replication

Plan a replication of a paper, claim, or benchmark, and execute only after an explicit environment choice. Use when the user asks to replicate results, reproduce an experiment, verify a claim empirically, or build a replication package.

Quality

80%

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/replication/SKILL.md

Quality

Content

76%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 concise, mostly actionable delegating skill that gates execution on an environment choice. Its main weakness is the absence of an explicit validation/verification checkpoint for what can be a batch or destructive operation, capping workflow clarity.

Suggestions

Add an explicit verification step after execution (e.g., check that scripts ran successfully and outputs were written before reporting results) to lift workflow clarity above the destructive/batch cap of 3.

Add a short "## Workflow" / "## Output" structure (or a numbered sequence) so the environment-choice gate and output handling read as a clear ordered process rather than flat prose.

Note briefly how to confirm the `/replicate` workflow is available and what to do if it is missing, closing the one actionability gap in this delegating skill.

Dimension	Reasoning	Score
Conciseness	Four lean lines each carrying distinct information (workflow invocation, slash-command caveat, agents, environment gating, output spec) with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	Gives concrete, runnable guidance (invoke `/replicate`, enumerate four specific environments, specify saved outputs), but the actual workflow body lives in the referenced slash command rather than inline, leaving a minor gap.	4 / 5
Workflow Clarity	Sequence is present with an environment-choice checkpoint before code runs, but there is no result validation/verification step; since replication can be a batch/destructive operation, the missing validation caps this at 3.	3 / 5
Progressive Disclosure	A short, single-purpose skill with no bundle files and reasonable labeling ("Agents used:", "Output:"), but the body is flat prose under one heading rather than clearly delineated sections, leaving minor organization gaps.	4 / 5
	Total	16 / 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 both capability and explicit trigger conditions with concrete natural-language phrases. It is specific and well-targeted, with only minor overlap and synonym-coverage gaps.

Dimension	Reasoning	Score
Specificity	Names the domain ("replication of a paper, claim, or benchmark") and several concrete behaviors (plan, gate execution on an explicit environment choice, then execute), landing above the 1-2-action anchor but short of comprehensive multi-action coverage.	4 / 5
Completeness	Explicitly answers both what ("Plan a replication... and execute only after an explicit environment choice") and when ("Use when the user asks to replicate results, reproduce an experiment, verify a claim empirically, or build a replication package") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("replicate results", "reproduce an experiment", "verify a claim empirically", "build a replication package") with replicate/reproduce synonyms, though a few variants like "rerun" or "reproduction package" are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear empirical-replication niche with distinct triggers, but "verify a claim empirically" has minor overlap risk with general analysis or verification skills.	4 / 5
	Total	17 / 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: companion-inc/feynman
Path: skills/replication/SKILL.md
Commit: 95c51d9

Reviewed: about 9 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.