feat(skills): creating-actions — guided authoring of reusable Maestro actions#272
Merged
Conversation
… actions
New skill walking the agent through the full action-authoring contract:
inventory-dedup scan before authoring, creation-path choice (recorder /
direct YAML / maestro_generate), selector grounding, a required ASCII
flow diagram (screens + transitions annotated with exact testIDs and
${PARAMS}, embedded in the YAML header with glyph-first lines so
parseM7Header cannot misread a diagram line as metadata — a bare
"# status: ..." line demonstrably overwrites the field), the M7 header
contract, pre-replay validation, and replay-to-promote via
cdp_run_action.
Ships references/m7-header-reference.md (full field glossary, parser
behavior, lifecycle, failure codes) and examples/add-product-to-cart.yaml
— validated end-to-end against the real toolchain: parseM7Header (all 11
fields round-trip with the diagram embedded), learned-actions.mjs
(inventory lists exact metadata + synthesizes the replay command), and
Maestro check_flow_syntax (valid).
Skill tested RED→GREEN with subagents: baseline run produced no diagram
and no dedup scan; with the skill loaded, a confined agent followed all
steps and produced a toolchain-clean action on an unseen flow.
Routed from using-rn-dev-agent (decision tree + skill map, count 7→8)
and cross-linked from rn-testing's M7 section; registered in
plugin.json; changeset: rn-dev-agent-plugin minor.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: ee868f2588
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Codex review on PR #272 (P2, verified real): both handlers accept params (GH #116 — threaded to maestro as -e KEY=VALUE on first attempt AND post-repair retry, run-action.ts:107/258/447), but the zod registrations omitted the field. zod strips unknown keys by default, so parameter bindings were silently dropped at the tool-call layer and a parameterised action failed at runtime with unset ${VAR} placeholders — breaking the call shape the new creating-actions skill (and the pre-existing commands/run-action.md) document. TDD: pr-272-params-schema-wiring.test.js pins both registrations (failed before the schema fix, passes after). Key-format validation (/^[A-Z_][A-Z0-9_]*$/) remains in the maestro_run handler. Full suite 1915/1915. dist rebuilt. Changeset: rn-dev-agent-cdp minor. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 18ac6423da
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| ## Step 5 — Validate Before First Replay | ||
|
|
||
| 1. **Header parses + inventory lists it**: re-run the Step-0 command with `--filter <id>` — confirm `intent`, `tags`, `mutates`, `status` come back exactly as written (not `?`). This also proves the embedded diagram didn't corrupt the header. | ||
| 2. **Placeholder coverage**: `grep -o '\${[A-Z_]*}' <file>` over the steps ↔ `# params` list, both directions. |
There was a problem hiding this comment.
For actions that use allowed digit-bearing params such as ${PRODUCT_ID2} or ${OTP_6}, this validation command misses the placeholder because [A-Z_]* cannot consume digits before the closing brace. The contract above and the inventory scanner both allow [A-Z_][A-Z0-9_]*, so Step 5 can incorrectly pass while leaving a required binding out of # params, and the first replay then runs with an unset placeholder. Use the same full param regex here as the scanner/contract.
Useful? React with 👍 / 👎.
Lykhoyda
added a commit
that referenced
this pull request
Jun 11, 2026
…278) * feat(agents): all agents on opus; rn-code-architect on fable rn-tester, rn-code-explorer, rn-code-reviewer move sonnet → opus; rn-debugger already opus; rn-code-architect moves opus → fable (claude-fable-5 — the top tier, fitting the architect's role as the single deep-reasoning blueprint step in the /rn-feature-dev pipeline, where it runs 1-2× vs the explorers'/reviewers' 2-3× parallel fans). Model-tier prose synced: using-rn-dev-agent agent-map tables + decision tree, docs-site agent pages + index tables. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor(skills): efficiency pass — dedup, trigger-only descriptions, stale-claim fixes - rn-feature-development (5,076→3,962 words, −22%): Phase 8 defers to commands/proof-capture.md as the single protocol source (was a ~1,800-word drifting duplicate) with pipeline deltas on top; 8 per-phase evaluator lines collapsed to one core principle; description rewritten trigger-only per the CSO rule (workflow-summarizing descriptions make the body get skipped). - using-rn-dev-agent (2,065→1,825): HELPERS_NOT_INJECTED recovery moved to rn-debugging (its owner) with routing pointers; surface counts fixed (76 tools / 14 commands, were 64/16). - rn-testing: M7 section slimmed to a 5-key table + creating-actions pointer; heading preserved for citations. - rn-best-practices / rn-setup: trigger-only descriptions (dropped the rot-prone 118-rule inventory; added failure-phrase triggers). - Correctness: maestro_run/cdp_run_action params claims updated for #272 (two files said "no -e pass-through"); run-action.md citation fixed ("Maestro Flow Standards" → real heading); smoke-test standardized on cdp_run_action (RunRecord + promotion), plain maestro_run reserved for the on-camera replay; <test-app> placeholder defined. Verified: frontmatter parses on all 8 skills; zero stale-claim greps; all cross-references resolve; confined-subagent retrieval test answered the full Phase 8 chain (skill → proof-capture → creating-actions) concretely — its 4 findings (stale Step-1.4 refs, smoke-test contradiction, Steps-range skipping the diagram, undefined placeholder) are fixed in this commit. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
New
creating-actionsskill (the plugin's 8th) that facilitates creating new actions — replayable Maestro flows under.rn-agent/actions/— with a required ASCII flow-diagram design step mapping screens/transitions to exact testIDs/selectors before any YAML is written.The skill codifies the full authoring contract that previously lived scattered across
rn-testing,run-action.md, and the bridge source:learned-actions.mjsbefore authoring; extend a near-duplicate instead of forking itcdp_record_test_*) vs direct YAML vsmaestro_generatecdp_component_tree/device_snapshot/ source grep — never invented[RouteName]boxes,│-arrows labeled with exact selectors and${PARAMS}, one assertion anchor per screen; embedded in the YAML header so each action documents itselfstatus: experimentalat creation)cdp_run_action(never hand-setactive; sidecar is never hand-written)Ships with
references/m7-header-reference.md(full field glossary, parser behavior, lifecycle transitions, failure codes) andexamples/add-product-to-cart.yaml(worked example with embedded diagram).Why the diagram rules are strict (grounded in parser reality, not style)
parseM7Headertrims each comment line and last-wins kv-parses it: an adversarial probe confirmed a diagram line# status: shows spinnersilently overwrites the action'sstatus. Hence: every diagram line's content starts with a non-letter glyph ([,│,▼).learned-actions.mjsextracts${VAR}params from the whole file text, comments included (learned-actions.mjs:115) — so the skill pins down exactly where${...}may appear (steps + diagram mirroring steps; bare names in prose).Verification
parseM7Headerround-trips all 11 M7 fields with the diagram embedded (incl.produces+expectedRouteSequence);learned-actions.mjslists exact metadata and synthesizes the replay command with exactly one-e; Maestrocheck_flow_syntax→ valid.status-overwrite hazard the skill guards against.Wiring
plugin.json(skills7→8)using-rn-dev-agent(new decision-tree branch + skill-map row, count bump)rn-testing's M7 sectionrn-dev-agent-pluginminor🤖 Generated with Claude Code