001-jeremy-taskwarrior-integration
Enforces complete Taskwarrior integration protocol for ALL coding tasks. Activates automatically when user mentions "taskwarrior", "task warrior", "tw", or discusses task management. Decomposes all coding work into properly tracked Taskwarrior tasks with full lifecycle: task add → task start → implementation → task done. Integrates with Timewarrior for automatic time tracking.
81
77%
Does it follow best practices?
Impact
81%
1.76xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./backups/skills-migration-20251108-070147/plugins/productivity/001-jeremy-taskwarrior-integration/skills/001-jeremy-taskwarrior-integration/SKILL.mdQuality
Discovery
100%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 is a strong skill description that clearly identifies its niche (Taskwarrior integration for coding tasks), lists concrete actions (task lifecycle management, Timewarrior integration), and provides explicit trigger terms. The description is concise yet comprehensive, covering both what the skill does and when it should activate.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: decomposes coding work into tasks, tracks full lifecycle (task add → task start → implementation → task done), integrates with Timewarrior for time tracking. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (decomposes coding work into Taskwarrior tasks with full lifecycle, integrates with Timewarrior) and 'when' (activates when user mentions 'taskwarrior', 'task warrior', 'tw', or discusses task management). Explicit trigger guidance is present. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'taskwarrior', 'task warrior', 'tw', 'task management'. These cover common variations including abbreviations and alternate spellings. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around Taskwarrior/Timewarrior integration specifically for coding tasks. The specific tool names and workflow (task add → task start → task done) make it very unlikely to conflict with generic task management or coding skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, concrete Taskwarrior commands with clear workflow sequencing and validation checkpoints. However, it is severely bloated—repeating the same lifecycle pattern numerous times, explaining concepts Claude already knows, and inlining reference material (tag taxonomies, priority matrices, troubleshooting) that should be in separate files. The content could be reduced by 60-70% without losing any actionable value.
Suggestions
Reduce the core SKILL.md to ~80 lines covering the 5-phase protocol once with one example, and move tag taxonomy, priority guidelines, special scenarios, troubleshooting, and additional examples into separate referenced files (e.g., EXAMPLES.md, REFERENCE.md).
Remove the 'What This Skill Does', 'When This Skill Activates', 'Summary', and 'Integration with Your Workflow' sections entirely—these restate frontmatter metadata or provide no actionable guidance.
Consolidate the lifecycle demonstration: show the add→start→implement→done cycle once with one good example instead of repeating it 8+ times across Examples, Expected User Workflow, Phase descriptions, etc.
Remove explanations of basic concepts like what priority:H means or what tags are—Claude understands these. Keep only the specific tag taxonomy as a reference file if needed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Massive redundancy: the same lifecycle (add → start → implement → done) is repeated 8+ times across sections. Explains obvious concepts like what priority levels mean, includes a 'What This Skill Does' section that restates the description, a 'When This Skill Activates' section that belongs in frontmatter, tag taxonomies Claude doesn't need memorized, and a summary that repeats everything. The 'Best Practices' DO/DON'T section largely restates the mandatory rules. The troubleshooting and integration sections add little actionable value. | 1 / 3 |
Actionability | All commands are concrete, executable bash commands with proper Taskwarrior syntax. Examples show exact command sequences with realistic arguments (project names, tags, dependencies). The quick reference table and multiple worked examples provide copy-paste ready commands for every scenario. | 3 / 3 |
Workflow Clarity | The 5-phase workflow is clearly sequenced with explicit validation checkpoints (verify task is active, check timew, completion checklist). Feedback loops are present for blockers (stop → annotate → modify +blocked), scope changes, and error recovery. The dependency chain ordering is explicit. The verification checklist before delivering code is a strong validation step. | 3 / 3 |
Progressive Disclosure | Monolithic wall of text with no bundle files or external references. Content that could easily be split (tag taxonomy, priority guidelines, troubleshooting, examples, quick reference) is all inline. At this length, the skill desperately needs to be split into a concise overview SKILL.md with references to supporting files like EXAMPLES.md, TAGS.md, and TROUBLESHOOTING.md. | 1 / 3 |
Total | 8 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (588 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Commit
13d35b8
- 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.