@martinffx/atelier 1.2.2 → 1.3.0

package/skills/oracle-debug/SKILL.md

@@ -0,0 +1,218 @@
+---
+name: oracle-debug
+description: >
+  Disciplined debugging methodology. Triggers on bug reports, test failures, "debug this",
+  "diagnose this", unexpected behavior, build failures, integration issues, or performance
+  regressions. Always find root cause before attempting any fix.
+user-invocable: true
+---
+
+# Oracle Debug
+
+Random fixes waste time and create new bugs. Quick patches mask underlying issues.
+
+**Core principle:** find root cause before attempting any fix. Symptom fixes are failure.
+
+**Violating the letter of this process is violating the spirit of debugging.**
+
+## The Iron Law
+
+```
+NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
+```
+
+If you haven't completed Phase 1, you cannot propose fixes.
+
+## When to Use
+
+Use for any technical issue:
+
+- Test failures
+- Bugs in production
+- Unexpected behavior
+- Performance regressions
+- Build or integration failures
+- Intermittent failures
+
+**Use this especially when:**
+
+- Under time pressure
+- "Just one quick fix" seems obvious
+- You've already tried multiple fixes
+- The previous fix didn't work
+- You don't fully understand the issue
+
+## The Four Phases
+
+You must complete each phase before proceeding to the next.
+
+---
+
+## Phase 1 — Root Cause Investigation
+
+**Before attempting any fix:**
+
+Use the project's domain glossary and ADRs to build a clear mental model of the
+relevant modules before tracing.
+
+1. **Read error messages carefully.** Read the full stack trace, line numbers, file paths, and error codes. Don't skip warnings.
+2. **Build a fast feedback loop.** If you don't have a fast, deterministic, pass/fail signal for the bug, no amount of code-reading will save you. Spend disproportionate effort here.
+
+   Try these in order:
+   - Failing test at the seam that reaches the bug
+   - Curl / HTTP script against a running dev server
+   - CLI invocation with fixture input
+   - Headless browser script (Playwright/Puppeteer)
+   - Replay a captured trace (network payload, event log)
+   - Throwaway harness (minimal subset of the system)
+   - Property/fuzz loop for "sometimes wrong" bugs
+   - Bisection harness (e.g., `git bisect run`)
+   - Differential loop (old vs new version)
+   - HITL bash script (last resort — structure the human clicks)
+
+   Iterate on the loop: make it faster, sharper, and more deterministic. A 30-second flaky loop is barely better than no loop.
+
+3. **Reproduce the bug.** Run the loop. Confirm the failure matches what the user described, is reproducible across runs, and the exact symptom is captured.
+4. **Check recent changes.** `git diff`, recent commits, new dependencies, config changes, environment differences.
+5. **Trace data flow.** In multi-component systems, add diagnostic instrumentation at each boundary:
+   - Log what data enters each component
+   - Log what data exits each component
+   - Verify environment/config propagation
+   - Check state at each layer
+
+   Run once to gather evidence, then narrow to the failing component.
+6. **Trace backward through the call stack.** Where does the bad value originate? What called this with the bad value? Trace up until you find the source. Fix at the source, not at the symptom.
+
+### Non-deterministic bugs
+
+The goal is not a clean repro but a **higher reproduction rate**. Loop the trigger 100×, parallelize, add stress, narrow timing windows, inject sleeps. A 50% flake is debuggable; 1% is not — keep raising the rate until it is.
+
+### When you genuinely cannot build a loop
+
+Stop and say so explicitly. Ask the user for:
+
+- Access to the environment that reproduces it
+- A captured artifact (HAR, log dump, core dump, screen recording)
+- Permission to add temporary production instrumentation
+
+**Do not proceed to Phase 2 without a loop you believe in.**
+
+---
+
+## Phase 2 — Pattern Analysis
+
+Find the pattern before fixing.
+
+1. **Find working examples.** Locate similar working code in the same codebase.
+2. **Compare against references.** If implementing a known pattern, read the reference implementation completely.
+3. **Identify differences.** List every difference between working and broken, however small.
+4. **Understand dependencies.** What components, config, settings, and assumptions does this code rely on?
+
+---
+
+## Phase 3 — Hypothesis and Testing
+
+Use the scientific method.
+
+1. **Generate 3–5 ranked hypotheses.** Single-hypothesis generation anchors on the first plausible idea. Each hypothesis must be falsifiable: state the prediction it makes. **Show the ranked list to the user before testing** — they often have domain knowledge that re-ranks instantly.
+
+   > Format: "If `<X>` is the cause, then `<changing Y>` will make the bug disappear / `<changing Z>` will make it worse."
+
+2. **Test one variable at a time.** Make the smallest possible change to test the hypothesis.
+3. **Instrument mapped to predictions.** Each probe must map to a specific prediction. Prefer a debugger/REPL over logs; prefer targeted logs at boundaries over "log everything and grep".
+
+   **Tag every debug log** with a unique prefix, e.g. `[DEBUG-a4f2]`. Cleanup becomes a single grep.
+
+4. **Performance regressions.** Logs are usually wrong. Establish a baseline measurement (timing harness, profiler, query plan), then bisect. Measure first, fix second.
+
+5. **When you don't know, say so.** Don't pretend. Ask for help or research more.
+
+---
+
+## Phase 4 — Implementation
+
+Fix the root cause, not the symptom.
+
+1. **Create a failing test case.** The simplest possible reproduction. MUST exist before the fix.
+
+   A **correct seam** is one where the test exercises the real bug pattern as it occurs at the call site. If the only available seam is too shallow, note that the codebase architecture is preventing the bug from being locked down.
+
+2. **Implement a single fix.** Address the root cause. One change at a time. No "while I'm here" improvements. No bundled refactoring.
+3. **Verify the fix.** Does the test pass? Do other tests still pass? Does the original repro no longer reproduce?
+4. **If the fix doesn't work:**
+   - STOP
+   - Count the failed fix attempts
+   - If < 3: return to Phase 1 with the new information
+   - If ≥ 3: **question the architecture**. Pattern problems, hidden coupling, and shared state that each fix reveals are signs of a wrong pattern. Discuss with the user before attempting Fix #4.
+
+### Cleanup + post-mortem
+
+Before declaring done:
+
+- [ ] Original repro no longer reproduces (re-run Phase 1 loop)
+- [ ] Regression test passes (or absence of seam is documented)
+- [ ] All `[DEBUG-...]` instrumentation removed
+- [ ] Throwaway prototypes deleted or moved to a clearly-marked debug location
+- [ ] The correct hypothesis is stated in the commit / PR message
+- [ ] You asked: "What would have prevented this bug?"
+
+---
+
+## Red Flags — Stop and Return to Phase 1
+
+If you catch yourself thinking:
+
+- "Quick fix for now, investigate later"
+- "Just try changing X and see if it works"
+- "Add multiple changes, run tests"
+- "Skip the test, I'll manually verify"
+- "It's probably X, let me fix that"
+- "I don't fully understand but this might work"
+- "Pattern says X but I'll adapt it differently"
+- "One more fix attempt" (after 2+ failures)
+- Each fix reveals a new problem in a different place
+
+All of these mean: stop. Return to Phase 1.
+
+## Common Rationalizations
+
+| Excuse | Reality |
+|---|---|
+| "Issue is simple, don't need process" | Simple issues have root causes too. |
+| "Emergency, no time for process" | Systematic debugging is faster than thrashing. |
+| "Just try this first, then investigate" | First fix sets the pattern. Do it right from the start. |
+| "I'll write the test after confirming the fix" | Untested fixes don't stick. Test first proves the bug. |
+| "Multiple fixes at once saves time" | Can't isolate what worked. Causes new bugs. |
+| "Reference too long, I'll adapt the pattern" | Partial understanding guarantees bugs. |
+| "I see the problem, let me fix it" | Seeing symptoms ≠ understanding root cause. |
+
+## Quick Reference
+
+| Phase | Key Activities | Success Criteria |
+|---|---|---|
+| 1. Root cause | Read errors, build loop, reproduce, trace data flow | Understand what and why |
+| 2. Pattern analysis | Find working examples, compare | Identify differences |
+| 3. Hypothesis | Form theory, test minimally | Confirmed or new hypothesis |
+| 4. Implementation | Failing test, single fix, verify | Bug resolved, tests pass |
+
+## Debug Summary
+
+After each session, summarize:
+
+```
+## Debug Summary
+
+**Problem:** [One sentence]
+**Root Cause:** [What actually was wrong]
+**Fix:** [How you fixed it]
+**Verification:** [Test results]
+**Prevention:** [Regression test added? Architectural finding?]
+```
+
+## References
+
+- **Language-specific tools** → `references/language-tools.md`
+- **Common bug patterns** → `references/bug-patterns.md`
+- **Logging & techniques** → `references/techniques.md`
+
+Structure inspired by [obra/superpowers systematic-debugging](https://github.com/obra/superpowers).

