Menu
Extract creative intent from images into executable build specs. Activates on images + build intent, "image to mission", "i2m", or capturing visual energy in code/design.
| name | image-to-mission |
| description | Extract creative intent from images into executable build specs. Activates on images + build intent, "image to mission", "i2m", or capturing visual energy in code/design. |
Takes one or more images plus optional creator context and produces:
Activate when the user provides images AND expresses intent to:
DO NOT activate when the user:
Before building anything, enter observation mode:
Process each image through four layers:
Structure context into: process, intent, constraints, accidents, multipurpose. Extract the process insight — the key understanding about HOW it was made.
Synthesize observations + context into unified understanding. Find what neither source reveals alone.
Convert understanding to numerical parameters:
Translate parameters to target medium. Generate step-by-step instructions with philosophy notes.
Package everything for transmission. Validate self-containment.
| Format | When | Content |
|---|---|---|
| Direct build | Simple, single-medium output | Code/SVG + philosophy notes |
| Build spec | Medium complexity | Step-by-step instructions |
| Mission package | Complex, multi-component | Full vision_to_mission handoff |
| Transmission package | Cross-context work | JSON/Markdown bundle |
Code lives in src/vtm/image-to-mission/. Key modules:
Generate intelligence briefings for the planning dashboard. Use this skill whenever a request file appears in `.planning/console/inbox/pending/` whose `type` field starts with `intelligence.` (refresh_briefing, triage_finding, snapshot_diff, investigate_section, dismiss_finding). The skill reads the per-project KB at `.gsd/intelligence/intelligence.db`, synthesizes a briefing with a causal hypothesis + acknowledged uncertainty + confidence label and ranked moves, then writes the result back to the KB. Always trigger this skill for these request types — do not generate briefings manually.
Sketched Isotropic Gaussian Regularization primitive. Scalar loss matching the embedding distribution to a standard-normal target via Cramér-Wold slicing and the Epps-Pulley empirical characteristic function test. Port of rbalestr-lab/lejepa (MIT). Default-off in v1.49.571.
Adversarial spec-compliance PR review — cross-references diffs against approved specs, verifies runtime claims against source, detects competing PRs, audits scope/convention compliance. Use before merging.
Pick among candidate outputs (code, configs, plans) by running them on diverse inputs and clustering by behavioural fingerprint, rather than by textual aggregation or log-probability. Activates when an executor returns multiple plausible candidates that need disambiguation, when output-majority voting would be the default choice, or when reviewing generated code that has not yet been validated. The 2026 evidence (Semantic Voting, arxiv 2605.08680v1) is that any execution-based selector dominates output-majority voting by 19-52pp; sketch-generated inputs beat random fuzz by 11.3pp. Triggers: "pick the best candidate", "majority vote on code", "select from N samples", "validate the generated output", "behavioural verification".
Classify the information-need of a query and dispatch it to the appropriate retrieval or reasoning strategy. Use before read-side memory access, before multi-strategy retrieval, or any time you'd otherwise default to "one retriever for everything". Returns a strategy label, a token budget, and a retrieval depth so downstream handlers can be specialised. Backed by Pre-Route (arxiv 2605.10235v2) and MemFlow (arxiv 2605.03312v1), which together show LLMs possess latent routing ability elicitable via a structured prompt — and that externalising the routing decision improves small-model performance by ~2x. Triggers: "route this", "what strategy", "before retrieving", "intent classification", or any query whose ideal handling depends on what KIND of question it is.
Audit a skill by running a paired probe — the same task once with the skill loaded and once without — segment both traces into goal-directed phases, align phases, and emit a SIP report (surface anchoring, template copy, excess planning, task recovery, off-task artifact). Use whenever a skill is created, modified, or proposed for retirement. Pass-rate is BLIND to most skill effects: CTA (arxiv 2605.11946v1) shows a single skill can produce 522 measurable behavioural changes across 49 tasks while pass-rate moves only +0.3%. Triggers: "audit this skill", "is this skill helping", "retire skill", "before shipping skill", "behavioural impact of skill X", or any skill review event.
