research

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

Quality

41%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/research/SKILL.md

Quality

Content

46%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 body is a compact, reasonably structured instruction-only skill with a clear output location, but it is light on actionable specifics and lacks explicit validation checkpoints in its testing workflow. Adding a concrete example/template and an explicit test-validate loop would materially raise quality.

Suggestions

Provide a minimal example of the expected research .md structure (section headings and a sample entry) so the output is copy-paste concrete.

Turn the testing step into an explicit validate-fix-retry loop: run the temp script, assert the expected output, fix and re-run until it passes, then delete.

Tighten the opening (drop the line that restates the description) and replace vague phrasing like "check the logics you are thinking" with a specific validation objective per temp script.

Dimension	Reasoning	Score
Conciseness	The body is short and does not explain concepts Claude already knows, but the opening line duplicates the description and phrasing like "check the logics you are thinking" could be tightened, so it is mostly efficient with some trimmable redundancy.	3 / 5
Actionability	Beyond the concrete output path (.claude/plans/{plan_name_folder}/research.md), the guidance is high-level hints ("check the logics you are thinking", "make reasonable technical decisions") with no example research file, template, or concrete testing recipe, matching minimal concrete guidance.	2 / 5
Workflow Clarity	The must-do bullets and section order give a recognizable sequence, but validation checkpoints are only implicit ("based on the output decide what should be done") with no explicit validate/fix/retry loop, fitting the steps-listed-but-checkpoints-implicit anchor.	3 / 5
Progressive Disclosure	At under 50 lines with no need for external references, it is organized into clear sections (Python test validations, Document base) with a bulleted must-do list; minor roughness in flow keeps it just below a 5.	4 / 5
	Total	12 / 20 Passed

Description

37%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 conveys the skill's purpose at a high level but lacks concrete actions, natural trigger terms, and any explicit "when to use" guidance. It is moderately distinct but generic enough to risk overlap with other planning skills.

Suggestions

Add concrete actions to the description (e.g., 'investigate affected Python files, enumerate required changes, and draft a tested solution plan').

Append a 'Use when...' trigger clause naming natural phrases a user would say (e.g., 'Use when planning a code change, scoping a task, or researching what needs to change before implementation').

Sharpen the niche by referencing the specific output (a research .md under .claude/plans) to reduce overlap with generic planning skills.

Dimension	Reasoning	Score
Specificity	It names the domain ("research") but the actions are generic ("Structure a research", "Identify what must change") rather than concrete, matching the score-2 anchor; it does not list 1-2 concrete actions that would warrant a 3.	2 / 5
Completeness	It states a clear-enough "what" (structure research, identify changes) but provides no "when" / trigger guidance, so per the missing-trigger cap it lands at 3 rather than 4.	3 / 5
Trigger Term Quality	Only "research" is a natural keyword; there is no "Use when..." clause and no common variations or synonyms, so it matches one-or-two generic keywords with the natural phrases missing.	2 / 5
Distinctiveness Conflict Risk	"research" is somewhat specific but the activity is broad and could overlap with general planning or analysis skills, fitting the somewhat-specific-but-overlap anchor.	3 / 5
	Total	10 / 20 Passed

Validation

100%

Warnings & errors only

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: pymc-labs/pymc-marketing
Path: .claude/skills/research/SKILL.md
Commit: 66d575d

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.