scaffold-planning
Skill1 starsChanged 5 months agoMITView on GitHub
Generate the 5-file planning structure (PRD.md, ROADMAP.md, DECISIONS.md, PARKED.md, ERRORS.md) at the project root, pre-filled from the current conversation. Refuses to overwrite existing files.
In this repository13 other files it gives its agents.
- adversarial-verifySkill
- closed-loopSkill
- cluster-feedbackSkill
- doubt-gateSkill
- fleet-loopSkill
- hill-climbSkill
- keep-greenSkill
- loop-auditSkill
- loop-readinessSkill
- loop-stateSkill
- prod-watchSkill
- ship-preflightSkill
- source-groundedSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Create the standard planning document set at the project root.
- Distinctive: line 58
Never overwrite a file that already exists — abort for that file and report.
- Distinctive: line 61
All items that are out of scope for v0 go into PARKED.md, not PRD.md.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Scaffold Planning
Create the standard planning document set at the project root. Pre-fill each file from context already in the conversation — do not leave placeholders or ask for content that has been stated.
Files to create
PRD.md
One page maximum. Structure:
- One-liner: what it is and who it's for
- Problem being solved
- Target user
- v0 done criteria (checkboxes — these are the north star)
- In-scope items
- Out-of-scope items (→ PARKED.md)
- Constraints
- Non-goals
ROADMAP.md
Ordered slice list. Structure:
## v0 — Shippable to one user— ordered slices, sequential not parallel## v1 — After first real user## v2+ — Aspirational
DECISIONS.md
Append-only log. Pre-fill any decisions already made in the conversation. Format per entry:
## YYYY-MM-DD — <title>
**Choice:** <what was decided>
**Alternatives:** <what was rejected>
**Why:** <reasoning>
**Reversible?** yes | noPARKED.md
Deferred ideas — never refused, only promoted. Pre-fill any out-of-scope items surfaced in the conversation. Format:
## <idea>
**Captured:** YYYY-MM-DD
**Why parked:** <reason>
**Cost to revisit:** <rough estimate>ERRORS.md
Append-only failure log. Empty at scaffold time (no prior failures). Format for future entries:
## YYYY-MM-DD — <task>
**What failed:** <approach>
**What worked:** <fix>
**Why it failed:** <root cause>Constraints
- Never overwrite a file that already exists — abort for that file and report.
- PRD.md must stay under one page — cut anything that isn't a v0 done criterion.
- DECISIONS.md and ERRORS.md are append-only — never edit prior entries.
- All items that are out of scope for v0 go into PARKED.md, not PRD.md.
Usage
/scaffold-planning <project name>or:
We're building <X>. Scaffold the planning docs.Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

