evidence-plan
Idea → cited research → HTML proposal (human confirms) → /dev-kit:plan hand-off.
Skill by sh-ai-x
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.
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.
About
Use cases: frontend, research
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/evidence-plan
Tools it pre-approves 5
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
ReadWriteGlobGrepSkill
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
- 0.587score
harness-effectiveness
sh-ai-x
0-arg harness-effectiveness report.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
babysit-pr-local
sh-ai-x
0-arg local-mode PR babysitter.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
harness-mode
sh-ai-x
Session-scoped local-hook mode picker — fast (all optional local hooks off), full (default, all on), or custom (interactive per-local-hook picker via…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
gate-select
sh-ai-x
Unified 3-dimension picker for project / session / AI-judge gates.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
bootstrap
sh-ai-x
0-arg setup for CLAUDE.md, AGENTS.md, hooks, and optional CI.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
guard-mode
sh-ai-x
Session-scoped on/off toggle for the tdd-guard, worktree-guard, and git-guard hard-block hooks.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
babysit-pr
sh-ai-x
0-arg restart-safe PR check, diagnose, fix, and hand-off loop.
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
build
sh-ai-x
0-arg.
SkillAFreshness: A★ 1Claude Code - 0.552score
codex-cache-update
sh-ai-x
Refresh the dev-kit Codex marketplace checkout and synchronize the versioned plugin cache.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
bump
sh-ai-x
Explicit version bump of `.claude-plugin/plugin.json` + push of `chore/bump-vX.Y.Z`.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
evaluate
sh-ai-x
0-arg eval extension.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
ci-update
sh-ai-x
Detect + selectively apply drift between installed CI templates and current dev-kit source.
SkillBFreshness: B★ 1Claude Code +9
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
- Repository
- github.com/sh-ai-x/dev-harness-kit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sh-ai-x
- 0.587score
harness-effectiveness
sh-ai-x
0-arg harness-effectiveness report.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
harness-mode
sh-ai-x
Session-scoped local-hook mode picker — fast (all optional local hooks off), full (default, all on), or custom (interactive per-local-hook picker via…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
babysit-pr-local
sh-ai-x
0-arg local-mode PR babysitter.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
gate-select
sh-ai-x
Unified 3-dimension picker for project / session / AI-judge gates.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
guard-mode
sh-ai-x
Session-scoped on/off toggle for the tdd-guard, worktree-guard, and git-guard hard-block hooks.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
bootstrap
sh-ai-x
0-arg setup for CLAUDE.md, AGENTS.md, hooks, and optional CI.
SkillAFreshness: A★ 1Claude Code +9
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.
Cite this page
evidence-plan skill. Agent Mart. https://agentmart.dev/skills/sh-ai-x-evidence-plan (last updated 2026-10-24)