Chalk Labs
Need help deploying ftk-create-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/adiwirya-ftk-create-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
Use cases: writing
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/ftk-create-spec
What's inside
- Skill name
ftk-create-spec- Description
- Create and save a Spec from current conversation context. Use when the user asks to write, save, or generate a Spec without further interview.
- License
- MIT
- Instructions
- 51 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- interview-ledger-format.md · references/
- spec-format.md · references/
SKILL.md (first lines)
Do not interview the user or require outline approval. Ask inline only when a Critical Ambiguity would make the Spec unsafe or misleading. Capture the requirements-level problem, solution shape, user-visible behaviors, constraints, error cases, output rules, boundaries, and durable decisions inferred from the conversation. Merge items only when the merge is lossless: no actor, behavior, condition, rationale, traceability target, or downstream Work Item reference is lost. ## Process 1. If you have not already explored the target project, briefly inspect the files, docs, tests, examples, and domain context directly relevant to the conversation. Use the project's established vocabulary and respect relevant docs. 2. Identify the Test Seams for the feature. Prefer existing Test Seams over new ones. Capture durable testing decisions in `## Testing Strategy`; ask the user only if the Test Seam is a Critical Ambiguity. 3. Extract materially resolved questions and answers into an Interview Ledger, then create the Spec, preserving distinct requirements and boundaries from the conversation. ## Workflow Storage Before writing, ensure FTK workflow config exists at `.ftk/config.yaml` in the current working directory. If that file is missing or invalid, invoke `ftk-config` from the same current working directory, then continue. Read `.ftk/workflow.md`. Write the Spec using configured Workflow Storage and store the Interview Ledger with it. Load the FTK storage reference named by `.ftk/workflow.md` before writing, and follow its exact folder and file-naming convention. If writing cannot proceed, stop and report the missing prerequisite. Do not silently use another storage location. ## Write The Interview Ledger Read [interview-ledger-format.md](./references/interview-ledger-format.md) before writing the ledger. Extract materially resolved Q/A into stable `L#` records. Do not include trivial conversational turns. If there was no interview and no materially resolved answer beyond the source request, still write a minimal ledger with one `current` record for the initial request when it contains implementation-relevant requirements. ## Write The Spec Read [spec-format.md](./references/spec-format.md) before writing the Spec. Reference ledger IDs inline where the Spec covers ledger decisions, especially in `Requirements`, `Technical Decisions`, and `Testing Strategy`. Before finishing, check that every `current` ledger ID appears in the Spec. If an ID cannot be covered because it remains unresolved, mark that ledger record `deferred` and include the unresolved point under `Open Questions` or `Blocking Questions` when appropriate. ## Completion End by showing the location of the saved Spec and Interview Ledger. Then recommend starting a new session with `/new` and choosing one path. If this skill is running through a workflow variant, substitute the matching variant commands in the recommendation. ```md 1. Run `ftk-refine-spec <Spec>` to review the Spec and ledger coverage for contradictions and gaps. 2. Run `ftk-create-issues <Spec>` if the Spec should be decomposed into independently executable Work Items. 3. Run `ftk-implement <Spec>` if the Spec is small, cohesive, low-risk, and does not need decomposition. ``` Do not invoke the next workflow automatically.
From adiwirya/flutter-tools-kit, MIT.
More from adiwirya/flutter-tools-kit
- 0.479score
ftk-interview
adiwirya
Resolve intent, language, constraints, and decision dependencies before writing a Spec.
SkillCFreshness: CClaude Code +9 - 0.479score
ftk-config
adiwirya
Configure FTK workflow storage and semantics for the current working directory.
SkillCFreshness: CClaude Code +9 - 0.476score
ftk-build-ui
adiwirya
Build a Flutter screen or widget that visually matches a design from Figma, an image, or a description.
SkillCFreshness: CClaude Code +9 - 0.474score
ftk-ci
adiwirya
Generate a GitHub Actions workflow for a Flutter project — analyze, test, smoke build, artifact.
SkillCFreshness: CClaude Code +9 - 0.474score
ftk-scaffold-feature
adiwirya
Add a feature module (data/domain/presentation + Riverpod providers + route) to an existing Flutter project.
SkillCFreshness: CClaude Code +9 - 0.474score
ftk-scaffold-project
adiwirya
Create a new Flutter project with feature-first structure, Riverpod, linting, and optional flavors.
SkillCFreshness: CClaude Code +9 - 0.474score
ftk-execute
adiwirya
Execute a Spec's Work Items subagent-driven — a fresh ftk-implementer per item, ftk-task-reviewer gate per item, final whole-run review.
SkillCFreshness: CClaude Code +9 - 0.474score
ftk-l10n
adiwirya
Set up Flutter localization (ARB + intl, Indonesian/English default) or migrate hardcoded strings to AppLocalizations.
SkillCFreshness: CClaude Code +9 - 0.471score
ftk-refactor-legacy
adiwirya
Migrate an existing Flutter project toward FTK standards (feature-first, Riverpod, dio) one feature at a time, behind characterization tests.
SkillCFreshness: CClaude Code +9 - 0.469score
ftk-release
adiwirya
Build a release of a Flutter app — version bump, signing checks, APK/AAB/IPA build, upload guidance.
SkillCFreshness: CClaude Code +9 - 0.469score
ftk-add-tests
adiwirya
Add unit, widget, golden, or integration tests to a Flutter project, choosing the right level per seam.
SkillCFreshness: CClaude Code +9 - 0.469score
ftk-perf
adiwirya
Diagnose and fix Flutter performance problems — jank, slow lists, slow startup — measurement-first in profile mode.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 8, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/adiwirya/flutter-tools-kit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from adiwirya
- 0.479score
ftk-interview
adiwirya
Resolve intent, language, constraints, and decision dependencies before writing a Spec.
SkillCFreshness: CClaude Code +9 - 0.479score
ftk-config
adiwirya
Configure FTK workflow storage and semantics for the current working directory.
SkillCFreshness: CClaude Code +9 - 0.476score
ftk-build-ui
adiwirya
Build a Flutter screen or widget that visually matches a design from Figma, an image, or a description.
SkillCFreshness: CClaude Code +9 - 0.474score
ftk-execute
adiwirya
Execute a Spec's Work Items subagent-driven — a fresh ftk-implementer per item, ftk-task-reviewer gate per item, final whole-run review.
SkillCFreshness: CClaude Code +9 - 0.474score
ftk-ci
adiwirya
Generate a GitHub Actions workflow for a Flutter project — analyze, test, smoke build, artifact.
SkillCFreshness: CClaude Code +9 - 0.474score
ftk-l10n
adiwirya
Set up Flutter localization (ARB + intl, Indonesian/English default) or migrate hardcoded strings to AppLocalizations.
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 ftk-create-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
ftk-create-spec skill. Agent Mart. https://agentmart.dev/skills/adiwirya-ftk-create-spec (last updated 2026-10-24)