to-spec
Synthesize a conversation into a scoped specification, with publication when requested.
Skill by BumpyClock
Chalk Labs
Need help deploying to-spec?
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/bumpyclock-to-spec
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/to-spec
What's inside
- Skill name
to-spec- Description
- Synthesize a conversation into a scoped specification, with publication when requested.
- License
- MIT
- Instructions
- 71 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
Synthesize the current conversation and relevant codebase understanding into a spec. Reuse settled requirements, contracts, and decisions without another interview. When fetching tracker context or preparing publication, read [Tracker integration](../triage/TRACKER.md) for destination, role mapping, and authorization rules. Missing tracker setup does not block a draft. ## Process 1. Reuse existing context. Inspect relevant code only where it could change the spec's behavior or contracts. Use the project's domain glossary vocabulary and respect ADRs in the affected area. 2. Identify the agreed contracts and test interfaces. Ask only about unresolved choices that materially affect scope or those contracts. Do not reopen settled seams or invent decisions to fill gaps. 3. Write the requested spec using the applicable template sections below. Keep the problem, behavior, and scope explicit; scale the detail to the change. Return the draft, or publish it to the authorized destination when requested. Apply the configured `ready-for-agent` role only when the scope and contracts are settled enough for agent work. Finish with the draft or published issue reference. If publication is blocked, return the completed draft and the specific remaining decision or access requirement. <spec-template> ## Problem Statement The problem that the user is facing, from the user's perspective. ## Solution The solution to the problem, from the user's perspective. ## User Stories Number the distinct in-scope user behaviors. Use this format where it clarifies the actor and benefit: 1. As an <actor>, I want a <feature>, so that <benefit> <user-story-example> 1. As a mobile bank customer, I want to see balance on my accounts, so that I can make better informed decisions about my spending </user-story-example> Cover the requested behavior and meaningful edge cases without padding the list or expanding the feature. ## Implementation Decisions A list of implementation decisions that were made. This can include: - The modules that will be built/modified - The interfaces of those modules that will be modified - Technical clarifications from the developer - Architectural decisions - Schema changes - API contracts - Specific interactions Do NOT include specific file paths or code snippets. They may end up being outdated very quickly. Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it within the relevant decision and note briefly that it came from a prototype. Trim to the decision-rich parts, not a working demo, just the important bits. ## Testing Decisions A list of testing decisions that were made. Include: - The contracts and risks the selected checks address - Which modules will be tested - Prior art for the tests (i.e. similar types of tests in the codebase) ## Out of Scope A description of the things that are out of scope for this spec. ## Further Notes Any further notes about the feature. </spec-template>
From BumpyClock/agent-templates, MIT.
More from BumpyClock/agent-templates
- 0.592score
anatomy
BumpyClock
Build crafted, highly detailed, interactive isometric SVG figures that explain a technical idea as a real physical object (a test rig, a dial gauge, a cabinet…
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
babysit-pr
BumpyClock
Resolve feedback on an existing PR or stack, then babysit review and CI until mergeable or blocked.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
autonomous-delivery
BumpyClock
Adapt an orchestrator-worker system to deliver verified outcomes.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
ast-grep-cli
BumpyClock
Find code by AST shape or relationships with ast-grep.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
telemetry
BumpyClock
Design, implement, or review application telemetry instrumentation.
SkillAFreshness: A★ 1Claude Code +9 - 0.578score
split-to-prs
BumpyClock
Split current work into small reviewable PRs.
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
data-structure-audit
BumpyClock
Use when the user requests a complete, read-only codebase audit of data structures, state models, algorithms, control flow, or ownership.
SkillBFreshness: B★ 1Claude Code +9 - 0.546score
code-review
BumpyClock
Review a PR, branch, commit, or local diff for actionable defects and regressions.
SkillBFreshness: B★ 1Claude Code +9 - 0.546score
changelog
BumpyClock
Create or update user-facing changelog entries, or set up GitHub Actions to generate PR changelog entries.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
domain-modeling
BumpyClock
Sharpen project domain terms or author glossary and ADR content.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
change-amplification
BumpyClock
Find PR change-amplification from missing owners/contracts; rank cleanup backlog.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
brutal
BumpyClock
Give blunt strategic critique when the user explicitly requests brutal or no-sugarcoating feedback.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 18, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/BumpyClock/agent-templates
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from BumpyClock
- 0.592score
anatomy
BumpyClock
Build crafted, highly detailed, interactive isometric SVG figures that explain a technical idea as a real physical object (a test rig, a dial gauge, a cabinet…
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
babysit-pr
BumpyClock
Resolve feedback on an existing PR or stack, then babysit review and CI until mergeable or blocked.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
autonomous-delivery
BumpyClock
Adapt an orchestrator-worker system to deliver verified outcomes.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
ast-grep-cli
BumpyClock
Find code by AST shape or relationships with ast-grep.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
telemetry
BumpyClock
Design, implement, or review application telemetry instrumentation.
SkillAFreshness: A★ 1Claude Code +9 - 0.578score
split-to-prs
BumpyClock
Split current work into small reviewable PRs.
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 to-spec 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
to-spec skill. Agent Mart. https://agentmart.dev/skills/bumpyclock-to-spec (last updated 2026-10-24)