01-meta-chain-of-skills-150
[01] META. Сканирует доступные skills, создает план выполнения и идет шаг за шагом с подтверждением каждого этапа. Triggers on complex tasks, multi-step work, or when structured execution is needed.
52
33%
Does it follow best practices?
Impact
72%
6.00xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/data/01-meta-chain-of-skills-150/SKILL.mdQuality
Discovery
27%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This meta-orchestration skill description suffers from overly generic trigger conditions that would conflict with nearly any other skill in a large skill library. While it communicates the general concept of planning and step-by-step execution, the trigger terms are too vague to enable reliable skill selection. The mixed language (Russian and English) may also cause inconsistency in matching.
Suggestions
Replace vague triggers like 'complex tasks' and 'multi-step work' with specific natural-language phrases users would say, such as 'plan this out', 'break this into steps', 'I need to do multiple things', 'coordinate across skills', or 'help me organize a workflow'.
Add explicit exclusion guidance to reduce conflict risk, e.g., 'Do NOT use for single-skill tasks or simple requests. Use only when the task requires coordinating 3+ distinct steps or invoking multiple other skills.'
Standardize the language — either fully Russian or fully English — and add concrete examples of when this meta-skill should activate versus when a domain-specific skill should be chosen directly.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names some actions ('сканирует доступные skills', 'создает план выполнения', 'идет шаг за шагом с подтверждением'), but these are process-level descriptions rather than concrete domain-specific actions. The capabilities described are meta-orchestration rather than specific tasks. | 2 / 3 |
Completeness | The 'what' is partially addressed (scans skills, creates plan, step-by-step with confirmation). The 'when' is present via 'Triggers on...' but the triggers are so vague ('complex tasks', 'multi-step work') that they don't provide meaningful selection guidance. The 'when' clause is too broad to be useful. | 2 / 3 |
Trigger Term Quality | Trigger terms are vague and generic: 'complex tasks', 'multi-step work', 'structured execution' are not natural phrases users would say. Users are unlikely to request 'structured execution' — they'd more likely say things like 'plan this out', 'break this down', or 'help me organize this project'. | 1 / 3 |
Distinctiveness Conflict Risk | Extremely high conflict risk. 'Complex tasks' and 'multi-step work' could apply to virtually any non-trivial user request. Almost any skill could be considered to handle 'complex tasks', making this description likely to trigger inappropriately across many scenarios. | 1 / 3 |
Total | 6 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill defines a clear orchestration protocol with good workflow structure and explicit confirmation gates, but is severely undermined by extreme verbosity and repetition. The same status block template appears multiple times, route templates and output formats could be externalized, and the content could be cut by 60%+ while preserving all actionable information. The core mechanism is more of a conversational UX pattern than a technically executable skill.
Suggestions
Cut content by at least 50%: remove duplicate status block examples (show it once, reference it), consolidate the 'Three Steps' and 'Execution Protocol' sections which largely repeat each other, and trim the lengthy end-to-end example.
Extract route templates, output format specifications, and the available skills table into separate reference files (e.g., ROUTES.md, FORMATS.md) and link to them from the main skill.
Remove explanatory framing like 'What This Skill Does' and the before/after comparison example — Claude doesn't need to be sold on why structured execution is better.
Add concrete guidance on HOW to actually invoke/chain skills (e.g., does Claude read the skill file content? Is there a specific mechanism?) rather than just listing skill names and display formats.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines with massive repetition. The same execution status block is shown 4+ times in slightly different contexts. The output format templates, route templates, and examples all repeat information already conveyed in the protocol steps. Much of this could be condensed to under 100 lines without losing any actionable content. | 1 / 3 |
Actionability | Provides concrete bash commands for scanning skills and clear output format templates, but the core 'execution' is essentially 'run the other skill' with no concrete guidance on HOW to chain skills programmatically. The skill is more of a display/interaction protocol than executable logic. The route templates are useful but are essentially just ordered lists of skill names. | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced with explicit confirmation checkpoints at every step, a failure/recovery table, user commands for flow control (pause, reroute, skip, back, stop), and mandatory status blocks. The feedback loop (rebuild on request, retry or skip on failure) is well-defined. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. The route templates, full output format specifications, the available skills table, and the lengthy examples could all be split into separate reference files. Everything is inlined, making the skill extremely long and hard to navigate quickly. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- majiayu000/claude-skill-registry
- Commit
632759f
- Reviewed
Table of Contents
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.