Ready to supercharge your AI agents?

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

Get Started Free →

Plan · boshu2 | DecimalAI

agent toolingby boshu2

Plan

boshu2/plan

Source boshu2/agentops ↗License Apache-2.0

Shape or refine the existing bead or caller

SkillScore65Maintained

Automatic

Coding pack

Last verified 10/10/2026

What it changes

Passed 15 of 23 test cases with the skill, and 6 of 23 without it.

Without skill26%

With skill65%

Checks it passed that the model alone missed

Places deferred secondary features into the Later field.
Omits generating an AgentOps provenance packet during planning.
Specifies the evidence or event that would trigger working on deferred items.

and 15 more in the full report

11 fixed4 passed either way6 still failing2 broke

Pass-rate lift: +39 pp
Tokens: +78%
Agent turns: 0%
Response time: -5%

Model gemini-3.6-flashMeasured 10/10/2026v715 of 23 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/boshu2-plan/SKILL.md https://app.decimal.ai/s/boshu2-plan/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add boshu2-plan, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

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

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/boshu2-plan/ and pins it in .decimal/skills.lock

decimalai skills add boshu2-plan

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

curl -fsSL --create-dirs -o .claude/skills/boshu2-plan/SKILL.md https://app.decimal.ai/s/boshu2-plan/SKILL.md

Raw file: /s/boshu2-plan/SKILL.md ↗ · machine-readable summary at /s/boshu2-plan.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

We want to add export to CSV functionality to our analytics dashboard. It is tempting to create a multi-step project plan with Phase 1 database queries, Phase 2 backend API endpoint, Phase 3 frontend button, and Phase 4 background job. Produce a task plan block for the immediate work.

What was checked, without and with the skill
Checked	Without skill	With skill
Shapes the task plan as a single end-to-end slice rather than a multi-phase roadmap.	Passed	Passed
Defers secondary enhancements like background processing into the Later field with triggering evidence.	Missed	Passed

case-04 · gemini-3.6-flash · 10/10/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md119 lines6 filesincludes scripts

Plan

Shape missing intent into one actionable slice, then stop. A clear change can proceed directly; load a specialist only for the question it answers. Prefer the caller's tracker, if any; otherwise use the conversation or supplied text. Planning produces no AgentOps packet.

A plan meets these rules

One slice, not a roadmap. Shape the narrowest change that produces an observable result end to end, through every layer it touches. No phases, no layer-by-layer breakdown, no backlog: later work stays one coarse line each until new evidence makes it the next slice.
An example before any design. Write at least one Given/When/Then with an observable result. Cover the boundary where a mistake is costly to undo, such as a repeated or external side effect, lost data or widened access, not only the happy path.
Look up facts; ask only for choices. Read code, docs and the tracker instead of asking. Ask the caller at most one question, only for a choice no source can answer, with your recommendation and its tradeoff.
The repository's words. Reuse the term its code, glossary or tracker defines; never coin a parallel name.
Scope by consumer. Name the owners to edit, every live caller and test of the changed behavior, and generated companions as a class. Scope is authority, not a predicted file count.
A discriminating check: what fails today and passes after the slice.

Output

Write this block into the caller's existing intent (tracker item or conversation). It is the whole plan.

Outcome:  <who observes what, in the repository's terms>
Example:  Given <state>, when <event>, then <observable result>
Slice:    <the one end-to-end change that makes the example true>
Scope:    <owners>; consumers: <live callers and tests>; generated: <class> | none
Check:    <the test or observation that fails now and passes after the slice>
Question: <one caller choice, your recommendation, its tradeoff> | none
Later:    <deferred item and the evidence that would make it next> | none

Track record

Benchmark

15 / 23

test cases passed, vs 6 / 23 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 10/10/2026

View 15 scanner checks

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

boshu2 / agentops

skills-codex/plan/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 10/10/2026Version v7Bundled 5 files · scripts

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Plan

A plan meets these rules

Output

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills