CtrlK
BlogDocsLog inGet started
Tessl Logo

research

Structure a research based on the user request. Identify what must change in order to complete the task.

49

Quality

53%

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 ./.claude/skills/research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

The body is reasonably lean and well-organized for a short, single-file skill, but its guidance is mostly abstract with no concrete examples or explicit validation checkpoints, leaving actionability and workflow clarity at the middle level. It works as a high-level checklist but does not give copy-paste-ready instruction.

Suggestions

Add a concrete runnable example of a temporal python test file and how its output drives the next decision, to lift actionability.

Insert an explicit validation checkpoint in the testing workflow (e.g., "if execution fails, fix the assumption and re-run until the output confirms the logic").

Remove the repeated frontmatter description from the body and tighten redundant lines to improve conciseness.

DimensionReasoningScore

Conciseness

The ~35-line body is lean and avoids over-explaining concepts Claude knows, but repeats the frontmatter description ("Structure a research based on the user request. Identify what must change...") and contains rough, slightly redundant phrasing like "everything must be collapse in the research file", fitting "mostly efficient but could be tightened"; not level 3 due to redundancy, not level 1 because it is not padded.

2 / 3

Actionability

It offers some concrete specifics ("create a folder under .cursor/plans", "save all your discoveries under .cursor/plans/{plan_name_folder}/research", "Create temporal python files... Execute this python code") but mostly vague direction ("Make reasonable technical decisions", "Identify what should be change") with no executable commands or examples, matching "some concrete guidance but incomplete"; not level 1 because concrete paths exist, not level 3 because nothing is copy-paste ready.

2 / 3

Workflow Clarity

The "You must:" bullet list provides steps and the testing section implies validate-by-execution, but there is no explicit validation checkpoint or validate→fix→retry feedback loop, and for a skill involving test validation such checkpoints matter, matching "steps listed but validation gaps"; not level 3 because checkpoints are missing, not level 1 because steps are listed.

2 / 3

Progressive Disclosure

The skill is a single self-contained file under 50 lines with no bundle files and no external references, organized into clear sections (## Python test validations, ## Document base); per the simple-skills note this warrants a 3 for well-organized content, not level 2 because no inline content should be split out.

3 / 3

Total

9

/

12

Passed

Description

50%

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 names the research domain and a couple of actions but stays abstract and lacks any "Use when..." trigger guidance, capping it at the middle level across all dimensions. It reads as a mediocre, generic description rather than a sharply targeted one.

Suggestions

Add an explicit "Use when..." clause naming natural user triggers (e.g., when the user asks to research or investigate a change before planning).

Replace abstract phrasing like "Structure a research" with concrete capabilities (e.g., "Investigate the codebase, identify affected files, and draft a tested research plan").

Include common trigger-term variations such as investigate, explore, and analyze to improve distinctiveness and trigger quality.

DimensionReasoningScore

Specificity

Quotes "Structure a research based on the user request" and "Identify what must change in order to complete the task" name the research domain and two actions, but the actions are abstract rather than comprehensive concrete capabilities, matching the level-2 anchor; not level 3 because no multiple specific concrete actions, not level 1 because it does name real actions.

2 / 3

Completeness

It states what ("Structure a research... Identify what must change") but gives no "Use when..." clause or equivalent trigger, so per the judging guidelines a missing when caps completeness at 2; not level 3 because when is entirely absent, not level 1 because a what is present.

2 / 3

Trigger Term Quality

"research" is a natural term a user might say, but the phrasing "structure a research" is awkward and common variations like investigate, explore, or analyze are absent, fitting "some relevant keywords but missing common variations"; not level 1 because "research" is natural rather than jargon, not level 3 because coverage is thin.

2 / 3

Distinctiveness Conflict Risk

"research" is broad and could overlap with planning, exploration, or code-review skills, matching "somewhat specific but could still overlap with similar skills"; not level 1 because it is not as generic as "helps with code and documents", not level 3 because it lacks a clearly distinct niche.

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
pymc-labs/pymc-marketing
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.