Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

/cs:execute — 90-Day Execution Plan · alirezarezvani | DecimalAI

alirezarezvani/execute

SkillScore86Maintained

/cs:execute <decision> — Generate a 90-day execution plan with weekly milestones, DRIs, and check-in cadence from an approved decision. Use when a logged decision needs to become an operating plan — e.g. turning an approved market-entry call into weekly milestones with DRIs.

productivityby alirezarezvani

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Project Management pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/alirezarezvani-execute/SKILL.md

decimalai skills pull alirezarezvani-execute --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/alirezarezvani-execute/SKILL.md https://app.decimal.ai/s/alirezarezvani-execute/SKILL.md

Raw file: /s/alirezarezvani-execute/SKILL.md ↗ · machine-readable summary at /s/alirezarezvani-execute.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 26d ago

Yes — +59% lift · at higher cost+32% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-35%	0%
case-02	✗→✓	▲ Improved	25%	0%
case-03	✗→✓	▲ Improved	-18%	0%
case-04	✗→✓	▲ Improved	119%	0%
case-08	✗→✓	▲ Improved	52%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

alirezarezvani / claude-skills

.gemini/skills/execute/SKILL.md

View on GitHub ↗

License MITImported 9/1/2026Version v2

Skill contents

SKILL.md

/cs:execute — 90-Day Execution Plan

Command: /cs:execute <decision-path>

Turns an approved decision into a 90-day plan with weekly milestones, named DRIs, and a check-in cadence. Where most decisions die: between "we decided" and "what's next Monday?"

Pipeline Position

/cs:office-hours  →  /cs:brief  →  /cs:boardroom  →  /cs:decide  →  /cs:execute  →  /cs:post-mortem
                                                                       ↑ you are here

Input

An approved decision record (output of /cs:decide).

Output Plan Format

Saved to ~/.claude/execution/YYYY-MM-DD-<slug>.md:

markdown
# Execution Plan: <decision title>
**Decision:** <link to /cs:decide record>
**Owner (Sponsor):** <founder or exec>
**Start:** YYYY-MM-DD
**Checkpoint:** YYYY-MM-DD (90d)

## Outcome (binding)
[Copied from decision: success + kill criteria]

## Workstreams
| Workstream | DRI | Success Metric | Status |
|---|---|---|---|
| <e.g., Pricing rollout> | <name> | <metric, threshold> | Not started |
| <e.g., Comms> | <name> | <metric> | Not started |
| <e.g., Eng changes> | <name> | <metric> | Not started |

## Weekly Milestones
| Week | Milestone | DRI | Definition of Done |
|---|---|---|---|
| 1 | <e.g., positioning locked> | <name> | <observable outcome> |
| 2 | <e.g., draft launched> | <name> | <observable> |
| 3 | ... | | |
| 12 | <e.g., checkpoint review> | <name> | <observable> |

## Cadence
- **Weekly:** Owner reviews status (15 min)
- **Bi-weekly:** Cross-functional sync (30 min)
- **Day 30 / 60 / 90:** Checkpoint with cs-chief-of-staff

## Dependencies
- Internal: <list>
- External: <vendors, regulators, customers>

## Risk Register
| Risk | Likelihood | Impact | Owner | Mitigation |
|---|---|---|---|---|
| <e.g., delayed legal review> | M | H | <name> | <plan> |

## Kill Criteria Watch
[Copied from decision; reviewed at every checkpoint]
- <metric, threshold, action>

Workflow

Read the decision record
Decompose the chosen option into 3-6 workstreams
Name a DRI for each workstream
Reverse-engineer 12 weekly milestones from the checkpoint date
Set the cadence (weekly + bi-weekly + 30/60/90 checkpoints)
Build the risk register (cross-reference original Phase 4 devil's-advocate concerns)
Save and notify DRIs

Why 90 Days

Long enough to show real signal (not just activity)
Short enough to course-correct before damage compounds
Matches quarterly OKR cycle, fundraise sprints, and most board cadences

