recommendation-letter-assistant

Helps faculty and mentors draft standardized recommendation letters for.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

The body is highly actionable thanks to a real executable script, concrete commands, and a defined I/O schema, but it is bloated with generic boilerplate sections and shallow workflow validation that keep conciseness, workflow clarity, and progressive disclosure at the middle anchor.

Suggestions

Remove generic template sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template) that add no skill-specific value.

Tighten the workflow to skill-specific steps with a real validation/feedback loop (e.g., verify required inputs are present and confirm output schema before returning the draft) instead of a shallow py_compile check.

Move detailed competency phrase banks and specialty expectations into references/ and keep SKILL.md a lean overview that points to them, rather than inlining generic process guidance.

Dimension	Reasoning	Score
Conciseness	The core content (parameters, output schema, commands) is efficient, but ~195 lines for a single-script skill include generic boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template) and 'See ## X above' cross-references that pad the token budget.	2 / 3
Actionability	It provides a real, executable scripts/main.py, copy-paste commands ('python -m py_compile scripts/main.py', 'python scripts/main.py demo'), a concrete input parameter table, and a defined JSON output schema, matching the fully executable anchor.	3 / 3
Workflow Clarity	A numbered workflow, a Quick Check validation step, and an error-handling fallback are present, but the validation is shallow (syntax compile only) and the steps are generic process boilerplate rather than skill-specific guidance, so it does not reach 3.	2 / 3
Progressive Disclosure	Real one-level-deep bundle files exist and are signaled (references/guidelines.md, scripts/main.py), but the body itself is a monolithic wall of inline generic sections that could be split out, matching the 'some structure but could be better organized' anchor.	2 / 3
	Total	9 / 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 uses third person, but it is grammatically truncated, names only one action, and omits any 'Use when' trigger, leaving every dimension at the middle anchor.

Suggestions

Complete the truncated sentence (e.g., '...recommendation letters for medical trainees and residency/fellowship applicants') and add a 'Use when...' trigger clause.

List multiple concrete actions (e.g., draft, structure, and tailor letters by specialty) to raise specificity.

Add natural trigger terms users would say, such as 'recommendation letter', 'LOR', 'letter of recommendation', 'MSPE', or 'Dean's Letter'.

Dimension	Reasoning	Score
Specificity	The description names the domain ('recommendation letters') and one concrete action ('draft standardized') via 'Helps faculty and mentors draft standardized recommendation letters for', but it lists only a single action rather than multiple specific concrete actions, so it falls short of 3.	2 / 3
Completeness	It states what the skill does but provides no explicit 'when' trigger, and the sentence is truncated mid-phrase ('...letters for.'); per the guidelines a missing 'Use when' clause caps completeness at 2.	2 / 3
Trigger Term Quality	It includes relevant natural terms ('faculty and mentors', 'recommendation letters') users might say, but offers no common variations or 'Use when' phrasing, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	'Recommendation letters for' is a recognizable niche unlikely to conflict broadly, but the truncated, trigger-less phrasing leaves it only somewhat specific rather than a clearly distinct, trigger-rich description.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Commit: d924410

Reviewed: 3 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.