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

42%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/productivity/agent-context-manager/skills/agent-context-loader/SKILL.md

Quality

Content

50%Weight 40%Scale 1-3

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 into clear sections and avoids concept-explaining fluff, but it tells rather than equips: it gives procedural steps with no executable commands and completely orphans its own bundle, keeping examples and error detail inline instead of pointing to the reference files that already exist.

Suggestions

Reference the bundled helper script inline, e.g. step 1: "Run `bash scripts/check-agents-md.sh <dir>` to discover AGENTS.md files up the hierarchy", turning guidance into executable action.

Move the worked examples and the full error table into references/examples.md and references/errors.md (which already exist) and link to them from the body, fixing the orphaned bundle and improving progressive disclosure.

Add an inline validation checkpoint to the workflow, e.g. after reading all files, "Verify each discovered file decoded successfully before merging; re-scan any that errored."

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but the three full "Structure: / Result:" narrative examples are illustrative rather than instructional and could be tightened to earn the lean anchor at 3.	2 / 3
Actionability	The 7 numbered steps give concrete procedural guidance, but there are no executable commands or code, and notably the bundled helper script scripts/check-agents-md.sh is never referenced, leaving the guidance incomplete per the executable-anchor bar.	2 / 3
Workflow Clarity	The Instructions section is a clear, correctly ordered 7-step sequence, but it has no inline validation checkpoints or fix-retry feedback loops, capping a multi-step process at 2.	2 / 3
Progressive Disclosure	The body is well-sectioned (Overview, Instructions, Error Handling, Examples, Resources), but the existing bundle files (references/examples.md, references/errors.md, scripts/check-agents-md.sh) are never signaled, and examples and error handling that belong in those files are kept inline.	2 / 3
	Total	8 / 12 Passed

Description

35%Weight 40%Scale 1-3

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 targets a specific niche but leads with abstract buzzword ("proactive auto-loading") and provides only generic, contentless trigger guidance instead of natural keywords a user would say. It states a basic what and a vacuous when, landing in the middle of the scale.

Suggestions

Lead with concrete actions instead of "Execute proactive auto-loading", e.g. "Discovers, reads, and merges AGENTS.md files across the workspace and ancestor directories into a single context summary."

Replace the generic "Use when appropriate context detected" with real trigger terms users would say, e.g. "Use when the user mentions AGENTS.md, agent context files, or loading project instructions for a workspace."

Drop the circular filler "Trigger with relevant phrases based on skill purpose" which adds no information.

Dimension	Reasoning	Score
Specificity	The phrase "automatically detects and loads agents.md files" names the domain and two concrete actions, but the lead "Execute proactive auto-loading" is abstract buzzword that keeps it short of the multiple-specific-actions anchor at 3.	2 / 3
Completeness	A weak "what" (detects and loads agents.md) is present, but the "when" clause is contentless filler rather than explicit triggers, so per the missing-effective-trigger guideline it cannot reach 3.	2 / 3
Trigger Term Quality	"Use when appropriate context detected. Trigger with relevant phrases based on skill purpose" is vacuous meta-boilerplate with no natural keywords a user would actually say, matching the no-natural-keywords anchor rather than the partial-coverage anchor at 2.	1 / 3
Distinctiveness Conflict Risk	The AGENTS.md auto-loading niche is fairly specific and unlikely to conflict with unrelated skills, but the generic trigger language prevents it from being a clearly distinctive, conflict-proof description at 3.	2 / 3
	Total	7 / 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
Path: plugins/productivity/agent-context-manager/skills/agent-context-loader/SKILL.md
Commit: c4eafaf

Reviewed: 5 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.