track-management
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.
Overall
score
78%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 97%
↑ 2.42xAgent success when using this skill
Validation for skill structure
Evaluation results
100%
93%Search Feature Track Setup
New track creation
Track ID format
50%
100%
spec.md FR sections
0%
100%
spec.md NFR sections
0%
100%
spec.md scope sections
14%
100%
spec.md risks table
0%
100%
spec.md dependencies
0%
100%
plan.md header fields
0%
100%
plan.md verification tasks
0%
100%
plan.md checkpoints table
0%
100%
tracks.md linked entry
25%
100%
metadata.json task counts
0%
100%
metadata.json phases object
0%
100%
Track index.md
0%
100%
Without context: $2.0135 · 7m 8s · 50 turns · 42 in / 17,265 out tokens
With context: $0.7541 · 2m 46s · 28 turns · 76 in / 9,432 out tokens
100%
38%Document In-Flight Implementation State
Status markers and lifecycle
Completed tasks use [x]
100%
100%
Completed tasks include SHA
69%
100%
In-progress task uses [~]
0%
100%
Blocked task uses [!]
0%
100%
Blocked task includes reason
100%
100%
Skipped task uses [-]
0%
100%
Pending tasks use [ ]
100%
100%
Phase 1 checkpoint SHA recorded
60%
100%
Phase 1 tasks all closed
100%
100%
Phased plan structure
100%
100%
Without context: $0.2407 · 54s · 14 turns · 11 in / 2,925 out tokens
With context: $0.2597 · 54s · 11 turns · 310 in / 2,674 out tokens
90%
38%Auth Module Migration Track
Plan quality and track sizing
Refactor track type
0%
100%
Phase count
100%
100%
Refactor preparation phase
100%
100%
Verification per phase
33%
100%
Total task count
0%
100%
Tasks per phase
0%
0%
Atomic tasks
80%
100%
Testable acceptance criteria
100%
100%
Dependencies with type
0%
100%
Spec open questions section
100%
100%
Without context: $0.4006 · 2m 20s · 15 turns · 56 in / 7,395 out tokens
With context: $0.8908 · 3m 24s · 31 turns · 31 in / 11,226 out tokens
- Evaluated
- Agent
- Claude Code
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.