formula-derivation

Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a paper-ready formula document. Use when the derivation target is not yet fully fixed, the main object still needs to be chosen, or the user needs a coherent derivation package rather than a finished theorem proof.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

A well-sequenced, actionable instruction skill with strong workflow clarity and a real verification/feedback loop. Its weaknesses are moderate internal redundancy and a monolithic structure with no progressive disclosure for a longer-than-trivial skill.

Suggestions

Remove the 'Key Rules' section or replace it with a one-line pointer to the relevant workflow steps, since it duplicates Step 3/4/5/8 guidance and inflates the token budget.

Split the 'Required File Structure' template and the per-status 'Output Modes' detail into a referenced reference file (e.g. DERIVATION_TEMPLATE.md), keeping SKILL.md as an overview that links one level deep.

De-duplicate Step 7's 'derivation package must include' bullet list against the 'Required File Structure' code block so the canonical structure lives in one place.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's intelligence, but the terminal 'Key Rules' section restates workflow content (separate identity/proposition/approximation, keep one invariant object, mark uncertainty) and the 'Required File Structure' template overlaps Step 7's 'must include' list.	2 / 3
Actionability	Instruction-only yet highly actionable: exact target file (DERIVATION_PACKAGE.md), explicit STATUS values, a fill-in document template, and concrete step classifications (identity/proposition/approximation/interpretation).	3 / 3
Workflow Clarity	An explicit 8-step sequence culminates in a 'Final Verification' checklist, with a feedback loop that downgrades to a blocker report when the derivation cannot be made coherent honestly.	3 / 3
Progressive Disclosure	Sections are clearly organized, but the skill is a ~270-line monolithic file with no external references, and content that could be split (the file-structure template, output modes) is inline; the under-50-line exception does not apply.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 states concrete capabilities and gives an explicit 'Use when' trigger while distinguishing itself from the related proof-writer skill. Every dimension is well-satisfied with no vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a paper-ready formula document' — rather than naming only a domain.	3 / 3
Completeness	Answers both what (structures/derives research formulas) and when via an explicit 'Use when the derivation target is not yet fully fixed, the main object still needs to be chosen...' clause.	3 / 3
Trigger Term Quality	Covers natural phrasings users would actually say, including '推导公式', 'build a theory line', 'organize assumptions', and 'rewrite theory notes into a paper-ready formula document'.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche distinct from theorem proving ('rather than a finished theorem proof'), making conflict with a sibling proof skill unlikely.	3 / 3
	Total	12 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Commit: fe5963c

Reviewed: about 15 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.