Ready to supercharge your AI agents?

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

Make a Plan · penpot | DecimalAI

productivityby penpot

Make a Plan

penpot/make-a-plan

Source penpot/penpot ↗License MPL-2.0

Planning flow — research the subject of this session, produce an implementation plan with the planner skill, resolve open questions with the user in plain language, and save the final plan to .agents/plans/.

SkillScore52Maintained

Automatic

Coding pack

Last verified 10/6/2026

What it changes

Passed 8 of 16 test cases with the skill, and 3 of 16 without it.

Without skill17%

With skill52%

Checks it passed that the model alone missed

Flips the plan Status field to reviewed.
Passes full session context to the subagent.
States clearly that no decisions require user input.

and 8 more in the full report

8 fixed4 passed either way11 still failing0 broke

Pass-rate lift: +35 pp
Tokens: +49%
Agent turns: 0%
Response time: -48%

Model gemini-3.6-flashMeasured 10/6/2026v212 of 23 cases passed with skill · 16 comparable

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/penpot-make-a-plan/SKILL.md https://app.decimal.ai/s/penpot-make-a-plan/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add penpot-make-a-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/penpot-make-a-plan/ and pins it in .decimal/skills.lock

decimalai skills add penpot-make-a-plan

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

The plan summary for the layer grouping feature has just been delivered to the user. How should the response end?

What was checked, without and with the skill
Checked	Without skill	With skill
Lists /review-plan as the first suggested next step.	Missed	Passed
Lists /implement-plan as the second suggested next step.	Missed	Passed

case-19 · gemini-3.6-flash · 10/6/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md109 linessingle file

Make a Plan

Act as a senior software engineer: research the subject of this session in depth and produce a well-grounded, actionable implementation plan.

If the running agent cannot write (for example, the plan agent), say so and stop — this skill needs the build agent to save the plan.

When to use

The user asks to plan, design, or break down a task, in any phrasing: "make a plan", "how would we build X", "design an approach for Y" — or runs /make-a-plan.
The user asks to rework or extend an existing plan. While the plan is still unimplemented (pre-implement-plan iteration, e.g. after /review-plan findings or user feedback), revise the saved plan file in place. Once the plan has been implemented and reviewed (post /review-code findings on committed work), write a new derived plan file instead — never rewrite the executed plan. The planner skill defines the derived naming (--review-NN, --task-NN).
The user says to apply review-plan findings to a still-unimplemented plan: apply the agreed changes, flip Status to reviewed, and append one UTC ISO 8601 line to Review Log describing what changed. This apply step is the only pre-implementation write to those fields — review-plan itself stays read-only and never writes.

Do not use it to execute a plan — that is the implement-plan flow.

Instructions

Produce the plan with the planner skill. By default, research the subject of this session and draft the plan yourself. If I ask for it (for example, delegated in the user context), delegate to the general subagent instead — the delegate must also follow the planner skill and receive all the relevant session context (a review, user feedback, and so on).
Before asking me to decide anything, explain the plan and every open question in plain language. Assume I know only the high-level project goal, not the codebase, architecture, implementation terms, or the problem this task solves.
Once all decisions are answered and the plan is final, save it verbatim to the announced path under .agents/plans/ (create the directory if it does not

Track record

Benchmark

8 / 16

test cases passed, vs 3 / 16 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 — 9/23/2026

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

penpot / penpot

.agents/skills/make-a-plan/SKILL.md

View on GitHub ↗

License MPL-2.0Imported 9/23/2026Version v2

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

Make a Plan

When to use

Instructions

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills