kha-clarify-phase
Gather phase context through adaptive questioning before planning.
Skill by trevi00
Chalk Labs
Need help deploying kha-clarify-phase?
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/trevi00-kha-clarify-phase
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: design
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/kha-clarify-phase
What's inside
- Skill name
kha-clarify-phase- Description
- Gather phase context through adaptive questioning before planning. Use --auto to skip interactive questions (Claude picks recommended defaults). Use --chain for interactive discuss followed by automatic plan+execute. Use --power for bulk question generation into a file-based UI (answer at your own pace).
- License
- MIT
- Instructions
- 88 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- allowed-tools: must be a space-separated string
Files (1)
- SKILL.md
SKILL.md (first lines)
<objective>
Extract implementation decisions that downstream agents need — researcher and planner will use CONTEXT.md to know what to investigate and what choices are locked.
**How it works:**
1. Load prior context (PROJECT.md, REQUIREMENTS.md, STATE.md, prior CONTEXT.md files)
2. Scout codebase for reusable assets and patterns
3. Analyze phase — skip gray areas already decided in prior phases
4. Present remaining gray areas — user selects which to discuss
5. Deep-dive each selected area until satisfied
6. Create CONTEXT.md with decisions that guide research and planning
**Output:** `{phase_num}-CONTEXT.md` — decisions clear enough that downstream agents can act without asking the user again
</objective>
<execution_context>
@$HOME/.claude/get-shit-done/workflows/discuss-phase.md
@$HOME/.claude/get-shit-done/workflows/discuss-phase-assumptions.md
@$HOME/.claude/get-shit-done/workflows/discuss-phase-power.md
@$HOME/.claude/get-shit-done/templates/context.md
</execution_context>
<runtime_note>
**Copilot (VS Code):** Use `vscode_askquestions` wherever this workflow calls `AskUserQuestion`. They are equivalent — `vscode_askquestions` is the VS Code Copilot implementation of the same interactive question API.
</runtime_note>
<context>
Phase number: $ARGUMENTS (required)
Context files are resolved in-workflow using `init phase-op` and roadmap/state tool calls.
</context>
<process>
**Mode routing:**
```bash
DISCUSS_MODE=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" config-get workflow.discuss_mode 2>/dev/null || echo "discuss")
```
If `DISCUSS_MODE` is `"assumptions"`: Read and execute @$HOME/.claude/get-shit-done/workflows/discuss-phase-assumptions.md end-to-end.
If `DISCUSS_MODE` is `"discuss"` (or unset, or any other value): Read and execute @$HOME/.claude/get-shit-done/workflows/discuss-phase.md end-to-end.
**MANDATORY:** The execution_context files listed above ARE the instructions. Read the workflow file BEFORE taking any action. The objective and success_criteria sections in this command file are summaries — the workflow file contains the complete step-by-step process with all required behaviors, config checks, and interaction patterns. Do not improvise from the summary.
</process>
<success_criteria>
- Prior context loaded and applied (no re-asking decided questions)
- Gray areas identified through intelligent analysis
- User chose which areas to discuss
- Each selected area explored until satisfied
- Scope creep redirected to deferred ideas
- CONTEXT.md captures decisions, not vague vision
- User knows next steps
</success_criteria>
## Output
- artifact: `${phase_dir}/${padded_phase}-CONTEXT.md` — canonical decision record for downstream research/planning
- artifact: `${phase_dir}/${padded_phase}-DISCUSSION-LOG.md` — audit log of options presented and user choices
- artifact: `${phase_dir}/${padded_phase}-DISCUSS-CHECKPOINT.json` — incremental checkpoint while discussion is in progress; deleted after successful context write
- artifact: `${phase_dir}/${padded_phase}-QUESTIONS.json` — power-mode question state file when `--power` is used
- artifact: `${phase_dir}/${padded_phase}-QUESTIONS.html` — self-contained power-mode UI when `--power` is used
- artifact: `.planning/STATE.md` — updated resume/session pointer after context capture
- status: `context_captured` | `power_mode_waiting` | `planning_complete` | `phase_complete` | `skipped_existing_context` | `aborted_invalid_phase`
## Failure behavior
- existing `CONTEXT.md` or existing plans force an explicit update/view/skip or continue-and-replan decision; the skill never silently overwrites context
- interrupted discussion resumes from `${padded_phase}-DISCUSS-CHECKPOINT.json` instead of discarding completed areas
- empty AskUserQuestion reply: retry once, then fall back to plain-text numbered choices
- power-mode finalize with low answer coverage still writes `CONTEXT.md`, but unanswered questions are preserved as deferred items and the user is warned
## Gate summary
- preflight: phase resolves; `.planning/` exists; blocking anti-patterns from `.continue-here.md` are understood; phase directory is writable
- success criteria: `CONTEXT.md` and `DISCUSSION-LOG.md` are committed, or power mode writes `QUESTIONS.json`/`QUESTIONS.html`; `canonical_refs` is present; checkpoint file is removed after successful context write; `.planning/STATE.md` is updated
- abort triggers: invalid phase; user cancels after existing-context/existing-plan gates; blocking anti-pattern cannot be understood from the handoff
## Retry / Resume
- checkpoint: `${phase_dir}/${padded_phase}-DISCUSS-CHECKPOINT.json` or `${phase_dir}/${padded_phase}-QUESTIONS.json` in `--power` mode
- resume command: `/kha-clarify-phase ${phase_number}` (`--power` if using the file-based question UI)
- idempotent: no — repeated runs can revise prior decisions and overwrite `CONTEXT.md` / `DISCUSSION-LOG.md`
- stall detection: completed-area count stops advancing in the checkpoint, or power-mode `refresh` leaves `answered` unchanged while `remaining > 0`From trevi00/khaness, MIT.
More from trevi00/khaness
- 0.494score
gsd-skill-promotion-runbook
trevi00
Operator runbook for promoting auto-detected skill candidates via cli/promote_skill.py — token gate, body authoring, atomic commit sequence, exit code recovery.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
kha-ai-integration-phase
trevi00
Spec-driven AI/LLM integration phase — produces a governed AI-SPEC.md design contract (domain + framework + failure-mode taxonomy + eval-coverage manifest)…
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
kha-debug
trevi00
Systematic debugging with persistent state across context resets.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
kha-audit-planning-health
trevi00
Diagnose planning directory health in read-only audit mode by default, or repair audited issues only with --mode repair --confirm after a recent audit report.
SkillCFreshness: C★ 1Claude Code +9 - 0.487score
kha-capture-seed
trevi00
Capture a forward-looking idea with trigger conditions — surfaces automatically at the right milestone
SkillCFreshness: C★ 1Claude Code +9 - 0.487score
kha-advance
trevi00
Automatically advance to the next logical step in the GSD workflow
SkillCFreshness: C★ 1Claude Code +9 - 0.487score
kha-archive-completed-phases
trevi00
Archive accumulated phase directories from completed milestones
SkillCFreshness: C★ 1Claude Code +9 - 0.487score
kha-audit-milestone
trevi00
Audit milestone completion against original intent before archiving
SkillCFreshness: C★ 1Claude Code +9 - 0.487score
kha-capture-note
trevi00
Zero-friction idea capture.
SkillCFreshness: C★ 1Claude Code +9 - 0.487score
kha-explore-idea
trevi00
Socratic ideation and idea routing — think through ideas before committing to plans
SkillCFreshness: C★ 1Claude Code +9 - 0.487score
kha-analyze-dependencies
trevi00
Analyze phase dependencies and suggest Depends on entries for ROADMAP.md
SkillCFreshness: C★ 1Claude Code +9 - 0.487score
kha-audit-uat-backlog
trevi00
Cross-phase audit of all outstanding UAT and verification items
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 21, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/trevi00/khaness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from trevi00
- 0.494score
gsd-skill-promotion-runbook
trevi00
Operator runbook for promoting auto-detected skill candidates via cli/promote_skill.py — token gate, body authoring, atomic commit sequence, exit code recovery.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
kha-debug
trevi00
Systematic debugging with persistent state across context resets.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
kha-audit-planning-health
trevi00
Diagnose planning directory health in read-only audit mode by default, or repair audited issues only with --mode repair --confirm after a recent audit report.
SkillCFreshness: C★ 1Claude Code +9 - 0.490score
kha-ai-integration-phase
trevi00
Spec-driven AI/LLM integration phase — produces a governed AI-SPEC.md design contract (domain + framework + failure-mode taxonomy + eval-coverage manifest)…
SkillCFreshness: C★ 1Claude Code +9 - 0.487score
kha-capture-todo
trevi00
Capture idea or task as todo from current conversation context
SkillCFreshness: C★ 1Claude Code +9 - 0.487score
kha-analyze-dependencies
trevi00
Analyze phase dependencies and suggest Depends on entries for ROADMAP.md
SkillCFreshness: C★ 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 kha-clarify-phase 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
kha-clarify-phase skill. Agent Mart. https://agentmart.dev/skills/trevi00-kha-clarify-phase (last updated 2026-10-24)