orchestrate
Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.
45
47%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/orchestrate/SKILL.mdQuality
Discovery
67%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 has a clear structure with both 'what' and 'when' clauses, which is good. However, the core capability is described in vague terms ('wire together for complex features') without listing specific concrete actions, and the trigger terms are generic enough to risk overlap with other development-oriented skills. The description would benefit from more specific actions and more distinctive trigger language.
Suggestions
Add specific concrete actions such as 'define multi-step orchestration workflows, chain agent calls, configure skill dependencies' instead of the vague 'wire together for complex features.'
Include more distinctive trigger terms that users would naturally say, such as 'orchestrate,' 'multi-step workflow,' 'chain agents,' 'compose skills,' or 'pipeline' to reduce conflict risk with general development skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names some domain concepts ('Commands, Agents, and Skills') and mentions 'research, planning, and implementation phases,' but the core action 'Wire...together for complex features' is vague and doesn't list concrete actions like 'create orchestration configs' or 'define agent pipelines.' | 2 / 3 |
Completeness | Explicitly answers both 'what' ('Wire Commands, Agents, and Skills together for complex features') and 'when' ('Use when building features that need research, planning, and implementation phases'), with a clear 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'Commands,' 'Agents,' 'Skills,' 'research,' 'planning,' and 'implementation,' but these are fairly generic and could overlap with many contexts. Missing natural user phrases like 'orchestrate,' 'multi-step workflow,' 'pipeline,' or 'compose agents.' | 2 / 3 |
Distinctiveness Conflict Risk | 'Complex features' and 'research, planning, and implementation phases' are broad enough to overlap with many development-related skills. While 'Wire Commands, Agents, and Skills together' provides some specificity to an orchestration niche, the trigger terms like 'building features' could easily conflict with general coding or project management skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable high-level framework for multi-phase feature development but fails on actionability — it reads more like a conceptual overview than an executable guide. Key agents, commands, and validation mechanisms are referenced by name but never concretely defined or demonstrated. The lack of any supporting bundle files or references makes the numerous mentions of agents, hooks, and workflows unresolvable.
Suggestions
Add concrete, executable examples showing how to actually invoke each agent (e.g., the exact command syntax for delegating to the scout agent or running the reviewer agent).
Define what 'confidence score' means concretely and how to compute/check it — provide a specific threshold check mechanism rather than just saying 'below 70'.
Create and reference supporting files (e.g., AGENTS.md, HOOKS.md) that define the agents, quality gates, self-correction loops, and session handoff mentioned in the content.
Add a complete worked example showing one feature going through all four phases with actual commands and outputs at each step.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary sections like 'When to Use This' and 'When NOT to Use This' that are somewhat obvious heuristics Claude could infer. The agent selection table is useful but the 'Why' column adds marginal value. | 2 / 3 |
Actionability | No executable code, no concrete commands, no specific examples of how to invoke agents or commands. Everything is described abstractly — 'delegate to the orchestrator agent,' 'run the reviewer agent' — without showing actual syntax, command invocations, or configuration. There's no way to copy-paste and execute anything. | 1 / 3 |
Workflow Clarity | Steps are listed in a clear sequence with some validation gates mentioned (confidence score, approval, quality gates every 5 edits), but the validation steps are vague — no concrete commands for checking confidence, no specific quality gate implementation, and the feedback loop for failures is not defined. | 2 / 3 |
Progressive Disclosure | No bundle files are provided, yet the skill references multiple agents (scout, orchestrator, reviewer, debugger) and concepts (pro-workflow, self-correction loop, hooks, session handoff) without any links to supporting documentation. This is a monolithic file that leaves the reader with no way to discover the referenced components. | 1 / 3 |
Total | 6 / 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
- rohitg00/pro-workflow
- Commit
9fc35f5
- 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.