by comparing agent and skill descriptions, optionally asking the user to confirm first

Limitations

  • Binding suggestions rely on a description-similarity heuristic, so relevance can be imprecise
  • Only covers the link path conventions of Claude Code and Cursor
  • Edits agent definition files in place, so changes should be reviewed and version-controlled
  • Body synchronization requires the SKILLS_START / SKILLS_END markers to already exist in the agent file
When to use it

Run it after creating, renaming, or deleting skills, or whenever a subagent appears to be missing capabilities it needs for its role.

When not to use it

Avoid it if you do not want agent files rewritten automatically, or if your definitions do not follow the supported path conventions and marker comments.

Security analysis

Caution
Quality score80/100

The skill performs only local, legitimate maintenance of agent definition files: scanning skills, parsing frontmatter, removing dead links, and updating tables. There are no destructive commands, network calls, secret handling, or obfuscated payloads. The concern is moderate: it writes to configuration files, can auto-apply heuristic bindings without confirmation, and declares no allowed-tools despite needing write access. This warrants caution rather than risk.

Findings
  • •No allowed-tools declared even though the skill requires file reads, file writes/edits, directory scanning, and AskQuestion — an inconsistent permission surface that could lead an agent to use broad tools.
  • •Step 4 'Proactive' mending automatically adds skill bindings when heuristic confidence is 'high' without a defined threshold or user confirmation, mutating agent definitions silently.
  • •Instructions edit agent frontmatter and body sections in place with no backup, dry-run, or diff-review step, so a parsing error could corrupt agent files.
  • •No explicit path scoping/validation for the scanned skills/ and agents/ directories.
How this analysis is made

Examples

Clean up after deleting skills
I just deleted three skills from my repo. Audit all subagents in .claude/agents and remove any references to skills that no longer exist.
Suggest missing bindings
Review each subagent definition and suggest which available Agent Skills it should be bound to but currently isn't.
Wire up a new skill
I added a new skill called deploy-checklist. Update the subagents that should reference it and refresh their Capabilities sections.

name: mend-subagents description: Synchronizes Subagents with available Agent Skills, suggesting bindings and removing broken links.

Mend Subagents

Purpose

This skill ensures that all Subagents have accurate references to the available Agent Skills. It manages the binding between agents and skills, ensuring they remain consistent as the ecosystem grows or changes.

When to Use

  • After creating new Agent Skills.
  • After deleting or renaming skills.
  • When an agent seems to lack the capabilities it needs to perform its role.

Instructions

1. Index Available Skills

  • Scan the platform-specific skills/ directory and the root skills/ directory.
  • For each SKILL.md, extract the name and description from the YAML frontmatter.

2. Audit Subagents

  • Iterate through each agent definition (e.g., in .claude/agents/ or root agents/).
  • Parse the YAML frontmatter skills list and the ## Capabilities section.

3. Synchronize Bindings

  • Remove Dead Links: If an agent references a skill that no longer exists, remove it from the frontmatter and the Capabilities section.
  • Update Links: Ensure all links point to the correct relative path for the current platform.
    • Claude Code: [skill-name](../skills/skill-name/SKILL.md)
    • Cursor: [skill-name](../../skills/meta-agent-skills/skill-name/SKILL.md)
  • Capabilities Section: Use the <!-- SKILLS_START --> and <!-- SKILLS_END --> markers to synchronize the table of skills in the agent's body.

4. Suggestive Mending (AI Heuristic)

  • Compare the Agent's description with the descriptions of all available skills.
  • If a skill appears relevant but is not bound to the agent:
    • Interactive: Suggest the binding to the user via AskQuestion.
    • Proactive: If confidence is high, add the binding and report it.

5. Final Report

  • List all agents updated.
  • List all new bindings suggested or added.
  • Highlight any broken links that were removed.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/mend-subagents-mm8o52cb/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/mend-subagents-mm8o52cb' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/mend-subagents-mm8o52cb/download' --output '.skill-downloads/mend-subagents-mm8o52cb/SKILL.md.part' && mv '.skill-downloads/mend-subagents-mm8o52cb/SKILL.md.part' '.skill-downloads/mend-subagents-mm8o52cb/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/mend-subagents-mm8o52cb/SKILL.md' && test -s '.skill-downloads/mend-subagents-mm8o52cb/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/mend-subagents' && cp -R '.skill-downloads/mend-subagents-mm8o52cb' '.claude/skills/mend-subagents'

Cursor
test -f '.skill-downloads/mend-subagents-mm8o52cb/SKILL.md' && test -s '.skill-downloads/mend-subagents-mm8o52cb/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/mend-subagents' && cp -R '.skill-downloads/mend-subagents-mm8o52cb' '.cursor/skills/mend-subagents'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/mend-subagents-mm8o52cb'

openskills read 'mend-subagents-mm8o52cb'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/mend-subagents-mm8o52cb/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

React Hook Form Best Practices

Development

Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.

Claude CodeCursorWindsurf+2intermediateSafe 108,623
Skills Guide Bot

Emotion to Mantine Migration

Development

Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.

Claude CodeCursorWindsurf+1intermediateSafe 48,981
Skills Guide Bot

Scope Creep Detector

Development

Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.

Claude CodeCursorCodexintermediateSafe 135,015
Skills Guide Bot