Ready to supercharge your AI agents?

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

Get Started Free →

Trello-Aware Planning · aiskillstore | DecimalAI

aiskillstore/planning-with-trello

SkillScore95Maintained

Use when planning features, organizing sprints, or syncing work with Trello boards.

productivityby aiskillstore

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/aiskillstore-planning-with-trello/SKILL.md

decimalai skills pull aiskillstore-planning-with-trello --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/aiskillstore-planning-with-trello/SKILL.md https://app.decimal.ai/s/aiskillstore-planning-with-trello/SKILL.md

Raw file: /s/aiskillstore-planning-with-trello/SKILL.md ↗ · machine-readable summary at /s/aiskillstore-planning-with-trello.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 20d ago

Yes — +59% lift-43% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	-16%	0%
case-13	✗→✓	▲ Improved	-51%	0%
case-01	✗→✓	▲ Improved	-22%	0%
case-02	✗→✓	▲ Improved	-70%	0%
case-03	✗→✓	▲ Improved	-2%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

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

aiskillstore / marketplace

skills/bpsai/planning-with-trello/SKILL.md

View on GitHub ↗

Imported 8/10/2026Version v1

Skill contents

SKILL.md

Trello-Aware Planning

Board Structure (7 Lists Max)

Intake/Backlog - New ideas, not selected for work
Planned/Ready - Selected for upcoming work
In Progress - Active development
Review/Testing - Under review
Deployed/Done - Completed
Issues/Tech Debt - Bugs, improvements
Notes/Ops Log - Decisions, notes

Card Title Format

[Stack] Task Name

Examples: [CLI] Add MCP server, [Docs] Update README

Effort Labels

| Size | Description | Complexity | |------|-------------|------------| | S | Few hours | 0-25 | | M | Half-full day | 26-50 | | L | Multiple days | 51+ |

Stack Labels

| Label | Use For | |-------|---------| | Frontend (green) | React, UI | | Backend (blue) | Flask, API | | Worker (purple) | Background jobs | | Bug/Issue (orange) | Bugs | | AI/ML (black) | Models, LLM |

Workflow

1. Create Plan

bash
bpsai-pair plan new <slug> --type feature --title "Title"

2. Add Tasks

Break into 1-2 day units with acceptance criteria.

3. Sync to Trello

bash
# Preview
bpsai-pair plan sync-trello <plan-id> --dry-run

# Sync to Planned/Ready (recommended for sprints)
bpsai-pair plan sync-trello <plan-id> --target-list "Planned/Ready"

4. Execute Tasks

Follow managing-task-lifecycle skill for starting/completing.

Commands

bash
bpsai-pair plan list                    # List plans
bpsai-pair plan status <plan-id>        # Plan status
bpsai-pair plan sync-trello <plan-id>   # Sync to Trello
bpsai-pair task list --plan <plan-id>   # Tasks in plan

Illustrative Want to see what aiskillstore/planning-with-trello 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

