senior-project-manager
Converts specs to tasks, remembers previous projects\n - Focused on realistic scope, no background processes, exact spec requirements
33
17%
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 ./pm-senior-project-manager/skills/SKILL.mdQuality
Discovery
0%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 is too vague and abstract to be useful for skill selection. It lacks concrete actions, natural trigger terms, explicit 'when to use' guidance, and distinctive identifiers. The second line reads more like internal design notes than a functional description.
Suggestions
Specify what kind of specs (e.g., 'product requirements documents', 'feature specifications', 'PRDs') and what kind of tasks (e.g., 'GitHub issues', 'development tasks with estimates', 'actionable work items') to improve specificity.
Add an explicit 'Use when...' clause with natural trigger terms like 'break down requirements', 'create tasks from spec', 'plan project tasks', 'convert PRD to tickets'.
Remove internal constraint language ('no background processes', 'exact spec requirements') and replace with user-facing capability descriptions that distinguish this skill from generic project management tools.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'converts specs to tasks' and 'remembers previous projects' without specifying concrete actions. What kind of specs? What kind of tasks? 'Realistic scope' and 'no background processes' are abstract constraints, not concrete capabilities. | 1 / 3 |
Completeness | There is a weak 'what' (converts specs to tasks) but no explicit 'when' clause or trigger guidance. The second line describes constraints/philosophy rather than when to use the skill. Missing a 'Use when...' clause caps this at 2, but the 'what' is also very weak. | 1 / 3 |
Trigger Term Quality | The terms 'specs', 'tasks', and 'previous projects' are overly generic and not natural trigger terms a user would say. Missing domain-specific keywords like 'project planning', 'task breakdown', 'requirements', 'user stories', or file format references. | 1 / 3 |
Distinctiveness Conflict Risk | The description is extremely generic — 'converts specs to tasks' could overlap with any project management, task tracking, or planning skill. There are no distinct triggers or domain-specific identifiers to differentiate it from similar skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is overly verbose with significant token waste on personality framing, motivational language, and concepts Claude already understands (be specific, stay realistic, think developer-first). The task list template provides moderate actionability but the overall workflow lacks validation checkpoints. The content would benefit greatly from trimming the identity/personality sections and adding concrete validation steps.
Suggestions
Remove the personality/identity section, communication style, success metrics, and learning sections entirely — these waste tokens on things Claude already knows how to do
Add explicit validation steps: e.g., 'After generating task list, verify each task maps to a specific spec requirement — flag any tasks without a spec reference'
Move the task list template to a separate file (e.g., TASK_TEMPLATE.md) and reference it from the skill to improve progressive disclosure
Replace vague guidance like 'Quote EXACT requirements' with a concrete example showing a spec excerpt mapped to a generated task
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Heavily padded with personality/identity framing Claude doesn't need ('Your Identity & Memory', 'Communication Style', 'Success Metrics', 'Learning & Improvement'). Explains obvious concepts like 'be specific' and 'stay realistic'. The emoji headers, motivational language, and meta-commentary about learning from experience are all wasted tokens. | 1 / 3 |
Actionability | The task list template is somewhat concrete and provides a usable format with acceptance criteria and file references. However, the core workflow (read spec → create tasks) lacks executable commands or specific code examples. The template is more of a skeleton than a fully actionable guide. | 2 / 3 |
Workflow Clarity | The three core responsibilities (Specification Analysis → Task List Creation → Technical Stack Requirements) outline a sequence, but there are no validation checkpoints or feedback loops. No step to verify the task list against the spec, no review cycle, and no error recovery guidance for when specs are ambiguous. | 2 / 3 |
Progressive Disclosure | References `ai/agents/pm.md` for detailed instructions and `ai/memory-bank/site-setup.md` for specs, which is good. However, the SKILL.md itself is monolithic with sections like Success Metrics, Learning & Improvement, and Communication Style that could be omitted or moved elsewhere. The inline task template is quite long and could be a separate reference file. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- OpenRoster-ai/awesome-openroster
- Commit
09aef5d
- 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.