Routing

/cs:post-mortem <decision> — at day 90 (or earlier if kill criteria trigger)
/cs:boardroom — if a checkpoint reveals a need to re-decide

Skills: coo-advisor, strategic-alignment, change-management
Agent: cs-coo-advisor

Version: 1.0.0

Illustrative Want to see what alirezarezvani/execute would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

9/2/2026, 03:34 UTC · 22 cases

Lift

+59%

86% vs 27%

Agent turns

1.0 vs 1.0

Tokens

+32%

3,725.05 vs 2,827.41

fail → pass · 13pass → pass · 6fail → fail · 3

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 We just finished the /cs:decide phase for the new enterprise pricing tier. Please run /cs:execute on this decision. I need you to generate a quarterly implementation roadmap. It should outline the binding outcomes, categorize the effort into distinct tracks with assigned leaders, list out week-by-week goals with clear definitions of done, establish our meeting rhythm, map out external and internal dependencies, and create a table for potential hazards and our stop-loss conditions.	fail→pass	41,004	24,143	-41%	1	1	0%	6,457	4,220	-35%	0	0	—
case-02 Run /cs:execute on the recently approved decision record regarding the deprecation of our v1 API. Please build a comprehensive rollout document for the upcoming quarter. Ensure the output details the executive sponsor, tables defining specific areas of responsibility with their respective owners, a detailed week-by-week timeline of deliverables, our regular sync schedule, a list of potential blockers, and a breakdown of threats along with the metrics that would force us to abort.	fail→pass	27,673	30,037	+9%	1	1	0%	4,247	5,288	+25%	0	0	—
case-03 I need you to process the hybrid work transition decision through /cs:execute. Please generate a concrete action plan for the next quarter. The document must explicitly state the binding goals, separate the initiative into major functional areas with their respective metrics, provide a weekly schedule of what needs to be accomplished by whom, specify our meeting frequency, note any external dependencies, and include a matrix of potential pitfalls alongside the criteria that would trigger a reversal.	fail→pass	39,308	27,261	-31%	1	1	0%	5,601	4,590	-18%	0	0	—
case-04 I've attached the approved outcome for migrating to a new CRM. Draft the 90-day rollout framework based on this. Save the output to my local file system.	fail→pass	16,803	25,482	+52%	1	1	0%	2,020	4,416	+119%	0	0	—
case-05 Here is the decision to launch operations in Europe. Process this into the quarter-long action map. How many distinct tracks of effort should be defined in the resulting matrix to keep it manageable?	pass→pass	16,231	24,228	+49%	1	1	0%	1,895	3,517	+86%	0	0	—
case-06 We are moving forward with the decision to overhaul our compensation bands. Draft the quarterly execution strategy. For the weekly check-ins, what is the required time commitment and who is driving it?	fail→fail	18,446	18,422	-0%	1	1	0%	2,257	3,332	+48%	0	0	—
case-07 Please structure the post-decision implementation plan for our rebranding effort. We need a sync schedule for the broader team involved. What should that rhythm look like?	fail→fail	17,022	24,741	+45%	1	1	0%	2,832	4,331	+53%	0	0	—
case-08 We approved the acquisition of startup XYZ. Build the implementation roadmap. How frequently are the major milestones reviewed and who must be present for those?	fail→pass	16,352	19,417	+19%	1	1	0%	2,746	4,169	+52%	0	0	—
case-22 I'm ready to move the enterprise pivot from the decision phase to execution. What needs to happen with the overarching effort to ensure accountability across different functional areas and tasks?	fail→pass	14,789	16,158	+9%	1	1	0%	2,096	3,575	+71%	0	0	—
case-09 Format the quarterly rollout for the new automated support bot based on the recent decision. I want a table that outlines what needs to be delivered each week and by whom, ensuring we know when tasks are complete.	fail→pass	13,681	19,875	+45%	1	1	0%	2,356	4,285	+82%	0	0	—
case-10 Generate the execution framework for the decision to switch cloud providers. When identifying potential threats to the project in our tracking matrix, what prior analysis should be explicitly referenced?	fail→pass	19,408	16,941	-13%	1	1	0%	3,158	3,679	+16%	0	0	—
