sciomc

Orchestrate parallel scientist agents for comprehensive analysis with AUTO mode

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/sciomc/SKILL.md

Quality

Content

52%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.

The content is highly actionable with a clear, well-checkpointed workflow and concrete executable examples, but it is verbose and fails progressive disclosure: everything lives in one ~505-line file with no reference files for the bulky templates and schemas.

Suggestions

Move the full report template, state.json schema, and regex extraction library into separate reference files (e.g. REPORT_TEMPLATE.md, STATE_SCHEMA.md) and link them one level deep from SKILL.md.

Trim redundant routing/decision tables and remove explanations of concepts Claude already knows (regex syntax, JSON structure).

Consolidate the model-routing guidance so it appears once instead of being restated across the routing table, decision guide, and parallel-pattern sections.

Dimension	Reasoning	Score
Conciseness	At ~505 lines the body is noticeably verbose: it inlines full report templates, a complete JSON state schema, regex patterns, and config blocks that Claude already understands, with some redundant routing/decision tables; this matches the anchor for several padded, unnecessary sections.	2 / 5
Actionability	Provides concrete, mostly copy-paste-ready guidance: explicit Task tool invocations with subagent_type/model/prompt, extraction regexes, a state.json schema, and a full report template, with only minor gaps (templated {{placeholder}} loop-control blocks).	4 / 5
Workflow Clarity	Clear sequence (Decompose -> Execute -> Verify -> Synthesize) with an explicit verification/cross-validation checkpoint and AUTO-mode loop control with promise tags; minor validation gaps keep it just below the top anchor.	4 / 5
Progressive Disclosure	No bundle files exist and all content is inlined into a single monolithic SKILL.md; large report templates, the state schema, regex library, and config reference that clearly belong in separate reference files are not split out or signaled.	2 / 5
	Total	12 / 20 Passed

Description

53%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.

The description states a clear purpose and is reasonably distinct, but it lacks an explicit 'Use when' trigger clause and leans on skill-specific jargon rather than natural user language. It names the domain and one core action without comprehensively enumerating what the skill does.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user needs comprehensive, multi-angle research or parallel investigation of a complex goal.'

Enumerate concrete actions in the description (decompose into stages, run parallel scientists, cross-validate findings, synthesize a report) rather than a single 'Orchestrate' verb.

Swap jargon ('scientist agents', 'AUTO mode') for natural user-facing terms and synonyms so the description triggers on phrases users actually say.

Dimension	Reasoning	Score
Specificity	Names the domain ('parallel scientist agents', 'comprehensive analysis') and one concrete action ('Orchestrate') plus the AUTO mode modifier, matching the anchor for 1-2 concrete actions that are not comprehensive; it does not enumerate the multiple specific actions (decompose, verify, synthesize) it actually supports.	3 / 5
Completeness	Provides a clear 'what' (orchestrate parallel scientist agents for comprehensive analysis with AUTO mode) but has no explicit 'Use when...' trigger clause, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Contains some relevant terms ('research goal', 'analysis', 'parallel') but leans on skill-specific jargon ('scientist agents', 'AUTO mode') rather than the natural phrases and synonyms a user would say, missing common variations.	3 / 5
Distinctiveness Conflict Risk	The 'parallel scientist agents' + 'AUTO mode' framing carves out a fairly distinct niche with only minor overlap risk against general research/analysis skills; it is mostly distinguishable though not maximally so.	4 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (512 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 missing	Warning

	Total	13 / 16 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Path: skills/sciomc/SKILL.md
Commit: 5aa678c

Reviewed: 12 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.