CtrlK
BlogDocsLog inGet started
Tessl Logo

discussion-section-architect

Structures and writes discussion sections for academic papers and research reports. Use when writing a discussion section, interpreting research results, connecting findings to existing literature, addressing study limitations, synthesizing conclusions, or drafting any part of...

66

Quality

81%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The body has a clear, well-sequenced workflow with a useful revision checklist, but it is verbose due to repeated generic guardrail sections and its references are partly misleading (cited files missing, duplicate References heading). Tightening the templated sections and fixing the references would raise quality.

Suggestions

Remove or merge the redundant guardrail sections (Output Requirements, Error Handling, Input Validation, Output Contract, Failure Handling, User Checkpoints, Quick Validation) into a single concise block, keeping only what Claude would not already infer.

Fix the '## References' section: it cites 'references/guide.md' and 'references/examples/' that do not exist and duplicates the '## References' heading — point only to the real 'references/audit-reference.md'.

Show what 'python scripts/main.py --help' produces or document the script's actual output, so the script reference is actionable rather than a validation-only command.

DimensionReasoningScore

Conciseness

Mostly efficient in the core sections but padded with several overlapping generic guardrail blocks (Output Requirements, Error Handling, Input Validation, Output Contract, Failure Handling, User Checkpoints, Quick Validation) that restate scope/validation/fallback guidance multiple times.

2 / 3

Actionability

Provides concrete structure templates, a revision checklist, and worked example input/output pairs, but the core guidance is prose rather than executable code and the bundled script is only invoked via '--help' without showing its output.

2 / 3

Workflow Clarity

The Draft→Revise loop is clearly sequenced with an explicit re-check step and checklist, and the Quick Start and Workflow sections give an ordered path with validation feedback.

3 / 3

Progressive Disclosure

References are signaled but partly broken: the body cites 'references/guide.md' and 'references/examples/' that do not exist (only 'audit-reference.md' is present) and the '## References' heading is duplicated.

2 / 3

Total

9

/

12

Passed

Description

100%

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 is specific, complete, and well-targeted: it names concrete actions, provides an explicit 'Use when' trigger covering natural user phrasing, and occupies a distinct niche. It is among the strongest reference examples in the rubric.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions ('Structures and writes discussion sections,' 'interpreting research results,' 'connecting findings to existing literature,' 'addressing study limitations,' 'synthesizing conclusions').

3 / 3

Completeness

Explicitly answers both what it does and when to use it via the 'Use when writing a discussion section...' trigger clause.

3 / 3

Trigger Term Quality

Uses natural academic-writing phrasing a user would say ('writing a discussion section,' 'interpreting research results,' 'addressing study limitations,' 'synthesizing conclusions').

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (academic discussion sections) with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

16

Passed

Repository
aipoch/medical-research-skills
Reviewed

Table of Contents

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.