propose
Produce a prioritized, phased ASCII roadmap of everything worth building next, using the current session's understanding as the primary source of truth.
Skill by Banksy-said-hi
Chalk Labs
Need help deploying propose?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/banksy-said-hi-propose
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/propose
What's inside
- Skill name
propose- Description
- Produce a prioritized, phased ASCII roadmap of everything worth building next, using the current session's understanding as the primary source of truth. Use when the user types /propose.
- License
- MIT
- Instructions
- 45 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## Sources, in priority order
1. **This conversation** — things discussed, files read, bugs found, decisions, pending work. Use it first and fully.
2. **Targeted lookups**, only for what the session is missing:
- an item mentioned but not detailed → read that file
- open issues → `gh issue list --state open --limit 50`
- `features/` or `lessons/` folders, if present → read them
- recent momentum → `git log --oneline -15`
No full project survey, no speculative reads.
## Reasoning
Weigh dependencies, risk (architectural impact, shared infra), value per effort, momentum (half-done work), and debt. Group into 3–5 **independently shippable** phases.
## Output
Item format: `[effort] · [VERB] [what] → [measurable result]` — effort S=hours, M=1–2d, L=3–5d, XL=1wk+.
Example: `S · Dynamic-import MetricsSection → /system First Load 200 kB → 90 kB`
```
ROADMAP · <date>
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
NOW · <theme>
S · <verb> <what> → <impact>
NEXT · <theme>
M · <verb> <what> → <impact>
SOON · <theme>
L · <verb> <what> → <impact>
LATER · <theme>
XL · <verb> <what> → <impact>
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Start here → <item> · <why it unblocks the most>
```
Rules:
- NOW is always stability, debt, and blockers.
- Themes: ≤3 words, outcome-oriented ("Cut render debt", not "Performance phase").
- Impact is concrete: a number, a user behavior, or a removed risk.
- Don't pad: 5 real items → show 5. No dependency map unless a dependency is non-obvious.From Banksy-said-hi/claude-skills, MIT.
More from Banksy-said-hi/claude-skills
- 0.565score
yo
Banksy-said-hi
Quick "where are we" re-orientation after the user has been away.
SkillAFreshness: AClaude Code +9 - 0.565score
unify
Banksy-said-hi
Autonomous last-gate-before-push drift audit.
SkillAFreshness: AClaude Code - 0.565score
vis
Banksy-said-hi
Explain a freshly cloned repo visually in a landscape PDF on the Desktop (overview, dictionary, technologies, data models, abstract architecture map…
SkillAFreshness: AClaude Code - 0.565score
scout
Banksy-said-hi
Objective deep research before or during building - how others (competitors, open source, papers, platform docs) solve the problem at hand, what our code does…
SkillAFreshness: AClaude Code +9 - 0.565score
dump
Banksy-said-hi
Write a project handoff document (Markdown, plus PDF when pandoc is available) into progress/ covering everything discussed, built, decided, and remaining, so…
SkillAFreshness: AClaude Code +9 - 0.565score
issues
Banksy-said-hi
Fetch all open GitHub issues, ground them in the codebase, and give each a root cause, proposed fix, downstream effects, and a value-to-effort priority ranking.
SkillAFreshness: AClaude Code - 0.565score
lesson
Banksy-said-hi
Document the bug or non-obvious challenge just resolved in this session as a file in the project's lessons/ folder, so future sessions (and /study) learn from…
SkillAFreshness: AClaude Code +9 - 0.565score
perf
Banksy-said-hi
Autonomous, stack-aware performance audit.
SkillAFreshness: AClaude Code - 0.565score
sec
Banksy-said-hi
Autonomous, stack-aware security audit.
SkillAFreshness: AClaude Code - 0.565score
spec
Banksy-said-hi
Turn a feature, idea or behaviour change into a written spec by finding the gaps and asking about them instead of guessing.
SkillAFreshness: AClaude Code +9 - 0.565score
study
Banksy-said-hi
Deeply study the current project so you are ready to implement features.
SkillAFreshness: AClaude Code +9 - 0.565score
vid
Banksy-said-hi
Make a short, code-built motion-graphic film (teaser, launch, feature or explainer) for the current project, end to end - story, voiceover, music, sound…
SkillAFreshness: AClaude Code
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 25, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Banksy-said-hi/claude-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Banksy-said-hi
- 0.565score
lesson
Banksy-said-hi
Document the bug or non-obvious challenge just resolved in this session as a file in the project's lessons/ folder, so future sessions (and /study) learn from…
SkillAFreshness: AClaude Code +9 - 0.565score
scout
Banksy-said-hi
Objective deep research before or during building - how others (competitors, open source, papers, platform docs) solve the problem at hand, what our code does…
SkillAFreshness: AClaude Code +9 - 0.565score
dump
Banksy-said-hi
Write a project handoff document (Markdown, plus PDF when pandoc is available) into progress/ covering everything discussed, built, decided, and remaining, so…
SkillAFreshness: AClaude Code +9 - 0.565score
unify
Banksy-said-hi
Autonomous last-gate-before-push drift audit.
SkillAFreshness: AClaude Code - 0.565score
issues
Banksy-said-hi
Fetch all open GitHub issues, ground them in the codebase, and give each a root cause, proposed fix, downstream effects, and a value-to-effort priority ranking.
SkillAFreshness: AClaude Code - 0.565score
perf
Banksy-said-hi
Autonomous, stack-aware performance audit.
SkillAFreshness: AClaude Code
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get propose running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
propose skill. Agent Mart. https://agentmart.dev/skills/banksy-said-hi-propose (last updated 2026-10-24)