CtrlK
BlogDocsLog inGet started
Tessl Logo

aris-experiment-plan

Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `aris-research-refine`, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty, simplicity, and any LLM / VLM / Diffusion / RL-based contribution.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A well-structured, actionable planning skill with a clear phased workflow, decision gates, a final checklist, and concrete output templates. It assumes Claude's competence and avoids padding; the main gaps are a few trimmable explanatory sentences and the absence of a worked, filled-in example alongside the empty templates.

Suggestions

Add one short worked example (a filled-in Claim Map row and one Experiment Block) so the templates are unambiguous in practice and actionability reaches the top anchor.

Trim restated guidance in 'Key Rules' that duplicates the Phase 2–3 instructions to push conciseness toward maximally lean.

Consider moving the full EXPERIMENT_PLAN.md / EXPERIMENT_TRACKER.md skeletons into reference files referenced one level deep, which would let the overview stay leaner while improving progressive disclosure.

DimensionReasoningScore

Conciseness

The body is efficiently structured as phased guidance with templates and constants, and it assumes Claude's domain competence (it does not explain what an ablation or baseline is). A few explanatory sentences in the Overview and Key Rules restate phase content and could be trimmed, so it is not maximally lean.

4 / 5

Actionability

Provides highly concrete, copy-paste-ready markdown skeletons for EXPERIMENT_PLAN.md and EXPERIMENT_TRACKER.md with exact file paths, table headers, field lists, and numeric constants (MAX_PRIMARY_CLAIMS=2, DEFAULT_SEEDS=3), but offers only empty templates with no worked example showing a filled-in plan, leaving a minor gap.

4 / 5

Workflow Clarity

A clearly sequenced Phase 0–5 workflow with explicit decision/stop-go gates in Phase 4, a Final Checklist serving as a verification step, and a feedback loop for large-file writes (Write fails → retry via Bash cat heredoc), matching the top anchor for clear sequence with validation and error-recovery loops.

5 / 5

Progressive Disclosure

Well-organized into clear sections (Overview, Constants, Workflow, Key Rules, Composing with Other Skills) with no nested references and all content appropriately inline for a single-file templated workflow skill. Since it exceeds 50 lines and the large output templates could arguably live in reference files, it stops just short of the top anchor; no bundle files are present to evaluate against.

4 / 5

Total

17

/

20

Passed

Description

83%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.

A strong, third-person description that clearly states what the skill does and gives multiple explicit, natural trigger phrases for when to use it. It is highly specific to the research-planning niche with minimal conflict risk, held back only by deliverable-facets-as-actions framing and a lack of synonyms relative to the top anchor.

DimensionReasoningScore

Specificity

Names the core transformation ('Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap') and lists several concrete deliverable types (experiment plan, ablation matrix, evaluation protocol, run order, compute budget, paper-ready validation), but these are facets of one transformation rather than multiple distinct actions, so it falls just short of comprehensive coverage.

4 / 5

Completeness

Explicitly answers both 'what' (turn a proposal into a claim-driven experiment roadmap) and 'when' (use after aris-research-refine, or when the user asks for an experiment plan / ablation matrix / evaluation protocol / run order / compute budget / paper-ready validation) with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes six natural trigger phrases a researcher would actually say ('detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, paper-ready validation') plus an explicit pipeline trigger ('Use after aris-research-refine'), but lacks synonyms (e.g., benchmark, baselines) and file extensions, keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

Has a clear, specialized niche (paper-oriented experiment planning) and is pinned to a pipeline position ('Use after aris-research-refine') that distinguishes it from execution-focused siblings, but it lives in a family of closely related aris skills (aris-run-experiment, aris-research-refine), creating minor overlap risk.

4 / 5

Total

17

/

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
OpenLAIR/dr-claw
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.