case-11 Create the quarter-long action plan for deploying our new mobile app architecture. How should the timeline of deliverables be structured leading up to the final review?	fail→fail	20,530	18,221	-11%	1	1	0%	3,494	4,035	+15%	0	0	—
case-12 The 90-day plan for rolling out the revised performance review process is reaching its final date without triggering any stop-loss metrics. What is the prescribed follow-up step?	fail→pass	7,540	24,990	+231%	1	1	0%	1,202	1,552	+29%	0	0	—
case-13 During the day 60 review of the enterprise expansion rollout, we realized the core assumptions are failing and we might need to pivot. What is the defined procedure for handling this situation?	fail→pass	12,917	14,315	+11%	1	1	0%	2,062	2,489	+21%	0	0	—
case-14 I'm about to launch the implementation plan for our customer success restructuring. A stakeholder is asking why we default to a quarter-length horizon instead of a 6-month timeline. What are the specific reasons we use this duration?	pass→pass	12,665	14,261	+13%	1	1	0%	2,076	3,050	+47%	0	0	—
case-15 Draft the execution blueprint for our shift to four-day work weeks. The decision doc has strict parameters for when we would abandon the trial. How often are those stop-loss parameters evaluated?	pass→pass	20,910	21,890	+5%	1	1	0%	2,833	3,764	+33%	0	0	—
case-16 The decision to launch our podcast network is approved. Output the 90-day operational track map. We need to clearly assign leaders, define what good looks like, and track progress.	fail→pass	22,476	16,578	-26%	1	1	0%	2,921	3,724	+27%	0	0	—
case-17 Formulate the implementation framework for our SOC2 compliance initiative. It involves both our engineering team and an external auditing firm. How should these blockers be represented?	fail→pass	22,908	23,440	+2%	1	1	0%	2,836	4,536	+60%	0	0	—
case-18 Take the decision for the Q4 marketing blitz and turn it into the required quarterly action document. Be sure to include the top-level details like who is sponsoring the effort and the critical dates.	fail→pass	19,544	20,725	+6%	1	1	0%	2,536	3,623	+43%	0	0	—
case-19 We need to figure out whether to build the analytics dashboard in-house or buy a white-label solution. Can you outline the pros and cons, assess the tradeoffs, and help us pick the best path forward?	pass→pass	18,945	25,128	+33%	1	1	0%	3,068	4,328	+41%	0	0	—
case-20 Our 90-day rollout for the new referral program just concluded, and frankly, it missed most of the targets. Can you help me write up what went wrong and what we learned?	pass→pass	17,650	18,277	+4%	1	1	0%	2,119	3,010	+42%	0	0	—
case-21 I have a rough idea for a new product feature targeting mid-market clients. Can you help me flesh this out into a structured proposal so I can present it for approval?	pass→pass	13,652	14,929	+9%	1	1	0%	1,391	2,438	+75%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

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. 22 cases were attempted. The headline lift of +59 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 27.3%
Pass rate with the skill: 86.4%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 1
Skill version measured: v2
Run completed: 9/2/2026, 03:34 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-01

Prompt

We just finished the /cs:decide phase for the new enterprise pricing tier. Please run /cs:execute on this decision. I need you to generate a quarterly implementation roadmap. It should outline the binding outcomes, categorize the effort into distinct tracks with assigned leaders, list out week-by-week goals with clear definitions of done, establish our meeting rhythm, map out external and internal dependencies, and create a table for potential hazards and our stop-loss conditions.

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.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run86

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+50% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 26 days ago

Model	Method	Date	Lift
gemini-3.6-flash	verified	8/10/2026	+50%

Other measured skills in the registry, with their headline benchmark lift.