do-competitively

Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/sadd/skills/do-competitively/SKILL.md

Quality

Content

63%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 skill body is a thorough, actionable orchestration spec with strong workflow sequencing and concrete templates, but it is over-long with redundant warnings and worked examples and inlines content that could live in separate reference files. Trimming repetition and extracting templates/examples would lift conciseness and progressive disclosure.

Suggestions

Cut repeated CRITICAL warnings and consolidate the three worked examples into one, removing the redundancy that inflates token count without adding clarity.

Move the per-phase prompt templates and full examples into reference files (e.g. references/prompts.md, references/examples.md) and link to them one level deep from SKILL.md.

Replace verbose process narration (e.g. 'Let's approach this systematically') inside templates with leaner instruction sets that assume Claude's competence.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable and well-organized, but it includes padded repetition (the same CRITICAL warnings restated, repeated dispatch examples, three near-identical worked examples) and over-explains concepts like 'diversity through independence' that could be trimmed.	3 / 5
Actionability	It provides concrete, copy-paste prompt templates, exact dispatch instructions (4 Task calls in one message, subagent types, model: opus), and concrete file-naming conventions; only minor gaps (e.g. exact orchestrator parsing code) keep it from a 5.	4 / 5
Workflow Clarity	Phases 1, 2, 2.5, and 3 are clearly sequenced with explicit validation/checkpoint logic (wait for all agents, parse headers, score thresholds, redesign loop); the few missing validation gates are for non-destructive evaluation, so this sits just above the midpoint rather than at the cap.	4 / 5
Progressive Disclosure	There is no bundle directory and no external references — the entire specification is inlined into one large SKILL.md, so content that could be split out (prompt templates, examples) is inline; per the simple-skill guidance the inline organization is reasonable but not optimally decomposed.	3 / 5
	Total	14 / 20 Passed

Description

38%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 conveys a clear, concrete capability but omits any 'Use when...' trigger guidance and leans on technical jargon rather than natural user language, which caps completeness and trigger-term quality. Adding an explicit when-to-use clause with conversational trigger phrases would substantially improve it.

Suggestions

Add an explicit 'Use when...' clause naming the situations where this skill should be invoked (e.g. high-stakes tasks where quality matters more than speed).

Replace or supplement jargon ('meta-judge evaluation specification', 'evidence-based synthesis') with natural trigger phrases a user would actually say.

Sharpen distinctiveness by contrasting with simpler approaches, e.g. note it is for tasks where competitive multi-agent generation is justified over a single pass.

Dimension	Reasoning	Score
Specificity	Names the domain (competitive multi-agent generation) and several concrete actions (meta-judge evaluation specification, multi-judge evaluation, evidence-based synthesis), with only minor coverage gaps versus the score-5 anchor.	4 / 5
Completeness	It states a clear 'what' but has no 'when'/'Use when...' clause at all, and the rubric explicitly caps completeness at 3 for a missing trigger clause; combined with no concrete use scenario this sits below the midpoint.	2 / 5
Trigger Term Quality	The terms are technical jargon ('meta-judge evaluation specification', 'evidence-based synthesis') rather than natural phrases a user would say; it lacks the common conversational keywords users actually utter when they need this skill.	2 / 5
Distinctiveness Conflict Risk	The phrase is fairly specific to a competitive-generation niche, but 'execute tasks' and broad evaluation/synthesis framing could still overlap with general orchestration or code-generation skills.	3 / 5
	Total	11 / 20 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 (780 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: NeoLabHQ/context-engineering-kit
Path: plugins/sadd/skills/do-competitively/SKILL.md
Commit: 8539779

Reviewed: 5 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.