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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized and gives a clear sequenced workflow with error handling, but it fails to reference its own bundle files and inlines examples that already exist in references/examples.md, capping every dimension at the mid anchor.

Suggestions

Replace the inline Examples section with a pointer to references/examples.md (e.g. 'See [examples.md](references/examples.md) for monorepo, conflict, and edge-case scenarios') to remove duplication and improve progressive disclosure.

Reference the bundled script in the Instructions or Prerequisites (e.g. invoke or adapt scripts/check-agents-md.sh) so the guidance includes an executable artifact.

Add an explicit validation checkpoint to the workflow, e.g. after merging 'verify no unresolved conflicts before presenting context; if conflicts exist, surface them and confirm the deeper-directive override with the user.'

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but the inline Examples section (Examples 1–3) partially duplicates the richer references/examples.md bundle, so tokens could be tightened by pointing to the reference instead of restating.	2 / 3
Actionability	The 7-step instructions give specific, actionable direction (scan ancestors, order by depth, merge, report conflicts, cache), but there are no executable commands or script invocations and the bundled scripts/check-agents-md.sh is never referenced, leaving guidance concrete but incomplete.	2 / 3
Workflow Clarity	Steps are clearly sequenced with conflict detection in steps 5–6 and an error-handling table for recovery, but validation checkpoints are implicit rather than framed as explicit validate-then-proceed gates, matching the 'sequence present but checkpoints missing or implicit' anchor.	2 / 3
Progressive Disclosure	The body is well sectioned, but the bundle files (references/examples.md, references/errors.md, scripts/check-agents-md.sh) are never signaled from the body and examples that belong in the reference are inlined, matching 'references present but not clearly signaled; content that should be separate is inline'.	2 / 3
	Total	8 / 12 Passed

Description

50%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies a clear niche and includes a 'Use when' clause, but the trigger guidance is generic filler rather than concrete natural-language triggers, leaving every dimension at the mid-level anchor.

Suggestions

Replace 'Use when appropriate context detected. Trigger with relevant phrases based on skill purpose' with concrete natural triggers, e.g. 'Use when the user mentions AGENTS.md, agent instructions, agent context, or asks to load project conventions for an AI coding agent.'

Expand the action list beyond 'detects and loads' to name the specific operations (scans ancestor and subdirectories, merges instructions, reports conflicts, caches results).

Add common keyword variations users would actually say (AGENTS.md, agent instructions, project conventions, coding agent context) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The phrase 'automatically detects and loads agents.md files' names a clear domain and two concrete actions (detects, loads), but stops short of listing multiple specific actions, matching the 'names domain and some actions' anchor rather than the 'multiple specific concrete actions' anchor at 3.	2 / 3
Completeness	It states what the skill does ('detects and loads agents.md files') and includes a 'Use when...' clause, but that clause is circular filler ('appropriate context detected') rather than explicit trigger guidance, so the 'when' is present only in weak/implied form, capping completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	'agents.md files' is a relevant keyword, but the surrounding 'Use when appropriate context detected' and 'Trigger with relevant phrases based on skill purpose' are generic filler that supply no natural user-facing variations, so it has some relevant keywords but misses common variations.	2 / 3
Distinctiveness Conflict Risk	The agents.md-loading niche is reasonably distinct, but the generic trigger language ('appropriate context detected') could overlap with other context-loading skills, placing it at 'somewhat specific but could still overlap' rather than the clear-distinct-triggers anchor at 3.	2 / 3
	Total	8 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 3022dd3

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.