recommendation-letter-assistant

Helps faculty and mentors draft standardized recommendation letters for.

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/recommendation-letter-assistant/SKILL.md

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 content has a genuine executable core (script, parameter table, output schema) but is burdened by redundant boilerplate sections, self-referential fillers, and weakly signaled references. It is moderately actionable and organized but lacks a tight, skill-specific workflow and clean progressive disclosure.

Suggestions

Remove the self-referential filler lines ("See `## X` above for related details") and consolidate the redundant Workflow / Implementation Details / Output Requirements / Response Template sections into one concise skill-specific process.

Replace the generic validation commands with a copy-paste-ready invocation of `scripts/main.py` using the documented input parameters, and add an explicit validate-output-then-fix checkpoint.

Link `references/guidelines.md` by name from the body and move the generic meta-sections (Lifecycle Status, Evaluation Criteria, Security Checklist) into reference files so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body contains useful concrete content (parameter table, output JSON, real script) but is padded with boilerplate and self-referential fillers like "See `## Features` above for related details" that point to later sections, plus redundant restatements of the same generic workflow across multiple sections.	2 / 3
Actionability	Real executable commands (py_compile, `main.py demo`) and a runnable script exist, but the documented invocation with the actual input parameters is never shown as a copy-paste-ready example, so guidance is concrete yet incomplete.	2 / 3
Workflow Clarity	Sequenced steps and a fallback path are present, but the workflow is generic process boilerplate rather than a skill-specific sequence, and there is no explicit validate→fix→retry checkpoint tied to the script's output.	2 / 3
Progressive Disclosure	A real one-level reference file (references/guidelines.md) and script bundle exist with section structure, but the body references `references/` generically without linking the file by name and is largely a monolithic wall of boilerplate that should be condensed into an overview.	2 / 3
	Total	8 / 12 Passed

Description

57%

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 distinct niche and a concrete action but is grammatically truncated and lacks any explicit use-when trigger guidance or term variations. It is functional but incomplete and would benefit from a rewrite that finishes the sentence and adds trigger conditions.

Suggestions

Complete the truncated sentence and list multiple concrete actions (e.g., draft, structure, and tailor recommendation letters) instead of a single verb.

Add an explicit "Use when..." clause naming natural trigger terms users would say, such as "letter of recommendation," "LOR," "reference letter," "MSPE," or "Dean's Letter."

Dimension	Reasoning	Score
Specificity	The description names a concrete domain ("recommendation letters") and one action ("draft") plus the audience ("faculty and mentors"), but the sentence is truncated ("...letters for.") and lists only a single action rather than multiple specific concrete actions.	2 / 3
Completeness	It states what the skill does (draft recommendation letters) but provides no "Use when..." clause or equivalent trigger guidance, and the sentence is cut off mid-phrase; per the rubric, a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	"recommendation letters" is a natural term a user would say, but no common variations (LOR, letter of recommendation, reference letter, MSPE, Dean's Letter) are present, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	Recommendation letters for faculty/mentor use form a clear, narrow niche that is unlikely to trigger for unrelated skills, despite the truncated wording.	3 / 3
	Total	9 / 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
Path: scientific-skills/Academic Writing/recommendation-letter-assistant/SKILL.md
Commit: f5ef65b

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.