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 generic trigger terms that would cause it to conflict with almost any other skill. The 'what' is somewhat clear (scan skills, plan, execute step-by-step), but the 'when' criteria are too broad to be useful for skill selection. The mixed language (Russian + English) may also cause inconsistency in matching.
Suggestions
Replace vague triggers like 'complex tasks' and 'multi-step work' with specific, natural trigger phrases such as 'Use when the user explicitly asks to plan a workflow, orchestrate multiple skills, or requests step-by-step execution across different tools'.
Add concrete examples of when this skill should NOT be triggered to reduce conflict risk, e.g., 'Do not use for single-skill tasks or straightforward requests'.
Standardize the language — either fully Russian or fully English — and add more specific capability descriptions like 'coordinates execution across multiple skills, manages dependencies between steps, and provides progress checkpoints'.
| 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 so vague ('complex tasks', 'multi-step work') that they don't provide meaningful guidance for when to select this skill over others. | 2 / 3 |
Trigger Term Quality | Trigger terms like 'complex tasks', 'multi-step work', and 'structured execution' are overly generic and abstract. Users rarely say 'I need structured execution' — these are not natural keywords a user would use to invoke this skill. | 1 / 3 |
Distinctiveness Conflict Risk | Extremely high conflict risk — 'complex tasks' and 'multi-step work' could match virtually any non-trivial user request. This meta-skill would compete with nearly every other skill in a large skill library. | 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 explicit confirmation gates, user commands, and failure recovery, but is severely undermined by extreme verbosity and redundancy. The same workflow is described three times in different formats, output templates are repeated, and the entire content could be reduced by 60%+ without losing information. The lack of any progressive disclosure into supporting files compounds the bloat problem.
Suggestions
Eliminate redundancy by merging 'What This Skill Does', 'Three Steps', and 'Execution Protocol' into a single concise workflow section — currently the same process is described three times.
Move 'Common Route Templates', 'Available Skills for Routing', and detailed output format examples into separate reference files (e.g., ROUTES.md, FORMATS.md) and link to them from the main skill.
Remove explanatory content Claude doesn't need — e.g., the '❌ Without Chain-of-Skills' comparison, the 'Relationship to Other Skills' section, and verbose format templates that could be condensed to a single example.
Consolidate the multiple output format sections (Plan Presentation, Step Completion, Execution Complete, End of Each Message) into one compact reference with a single annotated example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Massive redundancy: the workflow is described three times (What This Skill Does, Three Steps, Execution Protocol). Output format templates are shown multiple times with near-identical status blocks. The 'Available Skills for Routing' table and 'Common Route Templates' add significant bulk. Much of this (how to list directories, what a progress bar looks like) is unnecessary for Claude. | 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' without specifying how to actually invoke/chain skills programmatically. The skill is more of a display protocol than executable guidance — it tells Claude what to print rather than how to technically orchestrate skill execution. | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced with explicit confirmation gates at each step, user commands for control flow (Pause/Reroute/Skip/Back/Stop), a failure modes & recovery table, and mandatory status blocks. The feedback loop (rebuild on request, retry or skip on failure) is well-defined. | 3 / 3 |
Progressive Disclosure | Everything is crammed into a single monolithic file with no references to external files for detailed content. The route templates, output formats, available skills table, examples, and operational rules could all be split into separate reference files. No bundle files exist to offload this content, resulting in a wall of text. | 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
ac1dcdc
- 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.