agent-context-loader
Execute proactive auto-loading: automatically detects and loads agents.md files. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
26
10%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/productivity/agent-context-manager/skills/agent-context-loader/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an extremely poor skill description. It uses circular, self-referential language for its trigger conditions ('use when appropriate context detected'), provides no concrete actions or outcomes, and includes no natural keywords a user would actually say. It would be essentially unusable for skill selection among multiple options.
Suggestions
Replace the circular trigger clause with specific, concrete conditions — e.g., 'Use when the user asks about agent configuration, mentions agents.md, or needs to load agent definitions from the workspace.'
Describe what the skill actually does in concrete terms — what happens after agents.md is loaded? What problem does this solve? E.g., 'Scans the workspace for agents.md files and loads agent definitions to configure available AI agents and their capabilities.'
Add natural trigger terms users would actually say, such as 'agent configuration', 'load agents', 'agent setup', 'agents.md', or 'configure agents'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'detects and loads agents.md files' which is a single vague action. 'Execute proactive auto-loading' is abstract jargon. There are no concrete, specific actions listed beyond this one nebulous capability. | 1 / 3 |
Completeness | The 'what' is extremely vague ('detects and loads agents.md files' with no explanation of purpose or outcome), and the 'when' is completely absent — 'Use when appropriate context detected' is a meaningless tautology that provides zero guidance on actual trigger conditions. | 1 / 3 |
Trigger Term Quality | The trigger guidance is entirely circular and vacuous: 'Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.' No actual natural keywords are provided. 'agents.md' is the only concrete term, and users would not naturally say 'auto-loading' or 'proactive auto-loading.' | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it could conflict with any skill involving file loading, configuration detection, or agent management. 'Trigger with relevant phrases based on skill purpose' is generic enough to match anything. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
20%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a design document or specification than an actionable skill for Claude. It describes what should happen at a high level but provides no executable commands, glob patterns, or concrete tool usage that Claude could follow. The content is also verbose, explaining concepts like symlink handling and encoding fallbacks that Claude already understands.
Suggestions
Replace abstract instructions with concrete tool invocations—e.g., actual glob patterns like `**/AGENTS.md` or `find` commands, and show how to use Read tool to load discovered files.
Add a concrete input/output example showing the actual content of a discovered AGENTS.md and the resulting merged output format, rather than narrative descriptions.
Remove explanatory content Claude already knows (what AGENTS.md files are, how symlinks work, what UTF-8 encoding is) and focus on the specific discovery algorithm and merge logic.
Add a validation step after merging instructions—e.g., confirming the merged context is coherent and presenting it to the user for confirmation before applying.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is verbose and explains concepts Claude already understands well—directory traversal, symlink handling, file encoding fallbacks, what AGENTS.md files are. The overview restates the description. The error handling table, while structured, covers edge cases Claude can reason about independently. Much of this content doesn't add novel knowledge. | 1 / 3 |
Actionability | Despite being a technical skill, there are zero concrete commands, code snippets, or executable examples. The instructions are entirely abstract descriptions ('scan the current working directory', 'read each discovered file', 'cache the discovery results') with no actual glob patterns, shell commands, or tool invocations. The examples are narrative descriptions rather than showing actual inputs/outputs. | 1 / 3 |
Workflow Clarity | The steps are listed in a logical sequence with a clear load order (root-first, deeper-later) and conflict resolution strategy. However, there are no validation checkpoints—no step to verify the merged context is correct, no feedback loop if merging fails, and no concrete verification that the cache is working properly. | 2 / 3 |
Progressive Disclosure | The content is organized into clear sections (Overview, Prerequisites, Instructions, Output, Error Handling, Examples, Resources), which is good structure. However, with no bundle files, the Resources section links to external URLs (some of which may not exist or be accurate), and the content is somewhat monolithic—the error handling table and examples could potentially be separated if the skill were more complex. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3a2d27d
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.