Skip to content
Agentmart
Submit a tool

evidence-plan

Idea → cited research → HTML proposal (human confirms) → /dev-kit:plan hand-off.

Skill by sh-ai-x

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying evidence-plan?

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.

Book a call

Install

Works with Claude Code. Read the repository before you give any tool access to your data.

npx agentmarket install skill/sh-ai-x-evidence-plan

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.

We use your email only for this newsletter. Privacy

About

Idea → cited research → HTML proposal (human confirms) → /dev-kit:plan hand-off. The proposal is rendered and reviewed BEFORE the expensive 5-gate PRD work runs, not after.

Use cases: frontend, research

No 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/evidence-plan

Tools it pre-approves 5

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Read
  • Write
  • Glob
  • Grep
  • Skill

What's inside

Skill name
evidence-plan
Description
Idea → cited research → HTML proposal (human confirms) → /dev-kit:plan hand-off. The proposal is rendered and reviewed BEFORE the expensive 5-gate PRD work runs, not after.
License
MIT
Allowed tools
Read, Write, Glob, Grep, Skill
Instructions
44 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

> [← Skills index](../../README.md)

## What it does

Three phases, in order. Each phase's output gates the next; the skill
never invokes `/dev-kit:build` and never writes source code.

1. **Research** — `Skill("research", <idea>)`. Produces cited evidence
   (every claim carries `url` + `fetched_at` + `source_type`, or is
   flagged `[UNCITED]`).
2. **Proposal** — writes `docs/proposals/<main>/idea-<slug>.yaml`
   (before/after + pros/cons/limitations, seeded from the research
   output), then `Skill("proposal", "<main>/idea-<slug>")` to render
   `docs/proposals/<main>/idea-<slug>.html`. `disallowed-tools` above
   includes `Bash`, but `proposal` renders via its own `Bash` grant in
   its own frontmatter — a called skill's tool grants are evaluated
   against its own frontmatter, not the caller's. **Stop here.** Tell
   the user to open the HTML and confirm before continuing — do not
   proceed to Phase 3 without an explicit go-ahead.
3. **Plan hand-off** — once confirmed, `Skill("plan", <idea>)`. Plan
   runs its own unmodified 5-gate loop and, at Gate 5/5, renders its
   own proposal under the phase-name slug (`<main>/<phase>`) — a
   separate, later "final design record" distinct from this skill's
   earlier "idea pitch" proposal at `<main>/idea-<slug>`. Collision is
   prevented by construction, not just the `idea-` prefix convention:
   `/dev-kit:proposal` refuses to overwrite an existing file with
   different content and has no overwrite flag (see
   `skills/proposal/SKILL.md` §Limitations), so a phase later named
   `idea-<slug>` would surface a conflict for the user to resolve
   rather than silently overwriting this skill's earlier proposal.

## Why this order

`/dev-kit:plan`'s Gate 4 (decompose) is the expensive step — full
phase + step-file generation. Reviewing a lightweight proposal before
that work runs, instead of after, means a rejected idea costs one
research pass and one proposal render, not a full PRD.

## Next step

`/dev-kit:plan` (invoked internally via `Skill("plan", ...)` once the
user confirms the Phase 2 proposal). This skill's job ends at the
Phase 3 hand-off.

From sh-ai-x/dev-harness-kit, MIT.

More from sh-ai-x/dev-harness-kit

Signals

Stars
1
Forks
2
Open issues
8
Last commit (this folder)
Aug 12, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from sh-ai-x

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 evidence-plan 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying evidence-plan?

CallGet help
Cite this page

evidence-plan skill. Agent Mart. https://agentmart.dev/skills/sh-ai-x-evidence-plan (last updated 2026-10-24)