CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

research-add-items

Add items (research objects) to existing research outline.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 content is concise and well-structured for a simple skill, but its actionability is incomplete and its workflow lacks an explicit validation/feedback loop for the in-place outline.yaml modification. Adding concrete merge/dedup details and a validation checkpoint would raise the weaker dimensions.

Suggestions

Specify the outline.yaml schema and a concrete merge/dedup procedure (e.g., key fields to match on for duplicate detection) so the append step is executable rather than abstract.

Add an explicit validation checkpoint after merging (e.g., re-parse outline.yaml to confirm valid YAML and that no duplicates remain) with a fix-and-retry feedback loop before saving.

Make the 'auto-read' and 'save' steps concrete with the actual tool calls or commands to use rather than describing the intent.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: short sequenced steps with no padding or explanation of concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

Gives some concrete guidance (a concrete file glob '*/outline.yaml', parallel agent launch, append/confirm/save actions) but is incomplete — no outline.yaml schema, no concrete merge or dedup mechanism, so it stays at 'some concrete guidance but incomplete'.

3 / 5

Workflow Clarity

Steps are sequenced (locate, supplement in parallel, merge/update) with a user-confirmation checkpoint, but the in-place destructive modification of outline.yaml lacks an explicit validate/feedback loop, capping workflow clarity at 3 per the destructive-operations guideline.

3 / 5

Progressive Disclosure

This is a short single-purpose skill (under 50 lines) with clear sections (Trigger, Workflow, Output) and no need for external references, so progressive disclosure scores 5 per the simple-skill scoring note.

5 / 5

Total

16

/

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 is concise and names a concrete action and domain, but it omits any explicit trigger guidance ('Use when...'), which caps completeness. It is reasonably distinct but would benefit from natural user-facing trigger terms.

Suggestions

Add a 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when the user wants to add or supplement research objects in an existing research outline.yaml').

Include natural trigger terms and synonyms a user would actually say (e.g., 'research outline', 'add sources', 'supplement outline', 'outline.yaml').

Broaden the specificity by listing the concrete operations supported (e.g., append, deduplicate, and confirm new research objects) rather than a single 'Add items' action.

DimensionReasoningScore

Specificity

Names the domain ('existing research outline') and one concrete action ('Add items (research objects)'), matching the '1-2 concrete actions, not comprehensive' anchor; below 4 because only a single action is named with no breadth of operations.

3 / 5

Completeness

Provides a clear 'what' (add items to an existing research outline) but no explicit 'when'/'Use when...' trigger guidance, so completeness is capped at 3 per the missing-trigger-clause guideline.

3 / 5

Trigger Term Quality

Contains relevant domain terms ('research objects', 'research outline') but lacks common variations, synonyms, or natural phrasings a user would say, fitting the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The niche of supplementing an existing research outline is fairly distinct with minor overlap risk against related research skills; below 5 because no concrete trigger phrases sharpen the boundary.

4 / 5

Total

13

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Weizhena/Deep-Research-skills

Path

skills/research-codex-en/research-add-items/SKILL.md

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.