claude-coach

Personal coach that teaches users to become Claude power users. Use this skill the FIRST time a user asks to "learn Claude", "be a power user", "coach me", "teach me Claude tricks", "what can Claude do", "make me better at prompting", or any variation. After activation, also use it on EVERY subsequent turn to detect missed optimization opportunities (vague prompts, ignored capabilities, manual work Claude could automate) and surface a single power-user tip. Trigger generously — most users do not know what they do not know, so err on the side of coaching.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

85%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 well-structured, highly actionable coaching skill with clear sequencing and excellent reference splitting. Its main weakness is structural redundancy: the bottom Name/Description/Features/Usage block reiterates the frontmatter and the 'When to invoke' trigger list, adding tokens without new information.

Suggestions

Remove or collapse the trailing 'Name', 'Description', and 'Features' sections (lines 145-159) — they duplicate the YAML frontmatter and add no new information.

Merge the 'Usage' activation-trigger code block (lines 162-179) into the existing 'When to invoke this skill' section to avoid listing the same triggers twice.

Weave the three scripts into the relevant workflow steps (e.g. reference cheat_code_filter.py in Step 2, coach_tip_classifier.py in Rule 5) rather than only listing them at the end, so their use is signaled at the point of need.

Dimension	Reasoning	Score
Conciseness	The operational rules are tight with no padded explanation of concepts Claude already knows, but the trailing Name/Description/Features/Usage sections duplicate the frontmatter and re-list the same activation triggers already given in 'When to invoke this skill', which could be trimmed.	3 / 5
Actionability	Provides fully copy-paste-ready templates — the exact ⚡ tip format, the structured prompt-rating block, the glossary entry format — plus three concrete worked examples covering first activation, a coachable moment, and a non-coachable moment.	5 / 5
Workflow Clarity	First activation is an explicit three-step sequence (capture context → deliver glossary → save state) and the ongoing mode is rule-based with a do-trigger/don't-trigger checklist plus a referenced 5-gate decision tree acting as a validation checklist.	5 / 5
Progressive Disclosure	SKILL.md is a lean overview pointing to one-level-deep real references — references/cheat-codes.md and references/coaching-rules.md — each clearly signaled with read-when guidance, with three real scripts listed and described; navigation is easy.	5 / 5
	Total	18 / 20 Passed

Description

91%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 description that clearly states both capability and trigger conditions with natural, varied keywords. Third-person voice is maintained throughout. Minor overlap risk comes from the always-on passive coaching mode rather than the activation triggers.

Dimension	Reasoning	Score
Specificity	Names the coaching domain and several concrete actions — 'teaches users to become Claude power users', 'detect missed optimization opportunities (vague prompts, ignored capabilities, manual work Claude could automate)', 'surface a single power-user tip' — with minor gaps in coverage rather than a fully exhaustive list.	4 / 5
Completeness	Explicitly answers both what ('Personal coach that teaches users to become Claude power users... surface a single power-user tip') and when ('Use this skill the FIRST time a user asks...', 'on EVERY subsequent turn') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural phrases users actually say — 'learn Claude', 'be a power user', 'coach me', 'teach me Claude tricks', 'what can Claude do', 'make me better at prompting' — including multiple synonyms and variations.	5 / 5
Distinctiveness Conflict Risk	The 'learn Claude' / 'coach me' / 'power user' niche is clearly distinct from other skills, but the passive 'EVERY subsequent turn' mode and 'trigger generously — err on the side of coaching' guidance create minor overlap risk once active.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: engineering/claude-coach/skills/claude-coach/SKILL.md
Commit: 19392f7

Reviewed: ~5 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.