project-planner
Detects stale project plans and suggests session commands. Triggers on: sync plan, update plan, check status, plan is stale, track progress, project planning.
Install with Tessl CLI
npx tessl i github:NeverSight/skills_feed --skill project-planner86
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/skillValidation for skill structure
Evaluation results
84%
7%Project Planning Health Check
Stale plan detection and command suggestion
Stale plan detected
100%
100%
3-day threshold applied
100%
100%
Relevant commit types cited
100%
100%
Correct command suggested
0%
100%
Plan not modified
100%
100%
docs/PLAN.md path referenced
100%
100%
/sync reads state
0%
0%
Commits since modification noted
100%
100%
No extraneous modifications
100%
0%
Reasoning provided
100%
100%
Without context: $0.1958 · 59s · 9 turns · 14 in / 2,867 out tokens
With context: $0.2035 · 48s · 12 turns · 15 in / 2,624 out tokens
100%
64%Project Onboarding Status Review
Missing plan detection and initial save suggestion
Missing plan identified
0%
100%
Correct command suggested
0%
100%
docs/PLAN.md path named
0%
100%
Plan file not created
100%
100%
/save described as write operation
0%
100%
Timing guidance provided
0%
100%
No incorrect commands
100%
100%
Skill only suggests
100%
100%
Single source of truth
20%
100%
No wrong plan location
0%
100%
Without context: $0.1449 · 52s · 8 turns · 13 in / 2,256 out tokens
With context: $0.3022 · 1m 10s · 19 turns · 271 in / 3,283 out tokens
100%
30%Mid-Sprint Planning Review
Uncommitted work detection and sync-status suggestion
Uncommitted changes detected
100%
100%
In Progress section flagged
100%
100%
Correct command suggested
0%
100%
Plan not modified
100%
100%
docs/PLAN.md path referenced
50%
100%
/sync described as read operation
0%
100%
Plan needs review conclusion
100%
100%
No incorrect commands
100%
100%
Only suggests
100%
100%
Without context: $0.1872 · 47s · 12 turns · 15 in / 2,464 out tokens
With context: $0.2034 · 47s · 13 turns · 48 in / 2,548 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.