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 description attempts to define a meta-orchestration skill but suffers from overly abstract trigger conditions that would match nearly any complex request. The mixed Russian/English language adds confusion, and the trigger terms ('complex tasks', 'multi-step work', 'structured execution') are too generic to reliably distinguish this skill from others. The core concept of scanning available skills and creating execution plans is somewhat specific, but the when-to-use guidance is far too broad.
Suggestions
Replace vague triggers like 'complex tasks' and 'multi-step work' with specific natural-language phrases users would say, such as 'make a plan', 'break this into steps', 'coordinate multiple skills', or 'I need help organizing this project'.
Add explicit boundaries for when NOT to use this skill (e.g., 'Do not use for single-step tasks or when a specific skill clearly matches the request') to reduce conflict risk with other skills.
Standardize the language — either fully Russian or fully English — and add concrete examples of the types of multi-skill workflows this orchestrates (e.g., 'when a task requires combining code generation, file processing, and testing').
| 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. It describes a meta-workflow rather than specific capabilities. | 2 / 3 |
Completeness | The 'what' is partially addressed (scans skills, creates plan, step-by-step execution), and there is a 'Triggers on...' clause, but the trigger conditions are too vague ('complex tasks', 'multi-step work') to serve as explicit, actionable guidance for when to select this skill. | 2 / 3 |
Trigger Term Quality | Trigger terms are vague and abstract: '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 step by step'. | 1 / 3 |
Distinctiveness Conflict Risk | Extremely high conflict risk — 'complex tasks' and 'multi-step work' could describe virtually any non-trivial user request. Almost any skill could be triggered by these terms, making this description very likely to conflict with other skills. | 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 has excellent workflow clarity with clear step sequencing, user confirmation gates, and failure recovery paths. However, it is extremely verbose — repeating the same status block format multiple times, including lengthy route templates inline, and providing extensive output formatting that could be inferred or referenced externally. The actual mechanism for executing individual skills is left vague, reducing actionability despite the concrete scanning commands.
Suggestions
Reduce content by at least 50%: remove duplicate status block examples (show it once), and move route templates and the available skills table to a separate reference file like ROUTES.md
Clarify the actual mechanism for 'executing a skill' — does Claude read the skill file and follow its instructions? This core action is never explicitly defined
Move the detailed output format templates (plan presentation, step completion, execution complete) to a separate FORMATS.md file and reference it with a one-line link
Remove the '❌ Without Chain-of-Skills' anti-example — it explains something Claude already understands and wastes tokens
| 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 (what a plan looks like, how to show progress) is presentation formatting that Claude can infer from a brief description. | 1 / 3 |
Actionability | Provides concrete bash commands for scanning skills and clear output templates, but the core 'execution' of each skill is vague — it just says '[... skill execution ...]'. The actual mechanism for invoking/running a skill is never specified. The skill is more of a display protocol than an executable workflow. | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced (SCAN → BUILD → EXECUTE) with explicit confirmation checkpoints at each step, user commands for rerouting/pausing/stopping, and a failure modes & recovery table. Validation is built into the confirmation-required protocol. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. The 'Common Route Templates' section, 'Available Skills for Routing' table, and extensive output format templates could all be split into separate reference files. Everything is inlined, making the skill very long and hard to navigate. | 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
d156cd1
- 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.