Skip to content

stevesolun/ctx / docs

skill-router

Flagged

Repo-aware recommendation manager for ctx. Scans the active repository, identifies stack and workflow signals, recommends a capped set of skills, agents, and MCP servers, and unloads helpers that no longer match the current work after user confirmation. Harnesses are recommended by the custom-model onboarding flow or loop adapters and then attach to the same recommendation layer.

FileKindSize
SKILL.mdskill md9.3 KB
assets/javascripts/catalog.jsscript2.5 KB
assets/javascripts/repo-stats-refresh.jsscript3.2 KB
backup-hook-install.mdmarkdown9.2 KB
catalog.mdmarkdown10.3 KB
ctx-fit/ARCHITECTURE_CANDIDATES.mdmarkdown12.9 KB
ctx-fit/ARCHITECTURE_GAP_ANALYSIS.mdmarkdown10.7 KB
ctx-fit/CTX_AUDIT.mdmarkdown11.6 KB
ctx-fit/CURRENT_STATE.mdmarkdown16.3 KB
ctx-fit/DECISIONS.mdmarkdown15.7 KB
ctx-fit/GOOD_FIRST_ISSUES.mdmarkdown20.6 KB
ctx-fit/IMPLEMENTATION_TRACKER.mdmarkdown697 B
ctx-fit/MAP.mdmarkdown7.8 KB
ctx-fit/PRD.mdmarkdown9.7 KB
ctx-fit/STATE.mdmarkdown60.9 KB
ctx-fit/milestones/M1_SPIKE_FRICTION_LOG.mdmarkdown5.5 KB
ctx-fit/milestones/MILESTONE_00_AUDIT.mdmarkdown5.1 KB
ctx-fit/planned_tasks.mdmarkdown17.7 KB
dashboard.mdmarkdown24.7 KB
enterprise-readiness-review.mdmarkdown8.7 KB
entity-onboarding.mdmarkdown18.0 KB
harness/attaching-to-hosts.mdmarkdown16.2 KB
harness/clean-host-contract.mdmarkdown4.5 KB
harness/loopflow-adapter-demo.mdmarkdown11.1 KB
huggingface-publish.mdmarkdown3.3 KB
index.mdmarkdown22.4 KB
knowledge-graph.mdmarkdown22.7 KB
marketplace-registry.mdmarkdown4.0 KB
memory-anchor.mdmarkdown2.7 KB
plans/ctx-agent-reviewer-workbench.mdmarkdown12.4 KB
plans/unified-capability-engine.mdmarkdown59.0 KB
qa/dashboard-user-story-status.csvother26.0 KB
qa/feature-user-story-status.csvother92.5 KB
research/context-engineering-guidance-audit.mdmarkdown10.4 KB
services/macos/com.claude.backup.watchdog.plistother1.7 KB
services/systemd/claude-backup-watchdog.serviceother1.3 KB
skill-lifecycle-and-dashboard.mdmarkdown6.2 KB
skill-quality-install.mdmarkdown6.2 KB
skill-router/index.mdmarkdown2.5 KB
skill-stack-matrix.mdmarkdown5.5 KB
skills-health.mdmarkdown3.5 KB
stack-signatures.mdmarkdown6.2 KB
telemetry.mdmarkdown24.7 KB
threat-model.mdmarkdown15.0 KB
toolbox/behavior-miner.mdmarkdown2.6 KB
toolbox/configuration.mdmarkdown4.0 KB
toolbox/council-runner.mdmarkdown2.4 KB
toolbox/hooks.mdmarkdown2.6 KB
toolbox/index.mdmarkdown3.0 KB
toolbox/intent-interview.mdmarkdown3.0 KB
toolbox/starters.mdmarkdown3.0 KB
toolbox/templates/docs-review.jsonconfig599 B
toolbox/templates/fresh-repo-init.jsonconfig533 B
toolbox/templates/refactor-safety.jsonconfig634 B
toolbox/templates/security-sweep.jsonconfig636 B
toolbox/templates/ship-it.jsonconfig676 B
toolbox/verdicts.mdmarkdown4.0 KB

toolbox/intent-interview.md

View on GitHub
# Intent interview

[`src/intent_interview.py`](https://github.com/stevesolun/ctx/blob/main/src/intent_interview.py)
bootstraps your toolbox set via a short, skippable interview.

The slash command `/toolbox init` is a thin wrapper; see
[`.claude/commands/toolbox-init.md`](https://github.com/stevesolun/ctx/blob/main/.claude/commands/toolbox-init.md).

## Flow

1. **Detect repo state** — is this a git repo? Any commits? What languages?
2. **Load behavior profile** — read `~/.claude/user-profile.json` for any
   mined suggestions.
3. **Ask up to three questions**:
   - Which starter toolboxes to activate.
   - Which miner suggestions to accept (if any).
   - Default analysis mode for new toolboxes.
4. **Persist** — write chosen toolboxes to `~/.claude/toolboxes.json`
   (only when `--apply` is passed).

Any prompt can be skipped with the word `skip`.

## Repo state detection

```python
@dataclass(frozen=True)
class RepoState:
    is_git: bool
    commit_count: int
    languages: dict[str, int]     # extension → file count
    markers: dict[str, str]       # marker file → language
    has_toolbox_config: bool

    @property
    def is_blank(self) -> bool:
        # True when the repo has effectively nothing to analyze yet.
        return not self.is_git or self.commit_count == 0 or (
            not self.languages and not self.markers
        )
```

Language scoring uses both extensions (`.py`, `.ts`, …) and marker files
(`pyproject.toml`, `Cargo.toml`, `Dockerfile`, …). Marker files bump the
score by 5 to reflect that they declare intent more strongly than a
stray extension match.

## Usage

```bash
# Default: interactive, dry-run (no write)
python -m intent_interview init

# Detect state only
python -m intent_interview detect

# Preset flows (no prompts)
python -m intent_interview init --preset blank --apply
python -m intent_interview init --preset existing --apply
python -m intent_interview init --preset docs-heavy --apply
python -m intent_interview init --preset security-first --apply

# Fully structured (CI / scripted setup)
python -m intent_interview init \
  --non-interactive \
  --starters ship-it,security-sweep \
  --suggestions 1,2 \
  --analysis dynamic \
  --apply
```

## Presets

| Preset | Starters | Default scope |
|---|---|---|
| `blank` | ship-it, security-sweep, fresh-repo-init | dynamic |
| `existing` | ship-it, refactor-safety | dynamic |
| `docs-heavy` | docs-review | diff |
| `security-first` | security-sweep | full |

## Skip semantics

- Typing `skip` at any prompt short-circuits the whole interview: no
  starters activated, no suggestions accepted, analysis mode unchanged.
- `--skip` on the CLI is the non-interactive equivalent.

## Exit codes

- `0` — success; JSON payload printed on stdout.
- non-zero — unrecoverable error (unknown preset, malformed args).

## Related

- [Starter toolboxes](starters.md) — the five bundles the interview can activate.
- [Behavior miner](behavior-miner.md) — source of the suggestions the interview offers.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall