recommendation-letter-assistant

Helps faculty and mentors draft standardized recommendation letters for.

Quality

51%

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

48%Weight 40%Scale 1-5

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

The skill body is well-structured with headers and a real executable script, but it is padded with generic boilerplate sections unrelated to recommendation letters and does not show how to actually invoke the skill with real inputs. References are only loosely signaled at the directory level.

Suggestions

Remove or relocate generic boilerplate (Risk Assessment, Security Checklist, Lifecycle Status, generic Evaluation Criteria) that does not advance the recommendation-letter task, to improve conciseness.

Document an executable command that passes real Input Parameters (applicant_name, relationship, duration, key_strengths, context) to scripts/main.py so the skill can be run for an actual letter, not just the demo path.

Link the specific reference file by name (e.g., 'See [references/guidelines.md](references/guidelines.md) for AAMC/ERAS and competency guidance') so references are clearly signaled one level deep.

Dimension	Reasoning	Score
Conciseness	The body runs ~200 lines with several generic padded sections (Risk Assessment table, Security Checklist, Lifecycle Status, Evaluation Criteria, Output Requirements) that are boilerplate rather than specific to recommendation letters. This matches the anchor for noticeably verbose with several unnecessary padded sections, and is not 3 because the padding is substantial rather than incidental.	2 / 5
Actionability	Concrete commands are present (py_compile, --help, demo) and the output format is concrete JSON, but the only skill-invoking command uses hardcoded demo defaults and there is no documented way to pass the real Input Parameters to actually draft a letter. This matches the anchor for some concrete guidance but incomplete with key details missing.	3 / 5
Workflow Clarity	The 5-step Workflow has a clear sequence with explicit validation (step 2 stops on unsupported scope) and a fallback feedback loop (step 5). It is not 5 because the steps are generic rather than recommendation-letter-specific, and not 3 because checkpoints are explicit.	4 / 5
Progressive Disclosure	scripts/main.py is clearly referenced and real, but references/ is signaled only at the directory level (guidelines.md is not linked by name), and substantial generic boilerplate is inlined that should be trimmed or moved. This matches the anchor for some structure with references present but not clearly signaled and content that should be separate inline.	3 / 5
	Total	12 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 one concrete action but is grammatically truncated and lacks any explicit 'when to use' trigger guidance, capping completeness. Keyword coverage is reasonable but misses common synonyms like LOR and letter of recommendation.

Suggestions

Complete the truncated sentence and add an explicit 'Use when...' clause naming natural triggers (e.g., 'Use when faculty or mentors ask for a letter of recommendation, LOR, reference letter, or MSPE/Dean's Letter').

Add 1-2 more concrete actions (e.g., 'draft, structure, and tailor recommendation letters') to lift specificity toward comprehensive coverage.

Include common synonyms and the medical-training context (residency, fellowship, MSPE) to improve trigger-term quality and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names the domain (recommendation letters) and one concrete action ('draft standardized recommendation letters'), matching the anchor for domain plus 1-2 concrete actions. It does not reach 4 because only a single action is given, and the sentence is truncated ('for.').	3 / 5
Completeness	It gives a clear 'what' (drafting standardized recommendation letters) but contains no 'when' / 'Use when...' trigger clause at all, which the rubric caps at 3. It is not 2 because the 'what' is concrete rather than vague.	3 / 5
Trigger Term Quality	It includes relevant keywords ('recommendation letters', 'faculty', 'mentors') but omits common natural synonyms users say such as 'letter of recommendation', 'LOR', 'reference letter', or 'MSPE/Dean's Letter'. This matches the anchor for some relevant keywords but missing common variations.	3 / 5
Distinctiveness Conflict Risk	The recommendation-letter niche is fairly distinct with minor overlap risk against general academic-writing skills. It falls short of 5 because the truncated description lacks explicit 'Use when...' trigger phrases that would fully distinguish it.	4 / 5
	Total	13 / 20 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: 63c61d3

Reviewed: 8 hours 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.