freeform-summary-to-galaxy-template

SKILL.md

# freeform-summary-to-galaxy-template

Follow the procedure below and use the artifact/reference sections as the runtime contract.

## When To Use

- gxformat2 skeleton with per-step TODOs from a free-form summary and Galaxy design brief.

## Inputs

- Read artifact `freeform-summary`. Produced by `interview-to-freeform-summary`, `summarize-paper`. Free-form source summary emitted by summarize-paper or interview-to-freeform-summary; consulted while emitting placeholder steps.
- Read artifact `freeform-galaxy-interface`. Produced by `freeform-summary-to-galaxy-interface`. Galaxy interface brief from freeform-summary-to-galaxy-interface that pins workflow inputs, outputs, labels.
- Read artifact `freeform-galaxy-data-flow`. Produced by `freeform-summary-to-galaxy-data-flow`. Galaxy data-flow brief from freeform-summary-to-galaxy-data-flow that pins abstract operations and collection choices.
- Read artifact `iwc-comparison-notes`. Produced by `compare-against-iwc-exemplar`. Structural diff guidance from compare-against-iwc-exemplar (run on the design brief); steers the skeleton toward IWC-aligned structure before per-step authoring. Carries an inline gxformat2 excerpt of the nearest exemplar.
- Read artifact `iwc-exemplar-gxformat2`. Produced by `compare-against-iwc-exemplar`. Cleaned gxformat2 view of the nearest IWC exemplar's relevant subgraph from compare-against-iwc-exemplar; pattern-match the draft's input/collection shapes, map-over wiring, output promotion, and post-job actions against this concrete idiom. Absent when no nearest exemplar was found.
- Read artifact `open-requirements-ledger`. Produced by `advance-galaxy-draft-step`, `apply-galaxy-workflow-changeset`, `compare-against-iwc-exemplar`, `cwl-summary-to-galaxy-data-flow`, `cwl-summary-to-galaxy-interface`, `cwl-summary-to-galaxy-template`, `freeform-summary-to-galaxy-data-flow`, `freeform-summary-to-galaxy-interface`, `freeform-summary-to-galaxy-template`, `implement-galaxy-tool-step`, `interview-to-galaxy-workflow-changeset`, `nextflow-summary-to-galaxy-data-flow`, `nextflow-summary-to-galaxy-interface`, `nextflow-summary-to-galaxy-reference-data`, `nextflow-summary-to-galaxy-template`, `repair-galaxy-draft-topology`. Carried obligations ledger open-requirements-ledger: the run's open, resolved, and surrendered entries with their provenance. Absent on the first Mold of a run; start an empty one.

## Outputs

- Write artifact `galaxy-workflow-draft` as `galaxy-workflow-draft.gxwf.yml`. Format: `yaml`. Schema: galaxy-workflow-draft. gxformat2 draft (see galaxy-workflow-draft-format): topology fully resolved (workflow inputs, outputs, step set, edges); tool_id / state / tool_shed_repository and wrapper-determined port names may be TODO with free-text _plan_state / _plan_context / _plan_in / _plan_out per step for later implementation Molds.
- Write artifact `open-requirements-ledger` as `open-requirements.ledger.yml`. Format: `yaml`. Carried obligations ledger re-emitted by this step: entries it appended or closed updated, every other entry passed through with its provenance intact.

## Required Tools

- **`gxwf`** (gxwf). `npm install -g '@galaxy-tool-util/cli@^1.8.1'`.
  Ephemeral run: `npx --yes --package @galaxy-tool-util/cli@1.8.1 gxwf`.
  Check: `gxwf --help | grep -q draft-validate`.
  Docs: https://github.com/jmchilton/galaxy-tool-util-ts/tree/main/packages/cli

## Load Upfront

- `references/notes/galaxy-data-flow-draft-contract.md`: Research note copied verbatim into the bundle. Respect the handoff from the freeform-to-Galaxy interface and data-flow briefs to the gxformat2 skeleton. Use when: translating abstract nodes, unresolved tool needs, and placeholder transformations into template TODOs.
- `references/notes/galaxy-workflow-draft-format.md`: Research note copied verbatim into the bundle. Emit the gxformat2 draft superset: TODO tool_id, optional state / tool_shed_repository, and per-step _plan_state / _plan_context planning fields.
- `references/notes/open-requirements-ledger.md`: Research note copied verbatim into the bundle. Close the open entries the settled topology discharges, and append a blocking entry for any settled step whose declared output no wired input can supply — the computability gap gxwf validation cannot see, raised here rather than left for the per-step loop to hit.
- `references/schemas/galaxy-workflow-draft.schema.json`: Schema file copied verbatim into the bundle. Output contract: the emitted gxformat2 draft conforms to galaxy-workflow-draft. Cast bundles the JSON Schema so the skill carries its output shape alongside the draft-validate CLI checks.

