research-and-planning

Perform structured research and turn findings into an implementation plan.

Quality

50%

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 ./.agents/skills/research-and-planning/SKILL.md

Quality

Content

51%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 token-efficient and well-structured but nearly empty of actionable content, relying entirely on referenced files that are missing. Without those files it offers only vague direction and no real workflow.

Suggestions

Add the missing reference files (reference/research.md and reference/make-plan.md) or inline the core workflow steps so the skill is self-contained.

Include a concrete sequenced workflow with explicit steps (e.g., 1. clarify requirements 2. gather findings 3. draft plan 4. validate against constraints) rather than a single vague sentence.

Add at least one validation checkpoint (e.g., confirm requirements with the user before producing the plan) to raise workflow clarity above 3.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean — a one-line purpose and a short references list with no padding or over-explanation of concepts Claude already knows, matching the score-5 anchor of every token earning its place.	5 / 5
Actionability	"Use this skill to clarify requirements and produce a plan" gives only minimal high-level hints with no concrete steps, and the referenced workflow files do not exist, so no executable guidance is available — between scores 1 and 2.	2 / 5
Workflow Clarity	Only a rough implied sequence (clarify → plan → implement) is present with steps poorly defined and no validation checkpoints, matching the score-2 anchor of a rough sequence with many gaps.	2 / 5
Progressive Disclosure	Structure is clear with a labeled one-level-deep References section, but the referenced paths (reference/research.md, reference/make-plan.md) do not exist in the bundle, so navigation is broken; scoring against actual bundle structure caps this at 3.	3 / 5
	Total	12 / 20 Passed

Description

50%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 a clear purpose in third person but lacks any explicit "Use when..." trigger guidance and offers only high-level actions. It is competent but generic, capping completeness and trigger quality at the midpoint.

Suggestions

Add a "Use when..." clause naming concrete triggers users would say (e.g., "Use when starting a new feature, investigating an unfamiliar codebase, or before writing implementation code").

List 1-2 more concrete actions to lift specificity (e.g., "gather requirements, survey relevant files, draft a step-by-step plan with milestones").

Include synonyms/natural variations of trigger terms to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (research/planning) and two actions — "Perform structured research" and "turn findings into an implementation plan" — but the actions are high-level and not comprehensive, matching the score-3 anchor.	3 / 5
Completeness	Gives a clear "what" but no "when"/"Use when..." clause; per the judging guidelines a missing explicit trigger caps completeness at 3, matching the score-3 anchor.	3 / 5
Trigger Term Quality	Contains relevant natural keywords ("research", "plan", "implementation plan") but lacks synonyms, variations, or trigger phrasing, fitting the score-3 anchor of some keywords with missing variations.	3 / 5
Distinctiveness Conflict Risk	"Structured research" and "implementation plan" form a mild niche but research/planning is broad and could overlap with many skills, matching the score-3 anchor of somewhat specific with overlap risk.	3 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: pymc-labs/CausalPy
Path: .agents/skills/research-and-planning/SKILL.md
Commit: f94d7af

Reviewed: 3 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.