discovery
Route a new or returning request into the refinement-driven workflow.
Skill by KKuze
Chalk Labs
Need help deploying discovery?
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/kkuze-discovery
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: productivity
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/discovery
What's inside
- Skill name
discovery- Description
- Route a new or returning request into the refinement-driven workflow. Use when the user opens a feature, bug, or change request and there is no active spec context yet.
- License
- MIT
- Instructions
- 29 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# discovery You are the entry point of the rd-flow workflow. ## When to invoke - The user describes a new feature, bug, or change in plain language. - The user mentions resuming a spec but the active spec is unclear. ## Steps 1. Read `.formal/settings/rules/routing.md` and apply it. 2. List existing specs (`rd-flow spec list`). If one matches, read its `manifest.yaml` and resume at `current_phase`. 3. Otherwise propose a kebab-case spec name and create it: ``` rd-flow spec new <name> --title "..." --summary "..." ``` 4. Hand off to the `requirements` skill. ## Output A one-paragraph confirmation: - chosen spec name, - whether it is new or resumed, - which phase the user is in, - the next concrete action.
From KKuze/rd-flow, MIT.
More from KKuze/rd-flow
- 0.521score
implement
KKuze
Build the implementation plan and code mapping from a verified rd-flow spec.
SkillBFreshness: BClaude Code +9 - 0.518score
validate
KKuze
Close the loop on an rd-flow spec by confirming every requirement maps to verified specs and shipping code.
SkillBFreshness: BClaude Code +9 - 0.471score
dafny-build
KKuze
Compile a verified Dafny spec to a target language (cs, java, go, js, py, cpp, rs) and capture the emitted artefacts.
SkillCFreshness: CClaude Code +9 - 0.471score
tla-model
KKuze
Author the TLA+ abstract behavioural spec for an rd-flow workspace.
SkillCFreshness: CClaude Code +9 - 0.469score
dafny-refine
KKuze
Refine an rd-flow TLA+ spec into a Dafny module with concrete types and contracts.
SkillCFreshness: CClaude Code +9 - 0.469score
dafny-prove
KKuze
Run Dafny verification on an rd-flow spec and iterate until proofs discharge.
SkillCFreshness: CClaude Code +9 - 0.469score
tla-check
KKuze
Run TLC against an rd-flow TLA+ model and triage the result.
SkillCFreshness: CClaude Code +9 - 0.447score
requirements
KKuze
Drive the requirements phase of an rd-flow spec.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- May 11, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/KKuze/rd-flow
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from KKuze
- 0.521score
implement
KKuze
Build the implementation plan and code mapping from a verified rd-flow spec.
SkillBFreshness: BClaude Code +9 - 0.518score
validate
KKuze
Close the loop on an rd-flow spec by confirming every requirement maps to verified specs and shipping code.
SkillBFreshness: BClaude Code +9 - 0.471score
dafny-build
KKuze
Compile a verified Dafny spec to a target language (cs, java, go, js, py, cpp, rs) and capture the emitted artefacts.
SkillCFreshness: CClaude Code +9 - 0.471score
tla-model
KKuze
Author the TLA+ abstract behavioural spec for an rd-flow workspace.
SkillCFreshness: CClaude Code +9 - 0.469score
dafny-refine
KKuze
Refine an rd-flow TLA+ spec into a Dafny module with concrete types and contracts.
SkillCFreshness: CClaude Code +9 - 0.469score
dafny-prove
KKuze
Run Dafny verification on an rd-flow spec and iterate until proofs discharge.
SkillCFreshness: CClaude 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 discovery 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
discovery skill. Agent Mart. https://agentmart.dev/skills/kkuze-discovery (last updated 2026-10-24)