CtrlK
BlogDocsLog inGet started
Tessl Logo

research-add-items

Add more items (research objects) to an existing outline.yaml. Optionally launches a web-search subagent to suggest items in the topic's domain.

59

Quality

68%

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 ./plugins/ultra-research/skills/research-add-items/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 a tight, well-structured orchestration workflow with concrete prompts, a clear sequence, and a user-confirmation checkpoint guarding the write operation. The main gap is the absence of an explicit validate/fix/retry feedback loop, which keeps workflow clarity at 4 rather than 5.

Suggestions

Add an explicit validation/retry loop after appending to outline.yaml (e.g. re-read the file, confirm the new entries persisted and remain deduplicated, fix and retry if not) to push workflow clarity toward 5.

Trim the routing rationale duplicated between the Pipeline Context section and Step 4 to tighten conciseness further.

Consider consolidating the thinness-rubric thresholds into a single reference (e.g. a short bulleted checklist) so the routing logic is scannable at a glance.

DimensionReasoningScore

Conciseness

The body is largely lean and assumes Claude's competence (exact Glob patterns, quoted prompts, a compact thinness rubric table), with only minor redundancy such as the routing rationale being previewed in Pipeline Context and re-stated in Step 4; not a 5 because a few sentences could still be trimmed.

4 / 5

Actionability

Guidance is concrete and largely copy-paste ready — the exact Glob pattern "*/outline.yaml", the literal AskUserQuestion prompts, the dedup-by-name rule, and the labeled routing options with "(Recommended)" suffixes; for an instruction-only orchestration skill this is mostly executable guidance with only minor gaps, just short of fully copy-paste-ready code.

4 / 5

Workflow Clarity

Four steps are clearly sequenced with an explicit user-confirmation checkpoint before the write (Step 3) and a thinness-rubric inspection after saving (Step 4); not a 5 because there is no explicit error-recovery/validate-then-retry feedback loop, though the confirmation checkpoint keeps it above the destructive-cap-of-3 threshold.

4 / 5

Progressive Disclosure

No bundle files are needed and none are referenced; the skill is short and cleanly organized into well-signaled sections (Trigger, Pipeline Context, Workflow Steps 1-4, Output), so per the simple-skill guidance a well-organized single file with no external references earns a 5.

5 / 5

Total

17

/

20

Passed

Description

58%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 states concrete, specific actions and a distinct target artifact, but omits any explicit "Use when..." trigger guidance, which caps completeness and weakens trigger-term quality. Adding a natural-language trigger clause would lift the two lowest dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when the initial item list in outline.yaml is missing topics and you want to add more before deep research."

Include natural user-facing synonyms (e.g. "research items", "add topics", "expand the outline") rather than only pipeline-internal jargon like "research objects".

Clarify the "when" context (after /research and before /research-deep) directly in the description so users know when to invoke it.

DimensionReasoningScore

Specificity

Lists specific concrete actions — "Add more items (research objects) to an existing outline.yaml" and "launches a web-search subagent to suggest items" — with a named target file and mechanism, leaving only minor coverage gaps; not a 5 because there are just two actions rather than comprehensive coverage.

4 / 5

Completeness

The description gives a clear "what" (add items to outline.yaml, optionally launch a subagent) but has no "Use when..." clause or equivalent trigger guidance, so per the rubric completeness is capped at 3 even though the "what" is clear.

3 / 5

Trigger Term Quality

Relevant keywords exist ("items", "outline.yaml", "web-search", "topic's domain") but they skew toward pipeline-internal jargon and lack the natural synonyms/variations a user would spontaneously say, fitting the "some relevant keywords but missing common variations" anchor.

3 / 5

Distinctiveness Conflict Risk

"Add more items (research objects) to an existing outline.yaml" carves a fairly distinct niche tied to a specific pipeline artifact, with only minor overlap risk against the sibling research-add-fields skill; not a 5 because the pipeline siblings could still collide.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
seanGSISG/claude-depot
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.