ds-experiment

Use when a quest is ready for a concrete implementation pass or a main experiment run tied to a selected idea and an accepted baseline.

Quality

76%

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 ./skills/ds-experiment/SKILL.md

Quality

Content

77%

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

The body is highly actionable with concrete APIs, paths, and a well-sequenced validated workflow. Its main weakness is token efficiency and progressive disclosure: heavy repetition and long inline protocol/palette sections bloat what should be a lean overview pointing to reference files.

Suggestions

Move the long-running bash_exec command protocol (section 5.1) and the connector-chart palette/style requirements into a reference file, leaving only a concise pointer in SKILL.md.

Deduplicate the run-contract material by stating it once in the Workflow section and cross-referencing it from 'Stage purpose', 'Quick workflow', and 'Preconditions and gate' instead of restating the field list repeatedly.

Consolidate the 'memory rules' and 'artifact rules' sections into a short summary plus a reference, since their exhaustive field/tag catalogs add length without changing the core instruction.

Dimension	Reasoning	Score
Conciseness	The body is ~810 lines with substantial repetition (the run contract recurs across 'Stage purpose', 'Quick workflow', 'Workflow step 1', 'Preconditions and gate', and 'Required plan and checklist'), and long inline sections like the bash_exec protocol and chart-palette hex codes that a leaner skill would offload, so it is mostly efficient but could be tightened well below the score-3 bar.	2 / 3
Actionability	It gives fully concrete, executable guidance: exact artifact calls (e.g., 'artifact.record_main_experiment(...)'), bash_exec modes with parameters, exact paths like 'artifacts/experiment/<run_id>/', and enumerated manifest fields and verdict enums — copy-paste ready.	3 / 3
Workflow Clarity	An explicit 8-step Workflow is sequenced with validation checkpoints (preflight, 'Validate the outputs', an 'Acceptance gate') and clear feedback loops (diagnosis mode, last-known-good rule, validate-fix-retry), matching the score-3 anchor for risky batch operations.	3 / 3
Progressive Disclosure	Real one-level-deep references exist and are clearly signaled (references/evidence-ladder.md, main-experiment-plan-template.md, main-experiment-checklist-template.md), but the SKILL.md itself is a monolithic 810-line wall with large inline sections (bash_exec protocol, chart palettes, memory rules) that read like content that should be split into reference files, matching the score-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 has an explicit 'Use when' trigger and a clear, distinctive niche within its quest workflow. Its weakness is jargon-heavy trigger terms and abstract action language rather than concrete capability verbs.

Suggestions

Add concrete capability verbs (e.g., 'run and record a main experiment, capture metrics and logs, compare against baseline') so the 'what' is more actionable.

Add natural-language trigger variations a user would actually say, such as 'run the experiment', 'main run', 'baseline comparison', or 'measure the selected idea'.

Consider whether 'quest' jargon should be paired with a plainer synonym so the description reads naturally outside this system's vocabulary.

Dimension	Reasoning	Score
Specificity	Phrases like 'a concrete implementation pass or a main experiment run' name the domain and a couple of actions, but the actions are abstract rather than a comprehensive list of concrete capabilities, matching the score-2 anchor.	2 / 3
Completeness	It explicitly answers both what ('a concrete implementation pass or a main experiment run') and when ('Use when a quest is ready...') with an explicit 'Use when' trigger clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	Terms such as 'quest', 'implementation pass', 'main experiment run', 'selected idea', and 'accepted baseline' are domain jargon that researchers in this system might say, but common natural variations a user would say are largely missing, so it sits at 2 rather than 3.	2 / 3
Distinctiveness Conflict Risk	It is tightly scoped to a specific workflow state (selected idea + accepted baseline within a quest), giving it a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (811 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/ds-experiment/SKILL.md
Commit: 6da7f7c

Reviewed: about 8 hours 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.