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.
20
10%
Does it follow best practices?
Impact
—
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 description is extremely weak across all dimensions. It uses circular, self-referential language for its trigger conditions ('use when appropriate context detected') that provides zero useful information for skill selection. The actual capability — loading agents.md files — is stated but never explained in terms of purpose or user benefit.
Suggestions
Replace the circular trigger clause with specific, concrete conditions: e.g., 'Use when the user asks about agent configurations, multi-agent workflows, or when agents.md files are present in the project directory.'
Explain what loading agents.md files actually accomplishes — what benefit does the user get? E.g., 'Loads agent definitions and configurations from agents.md files to enable multi-agent orchestration and task delegation.'
Add natural trigger terms a user might say, such as 'agents', 'agent configuration', 'multi-agent setup', 'load agents', or whatever domain-specific terms apply to this skill's actual purpose.
| 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 barely defined ('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 placeholder that provides zero actionable trigger guidance. | 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.' These are not natural keywords a user would say. 'agents.md' is the only concrete term, and it's unlikely to appear in user queries. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague ('appropriate context detected', 'relevant phrases based on skill purpose') that it could match virtually any query. There is nothing distinctive that would help Claude differentiate this skill from others. | 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 concrete tool calls, glob patterns, or executable code that Claude could actually use. The content is also significantly over-explained for its audience, spending tokens on concepts Claude already knows well (directory traversal, symlinks, encoding fallbacks).
Suggestions
Replace the abstract instruction steps with concrete, executable tool calls (e.g., specific glob patterns like `**/AGENTS.md`, `find` commands, or Bash/Python snippets for the discovery and loading process).
Remove explanatory content Claude already knows — eliminate the Prerequisites section, trim the Overview to one sentence, and reduce the error handling table to only non-obvious recovery strategies.
Add a concrete, copy-paste-ready example showing the actual tool invocations and expected output format rather than narrative descriptions of monorepo scenarios.
Add a validation step after merging instructions (e.g., confirm loaded context with the user or verify instruction count matches discovered files) to strengthen the workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is verbose and explains concepts Claude already understands well (directory traversal, symlinks, file encoding, what AGENTS.md files are). The overview, prerequisites, and much of the error handling table explain things that are obvious to Claude. The entire skill could be condensed to roughly 20 lines. | 1 / 3 |
Actionability | Despite being lengthy, the skill contains zero executable code, no concrete commands, no glob patterns, and no actual implementation. Steps like 'Scan the current working directory' and 'Read each discovered AGENTS.md file' are abstract descriptions rather than actionable instructions with specific tool calls or commands. | 1 / 3 |
Workflow Clarity | The 7-step sequence is clearly ordered and logically structured with a reasonable load-order strategy. However, there are no validation checkpoints or feedback loops — no step verifies that the merge was correct or that the loaded context is actually valid before being applied to the session. | 2 / 3 |
Progressive Disclosure | The content is organized into clear sections (Overview, Instructions, Output, Error Handling, Examples), which is decent structure. However, with no bundle files, the external resource links point to generic Anthropic docs rather than supporting reference files, and the inline content is longer than it needs to be — some of the error handling and examples could be split out. | 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
4801da6
- 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.