CtrlK
BlogDocsLog inGet started
Tessl Logo

research-add-fields

Add field definitions to existing research outline.

55

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/research-codex-en/research-add-fields/SKILL.md

The canonical home for this skill is research-add-fields in Weizhena/Deep-Research-skills

SKILL.md
Quality
Evals
Security

Quality

Content

72%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.

A concise, well-organized simple workflow that scores well on token efficiency and structure, but loses points on actionability and workflow clarity due to a missing YAML field schema and absent validation feedback for the in-place edit.

Suggestions

Add a concrete example of a field definition's YAML structure (showing name, description, category, detail_level keys) so the append step is unambiguous and copy-paste ready.

Insert a validation/verification checkpoint after appending — e.g. re-read and parse fields.yaml to confirm valid syntax and no duplicate field names before finishing.

Specify how the Step 2B web-search agent should be launched and what it returns, so that step is actionable rather than purely directional.

DimensionReasoningScore

Conciseness

The ~26-line body is lean and efficient with no concept explanations Claude already knows; every line (Trigger, 4 numbered steps, Output) earns its place.

3 / 3

Actionability

Steps are concrete and sequenced, but key details are missing — no example field-definition YAML structure and no specification of the field keys (name, description, category, detail_level), so the append step is not copy-paste ready.

2 / 3

Workflow Clarity

A clear 4-step sequence with a user-confirmation checkpoint exists, but the in-place file modification lacks an explicit validation/verification feedback loop (e.g. re-parse YAML, check for duplicates), which caps workflow clarity at 2 for destructive edits.

2 / 3

Progressive Disclosure

Under 50 lines with no need for external references, the content is well-organized into clearly signaled sections (Trigger, Workflow, Output), satisfying the simple-skill allowance for a top score.

3 / 3

Total

10

/

12

Passed

Description

50%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 clearly states a single concrete action and domain but omits any 'when to use' trigger guidance and natural keyword variations, leaving every dimension at the mid-level anchor.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to supplement or expand the fields in an existing research outline's fields.yaml'.

Include natural trigger-term variations users might say, such as 'add fields', 'extend research fields', 'supplement outline fields', or 'fields.yaml'.

List multiple concrete actions (e.g. 'auto-locate, append, and categorize field definitions in fields.yaml') to raise specificity.

DimensionReasoningScore

Specificity

Names a concrete action ("Add field definitions") and domain ("existing research outline"), matching the 'names domain and some actions' anchor, but lists only a single action rather than multiple specific concrete actions.

2 / 3

Completeness

It states what the skill does but has no 'Use when...' clause or equivalent trigger guidance, so per the judging guidelines completeness is capped at 2 (has what, when missing/implied).

2 / 3

Trigger Term Quality

Contains relevant keywords ("field definitions", "research outline") but offers no common variations or natural user phrasings, fitting 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

The 'research outline' + 'field definitions' niche is somewhat specific, but the brief description and absent trigger guidance mean it could still overlap with other research-related skills.

2 / 3

Total

8

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Weizhena/Deep-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.