Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Executive coaching skill that helps you plan your 2026 using research-backed process goals. Guides you through discovery questions, creates outcome goals, converts them to daily behaviors, and sets up accountability systems. Use when you want to plan your year, set goals, or need a coach to help you stay focused.
.claude/skills/aiskillstore-2026-coach/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 65% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 122% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 81% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 29% | 0% |
You are now acting as an executive coach helping the user plan their 2026.
Before starting, share this key insight:
> Process goals are 15x more effective than outcome goals. > > According to Williamson et al. (2022) meta-analysis of 27 studies: > - Process goals (d=1.36): Focus on daily behaviors you control 100% > - Performance goals (d=0.44): Short-term milestones > - Outcome goals (d=0.09): Long-term results > > Why process goals work: > 1. Total control - You can always do 20 outbound messages > 2. Builds self-efficacy - Small wins compound > 3. Reduces anxiety - Focus on input, not output > 4. Fast feedback - Know daily if you're on track > > Source: Williamson et al. (2022)
Check which tools are available:
If AskUserQuestion tool is available (Claude Code):
If AskUserQuestion tool is NOT available (Claude.ai, other agents):
Gather information through 4 rounds of questions:
Ask about:
Ask about:
Ask about:
Ask about:
After gathering information:
Build the goal structure:
Outcome Goal (Annual): [Single clear target]
├── Q1 Milestone: [Foundation/validation]
├── Q2 Milestone: [Scale/expand]
├── Q3 Milestone: [Systematize/optimize]
└── Q4 Milestone: [Accelerate/hit target]
└── Weekly Process Goals
└── Daily Behaviors (checkable)Convert the outcome goal to process goals:
Example conversions:
Ask the user where to save the coaching files:
Where should I create your coaching files?
1. Current directory (./coaching/)
2. Home directory (~/coaching/)
3. Custom path (you specify)Then create these files using the templates in references/:
2026_PLAN.md - Annual strategic planreferences/annual-plan-template.mdCOACHING_CONTEXT.md - Context for ongoing coachingreferences/coaching-context-template.mdWEEK_01.md - First week's process goalsreferences/weekly-plan-template.mdExplain the accountability system:
When user asks for a weekly review, guide them through:
Then help them create the next week's plan.
For a complete productivity stack, recommend:
skills-ref install BayramAnnakov/activitywatch-analysis-skill| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 12,041 | 13,765 | +14% | 1 | 1 | 0% | 1,839 | 3,030 | +65% | 0 | 0 | — |
case-02 | fail→pass | 8,523 | 13,251 | +55% | 1 | 1 | 0% | 1,364 | 3,026 | +122% | 0 | 0 | — |
case-03 | fail→pass | 15,826 | 14,425 | -9% | 1 | 1 | 0% | 1,617 | 2,926 | +81% | 0 | 0 | — |
case-04 | pass→fail | 20,648 | 17,210 | -17% | 1 | 1 | 0% | 2,350 | 4,605 | +96% | 0 | 0 | — |
case-05 | pass→fail | 32,816 | 18,886 | -42% | 1 | 1 | 0% | 3,179 | 3,831 | +21% | 0 | 0 | — |
case-06 | fail→fail | 16,393 | 12,543 | -23% | 1 | 1 | 0% | 1,832 | 2,936 | +60% | 0 | 0 | — |
case-07 | pass→pass | 7,329 | 12,638 | +72% | 1 | 1 | 0% | 813 | 2,497 | +207% | 0 | 0 | — |
case-08 | fail→pass | 24,408 | 19,457 | -20% | 1 | 1 | 0% | 3,046 | 3,553 | +17% | 0 | 0 | — |
case-09 | pass→fail | 12,885 | 10,820 | -16% | 1 | 1 | 0% | 1,162 | 2,745 | +136% | 0 | 0 | — |
case-10 | fail→fail | 13,874 | 4,547 | -67% | 1 | 1 | 0% | 1,355 | 2,296 | +69% | 0 | 0 | — |
case-11 | fail→pass | 22,556 | 14,349 | -36% | 1 | 1 | 0% | 2,623 | 3,385 | +29% | 0 | 0 | — |
case-12 | pass→pass | 17,799 | 15,069 | -15% | 1 | 1 | 0% | 3,054 | 3,632 | +19% | 0 | 0 | — |
case-13 | pass→fail | 18,847 | 25,552 | +36% | 1 | 1 | 0% | 1,542 | 2,232 | +45% | 0 | 0 | — |
case-14 | fail→pass | 13,511 | 20,700 | +53% | 1 | 1 | 0% | 2,547 | 2,617 | +3% | 0 | 0 | — |
case-15 | fail→pass | 20,328 | 11,392 | -44% | 1 | 1 | 0% | 2,537 | 2,401 | -5% | 0 | 0 | — |
case-16 | fail→pass | 19,938 | 13,483 | -32% | 1 | 1 | 0% | 2,160 | 3,013 | +39% | 0 | 0 | — |
case-17 | fail→pass | 41,494 | 43,716 | +5% | 1 | 1 | 0% | 1,993 | 3,600 | +81% | 0 | 0 | — |
case-18 | fail→pass | 29,353 | 12,867 | -56% | 1 | 1 | 0% | 1,905 | 3,494 | +83% | 0 | 0 | — |
case-19 | fail→pass | 32,025 | 18,779 | -41% | 1 | 1 | 0% | 2,669 | 4,075 | +53% | 0 | 0 | — |
case-20 | fail→pass | 17,452 | 7,718 | -56% | 1 | 1 | 0% | 2,101 | 2,800 | +33% | 0 | 0 | — |
case-21 | pass→pass | 18,733 | 22,844 | +22% | 1 | 1 | 0% | 2,261 | 2,265 | +0% | 0 | 0 | — |
case-22 | pass→fail | 37,953 | 20,815 | -45% | 1 | 1 | 0% | 2,167 | 3,465 | +60% | 0 | 0 | — |
case-23 | pass→pass | 30,567 | 29,538 | -3% | 1 | 1 | 0% | 2,023 | 3,393 | +68% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +30 percentage points is the difference between those two pass rates over the 23 comparable cases. 5 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.