planner
Create structured plans for multi-task projects that can be used by the task-orchestrator skill. Use when breaking down complex work into parallel and sequential tasks with dependencies.
70
66%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/planner/SKILL.mdQuality
Discovery
75%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 is well-structured with explicit 'what' and 'when' clauses, and it establishes a clear niche by referencing the task-orchestrator skill. Its main weakness is moderate specificity—it could list more concrete actions—and trigger term coverage could be broader to capture more natural user phrasings like 'workflow', 'subtasks', or 'decompose'.
Suggestions
Add more concrete actions such as 'define task dependencies, identify parallelizable work, sequence steps, and generate execution plans'.
Expand trigger terms to include natural user phrases like 'workflow', 'subtasks', 'decompose', 'project breakdown', or 'task graph'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (multi-task project planning) and a key action (create structured plans), but doesn't list multiple concrete actions. It mentions 'parallel and sequential tasks with dependencies' which adds some specificity, but overall it's not as comprehensive as listing distinct operations. | 2 / 3 |
Completeness | Clearly answers both 'what' (create structured plans for multi-task projects usable by task-orchestrator) and 'when' (when breaking down complex work into parallel and sequential tasks with dependencies). The 'Use when' clause is explicit. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'plans', 'multi-task projects', 'dependencies', 'parallel', 'sequential', and 'breaking down complex work'. However, it misses common user-facing terms like 'project plan', 'task breakdown', 'workflow', 'orchestration', 'decompose', or 'subtasks' that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche by specifying it creates plans specifically for the task-orchestrator skill, with focus on parallel/sequential tasks and dependencies. This is distinct enough to avoid conflicts with general planning or project management skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a reasonably well-structured planning skill that provides a clear template and good safety boundaries. Its main weaknesses are that it delegates core actionability to an external prompt file without summarizing enough of the key logic inline, and the inline plan template is verbose enough that it could benefit from being a separate referenced file. The workflow phases lack explicit validation checkpoints between steps.
Suggestions
Summarize the key decision logic from prompts/planner.md inline so the skill is actionable without loading the external file, or at minimum describe what each phase produces as output.
Add explicit validation checkpoints between workflow phases (e.g., 'Phase 2 output must include at least one sprint with demo criteria before proceeding to Phase 3 review').
Move the full plan template to a separate referenced file (e.g., templates/plan-template.md) and keep only a condensed example inline to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary content like the 'Bad vs Good' examples that are somewhat obvious to Claude, and the plan template is quite lengthy inline content that could be referenced externally. The principles section explains concepts Claude likely already understands (atomicity, testability). | 2 / 3 |
Actionability | The skill delegates most actual guidance to 'prompts/planner.md' rather than providing executable steps directly. The plan template is concrete and useful, and the hand-off commands are specific, but the core workflow is essentially 'load the full planner prompt and follow its process' which defers actionability to another file. | 2 / 3 |
Workflow Clarity | The 5-phase workflow is clearly listed but lacks validation checkpoints between phases. There's no explicit guidance on what to do if Phase 0 clarification reveals the project is too vague, or how to validate the plan before hand-off. The safety boundaries section partially compensates but doesn't integrate into the workflow sequence. | 2 / 3 |
Progressive Disclosure | Good structure with a quick start overview, key principles, a template, and clear references to external files (prompts/planner.md, prompts/parallel-task.md). Content is well-organized with clear sections and the references are one level deep and clearly signaled. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- jdrhyne/agent-skills
- Commit
6768672
- 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.