## Load On Demand

- `references/cli/draft-validate.json`: CLI command reference packaged as a sidecar. Validate the emitted draft against draft-contract rules (sentinel form, topology, _plan_* placement) before handing off. Use when: after writing or modifying the draft workflow file.
- `references/patterns/galaxy-collection-patterns.md`: Pattern note copied verbatim into the bundle. Use corpus-grounded collection pattern guidance for unresolved skeleton steps. Use when: adding TODO steps for collection cleanup, reshaping, relabeling, identifier synchronization, or collection-tabular bridges.
- `references/patterns/galaxy-conditionals-patterns.md`: Pattern note copied verbatim into the bundle. Use corpus-grounded conditional pattern guidance for unresolved skeleton steps. Use when: adding TODO steps for optional steps, gating on non-empty results, routing between alternative outputs, or transform-or-pass-through branches.
- `references/patterns/galaxy-interval-patterns.md`: Pattern note copied verbatim into the bundle. Use corpus-grounded genomic-interval pattern guidance for unresolved skeleton steps. Use when: adding TODO steps for interval overlap, merge, coverage, windowing, masking, or set-algebra on coordinate features.
- `references/patterns/galaxy-tabular-patterns.md`: Pattern note copied verbatim into the bundle. Use corpus-grounded tabular pattern guidance for unresolved skeleton steps. Use when: adding TODO steps for tabular filtering, projection, joins, aggregation, text-processing recipes, or tabular-collection bridges.
- `references/notes/galaxy-collection-semantics.md`: Research note copied verbatim into the bundle. Preserve Galaxy collection typing and map-over/reduction semantics in the gxformat2 skeleton. Use when: creating workflow inputs, outputs, and placeholder connections involving collections.
- `references/notes/galaxy-collection-semantics.yml`: Companion file copied verbatim into the bundle. Sibling of `references/notes/galaxy-collection-semantics.md`; read it where that note directs.
- `references/notes/galaxy-workflow-comments.md`: Research note copied verbatim into the bundle. Group the settled step set into titled stage frames (the gxformat2 `comments:` array) so the skeleton carries the analysis-stage narrative IWC authors annotate by hand. Schema-legal and optional. Use when: after topology is settled and the skeleton can be partitioned into named analysis stages (inputs, per-stage step clusters, parameter-derivation knots, visualization/outputs).
- `references/notes/galaxy-workflow-testability-design.md`: Research note copied verbatim into the bundle. Choose stable workflow input/output labels, testable checkpoint outputs, and fixture-compatible workflow interfaces while drafting the skeleton. Use when: the template decides workflow inputs, workflow outputs, promoted checkpoints, or collection output identifiers that future tests will need to address.

## Validation

- Validate `galaxy-workflow-draft.gxwf.yml` for artifact `galaxy-workflow-draft` against the galaxy-workflow-draft schema when a validator is available.

## Procedure

Read the original free-form source artifact if present, the free-form summary Markdown document, and the freeform-to-Galaxy interface and data-flow briefs. Emit a gxformat2 skeleton with workflow inputs, workflow outputs, placeholder steps, rough connections, and TODO slots for later implementation skills.

The free-form summary does not have a concrete schema yet; treat it as Markdown. Treat the prior-step index as the working context: source transcript or paper, free-form summary, freeform-to-Galaxy interface and data-flow briefs, and any open questions carried forward.