9/3/2026, 20:54 UTC · 22 cases

Lift

+59%

95% vs 36%

Agent turns

0%

1.0 vs 1.0

Tokens

-43%

986.55 vs 1,740.09

fail → pass · 14pass → pass · 7pass → fail · 1

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-04 We are organizing a Trello board for our software project. We want 10 lists including 'Backlog', 'Ready', 'In Progress', 'Code Review', 'QA', 'Staging', 'Prod', 'Bugs', 'Blocked', and 'Logs'. How should we structure our board lists for optimal plan synchronization?	fail→pass	22,023	14,964	-32%	1	1	0%	2,673	2,253	-16%	0	0	—
case-13 When categorizing tasks involving LLM prompt engineering and model evaluation pipelines, what stack label name and label color are assigned?	fail→pass	15,315	6,977	-54%	1	1	0%	1,672	813	-51%	0	0	—
case-01 I need to start a new feature plan for adding dark mode to our web app. Break down the work into manageable developer tasks with titles, estimated effort sizes, stack categorizations, and acceptance criteria. Also list the CLI commands to initialize this plan, check its status, and dry-run pushing it to our Trello board.	fail→pass	14,722	12,598	-14%	1	1	0%	2,640	2,046	-23%	0	0	—
case-02 Our team is preparing for the next sprint and we have an existing plan with the ID `user-profile-v2`. Please provide the exact terminal commands to inspect the plan's current tasks, run a test preview of the sync, and then push the tasks directly to our target list for ready work.	fail→pass	22,311	7,857	-65%	1	1	0%	3,456	1,027	-70%	0	0	—
case-03 I'm setting up our project tasks for a background job system, an API endpoint, and a bug fix. How should I format the card titles, effort sizes, and stack tags according to our Trello board standards, and what command do I run to check all active plans?	fail→pass	11,052	6,289	-43%	1	1	0%	1,737	1,706	-2%	0	0	—
case-05 Where on our project Trello board should architecture decision records, meeting summaries, and ops log entries be kept?	fail→pass	18,016	3,456	-81%	1	1	0%	1,969	1,001	-49%	0	0	—
case-06 A task requires setting up a simple environment variable check that takes about two hours and has low complexity (complexity score around 15). What effort label code should be assigned to this task?	fail→pass	12,719	2,242	-82%	1	1	0%	1,117	803	-28%	0	0	—
case-07 A developer task takes half to a full day of work with moderate complexity (complexity score around 40). What effort size designation code applies to this task?	pass→pass	14,154	7,256	-49%	1	1	0%	1,561	851	-45%	0	0	—
case-08 A complex refactoring task will span multiple days and has a complexity rating over 50. What effort size code should be assigned?	fail→pass	9,920	6,473	-35%	1	1	0%	1,452	724	-50%	0	0	—
case-09 What color tag and stack label should be assigned to React components and user interface work on our board?	fail→pass	9,120	6,394	-30%	1	1	0%	1,516	678	-55%	0	0	—
case-10 When tagging Flask services and REST API endpoints, what stack label name and color should be attached to the cards?	fail→pass	11,632	1,987	-83%	1	1	0%	1,805	750	-58%	0	0	—
case-11 Background async worker scripts and Celery job queue tasks need board labels. Which stack tag name and label color should be assigned to them?	pass→pass	13,992	4,177	-70%	1	1	0%	1,443	763	-47%	0	0	—
case-12 What label name and color code are used for tracking software bugs and defects?	fail→pass	14,900	1,902	-87%	1	1	0%	1,386	739	-47%	0	0	—
case-14 We want to initiate a new feature plan titled 'User Authentication' with slug 'user-auth'. What exact terminal command line call creates this plan using the proper plan type and title flags?	fail→pass	18,584	1,592	-91%	1	1	0%	3,350	809	-76%	0	0	—
case-15 We need to check the execution status of an active plan with ID 'payment-gateway-v1'. What CLI command checks this status?	fail→pass	20,415	6,862	-66%	1	1	0%	2,758	789	-71%	0	0	—
case-16 When syncing plan tasks to Trello for an upcoming sprint, which standard list target is recommended?	fail→pass	6,606	8,844	+34%	1	1	0%	999	791	-21%	0	0	—
case-17 Where on the board structure should newly submitted feature ideas go if they have not yet been selected for active or sprint work?	pass→pass	15,780	7,621	-52%	1	1	0%	1,689	846	-50%	0	0	—
case-18 Which board list is designated specifically for recording software bugs and technical debt items?	pass→pass	13,368	6,831	-49%	1	1	0%	1,297	729	-44%	0	0	—
case-19 When breaking down a plan into individual developer tasks, what work unit duration should each task target?	pass→pass	15,548	8,046	-48%	1	1	0%	1,957	857	-56%	0	0	—
case-20 What endpoint and HTTP method does the Trello REST API specify for creating a new webhook for board event notifications?	pass→pass	10,076	7,719	-23%	1	1	0%	939	964	+3%	0	0	—
case-21 What endpoint and HTTP method does the Trello REST API specify for retrieving all cards belonging to a specific list by list ID?	pass→pass	8,031	2,390	-70%	1	1	0%	531	942	+77%	0	0	—
case-22 What exact Git command creates an annotated tag named v1.0.0 with the message 'Release 1.0.0'?	pass→fail	7,303	1,793	-75%	1	1	0%	335	823	+146%	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: 36.4%
Pass rate with the skill: 95.5%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 1
Skill version measured: v1
Run completed: 9/3/2026, 20:54 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-04

Prompt

We are organizing a Trello board for our software project. We want 10 lists including 'Backlog', 'Ready', 'In Progress', 'Code Review', 'QA', 'Staging', 'Prod', 'Bugs', 'Blocked', and 'Logs'. How should we structure our board lists for optimal plan synchronization?

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 run95

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-37% 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 19 days ago

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