control-flow

Control flow: early returns, guard clauses, linearizing nested logic. Use for "flatten these conditions", "too many nested ifs", "linearize this try-catch", or handlers mixing throw and return. For a broad "simplify this" pass over a diff or package, use collapse-pass instead.

Quality

88%

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

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 highly actionable, clearly sequenced refactoring skill with strong executable examples and a checklist-style core pattern. Its weaknesses are token efficiency (philosophical framing and repeated summaries) and the lack of any progressive-disclosure structure for a relatively long, monolithic body.

Suggestions

Trim the 'human reasoning' framing and the repeated closing summary paragraphs (e.g. the 'Try the risky thing / Check if it failed' list and 'Every guard has the same shape...') since the code already demonstrates the pattern.

Consider moving two or three of the five inline examples into a referenced file (e.g. examples.md) and keeping SKILL.md as a tighter overview with the Core Pattern plus one canonical before/after, to add genuine progressive disclosure.

Add a brief behavior-preservation note (run tests / confirm output unchanged after refactoring) as an explicit checkpoint to strengthen workflow clarity for the refactor.

Dimension	Reasoning	Score
Conciseness	Mostly lean with concrete code, but the 'mirror natural human reasoning' framing (e.g. 'Ask the human question first') and repeated closing summaries ('Every guard has the same shape...') add tokens that could be tightened; it does not pad with basic concepts Claude already knows (which would be level 1), yet not every token earns its place (level 3).	2 / 3
Actionability	Multiple complete, executable TypeScript before/after examples drawn from a real codebase (e.g. checkFfmpegRecordingMethodCompatibility, the trySync refactor) — copy-paste ready rather than pseudocode (level 2) or abstract direction (level 1).	3 / 3
Workflow Clarity	Clear numbered Core Pattern checklist plus a guard-by-guard sequence with consistent check → return-early shape; this is non-destructive refactoring so the validation cap does not apply, and the single repeatable action is unambiguous rather than a sequence with implicit checkpoints (level 2).	3 / 3
Progressive Disclosure	Well-organized with clear section headers, but it is a single monolithic ~160-line file with five inline examples and no progressive-disclosure mechanism (no references deferring detail); it exceeds the under-50-line simple-skill carve-out and the level-3 anchor expects content appropriately split across files.	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, well-targeted description: it states concrete capabilities, quotes natural user trigger phrases, covers both what and when, and explicitly routes the overlapping broad-simplify case to a sibling skill. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete refactoring actions — 'early returns, guard clauses, linearizing nested logic' and 'handlers mixing throw and return' — matching the multiple-specific-actions anchor; it is not merely naming a domain plus a few actions (level 2).	3 / 3
Completeness	Explicitly answers both what ('Control flow: early returns, guard clauses, linearizing nested logic') and when ('Use for ...'), with explicit trigger guidance, so it is not a what-only/when-implied level 2.	3 / 3
Trigger Term Quality	Provides quoted natural phrases a user would actually say — "flatten these conditions", "too many nested ifs", "linearize this try-catch" — giving good coverage of natural terms rather than just some relevant keywords (level 2).	3 / 3
Distinctiveness Conflict Risk	Owns a clear niche (control-flow/nested-logic refactoring) and actively disambiguates with 'For a broad "simplify this" pass over a diff or package, use collapse-pass instead', making wrong-skill conflicts unlikely rather than merely somewhat specific (level 2).	3 / 3
	Total	12 / 12 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: EpicenterHQ/epicenter
Path: .agents/skills/control-flow/SKILL.md
Commit: cb12bcc

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.