Topology is this skill's job to settle. The output must be concrete gxformat2: workflow inputs with their final collection shapes and formats, workflow outputs, the step set, the producer→consumer edge graph, branches, and `when:` guards are all decided here. The upstream freeform-to-Galaxy interface and data-flow briefs guide those decisions, but if they hedge or leave a topology choice open, this skill makes the call from source evidence, IWC exemplars, and pattern pages — never emit a topology `TODO`. Wrapper resolution, by contrast, is **evidence-gated, not source-gated**: resolve each tool step to the tier its evidence supports — **Resolved** (fully concrete, no `_plan_*`), **Identity-pinned** (concrete `tool_id`, parameters and changeset left to the per-step skill), or **Deferred** (`tool_id: TODO`) — as defined in galaxy-workflow-draft-format. Capture whatever you defer in the `_plan_*` family (`_plan_state`, `_plan_context`, `_plan_in`, `_plan_out`) so the per-step skill has the source evidence and constraints it needs.

Source tendency: free-form sources rarely name tools, so steps land in **Deferred** more often than nf-core or CWL — but a free-form source that *does* name a specific tool/version with evidence hardens to the matching tier, and a corpus-confirmed utility wrapper (interval/tabular/collection op) is not deferred just because the surrounding prose is informal. When deferring a domain tool, cite the originating paper section, interview answer, figure, or supplementary table in `_plan_context`, and record vague intent in `_plan_state` ("default settings", "stranded reverse if mentioned, else unstranded") so the per-step skill knows the evidence ceiling.

Before handing off, sanity-check that each step is computable from what feeds it. Once the step set is settled, re-read it and ask, for each step, whether the operation its intent implies can actually be produced from the inputs you wired. The connection graph only knows that ports connect — not what each port is supposed to *contain* — so an output that needs evidence no input carries will validate fine and still be impossible to implement. Where you spot that gap, don't leave it implicit: wire (or add) the step that supplies the missing input, or record the unmet need plainly in `_plan_state` so the per-step skill or a reviewer can act on it rather than discover it late.

Things worth a second look:

- an output column or field that no wired input carries;
- an aggregate or summary whose grouping key isn't present upstream;
- a filter or threshold whose criterion isn't produced by any input;
- a join whose key doesn't exist on both sides;
- a step whose `_plan_*` promises more than its `in:` ports can supply;
- if classification step, is that classification/enumeration possible only from inputs.

Optionally, once topology is settled, group the step set into titled stage frames via the gxformat2 `comments:` array (one frame per analysis stage, `contains_steps:` populated, color decorative) — see galaxy-workflow-comments for the convention.

Before handing off, check each settled step is computable from what feeds it. The connection graph knows that ports connect, not what they carry — so a declared output that needs evidence no wired input supplies will validate yet can't be implemented. Where you find that gap, wire (or add) the producer; if you can't, record the vague intent in `_plan_state` and append a **blocking** entry to the open-requirements-ledger naming the step, the uncomputable output, and the missing evidence, so the per-step loop or repair-galaxy-draft-topology acts on it rather than discovering it late.

Output shape is gxformat2 with wrapper-tier relaxations and `_plan_state` / `_plan_context` / `_plan_in` / `_plan_out` per tool step — see galaxy-workflow-draft-format. Refinement open work for those planning fields lives in `refinement.md`.

## Feedback Mode

- Feedback mode is off unless the caller explicitly enables `--feedback` or supplies a feedback-ledger path.
- When enabled, read `_feedback.md` before doing the work and use its registered `foundry-feedback.ledger.yml` protocol.
- Preserve harness-owned run and phase state. Append only concrete observations about a canonical Foundry source asset or a related project that this run showed to be at fault; do not put ordinary workflow requirements in this ledger.
- Before reporting completion, make one explicit pass over the work you just did. Do not ask yourself whether anything was unclear — recall what happened: where you guessed at something the instructions should have settled, needed information this bundle does not carry, hit an instruction that contradicted another or contradicted the artifacts in front of you, used a packaged reference that did not cover your case, or did something the procedure never describes.
- Append an entry for each such event that clears the protocol's bar. If none do, append nothing and report `no feedback` explicitly. Silence and a clean pass are not the same thing, and nothing downstream can tell them apart unless you say which one it was.
- Pass the same ledger path to any subagent used for this work, and merge updates serially so one writer cannot overwrite another.

## Runtime Notes

- Do not read Foundry source files at runtime; use only files packaged in this skill bundle and user-supplied artifacts.
- Preserve declared artifact filenames unless the user or harness supplies explicit paths.
- Carry unresolved assumptions into the output artifact instead of silently inventing missing source evidence.