package/skills/{code-debug → oracle-debug}/references/bug-patterns.md

@@ -1,6 +1,6 @@
 # Common Bug Patterns
 
-Quick reference for recognising and fixing recurring bug categories.
+Quick reference for recognizing and fixing recurring bug categories.
 
 ---
 
@@ -45,7 +45,7 @@ const name = user.profile.name;
 
 ## Logic Errors
 
-**Symptoms:** Wrong output, wrong behaviour
+**Symptoms:** Wrong output, wrong behavior
 
 **Debug approach:**
 1. Trace through the logic manually
@@ -68,4 +68,4 @@ const name = user.profile.name;
 2. Identify hot paths
 3. Optimize the bottleneck
 
-**See also:** Phase 4 "Perf branch" in SKILL.md for the disciplined approach.
+**See also:** Phase 3 "Performance regressions" in SKILL.md for the disciplined approach.

package/skills/oracle-domain-modelling/SKILL.md

@@ -0,0 +1,84 @@
+---
+name: oracle-domain-modelling
+description: >
+  Build and sharpen a project's domain model. Use when the user wants to pin down
+  domain terminology or a ubiquitous language, record an architectural decision,
+  or when another skill needs to maintain the domain model.
+user-invocable: false
+---
+
+# Domain Modelling
+
+Actively build and sharpen the project's domain model as you design. This is the *active* discipline — challenging terms, inventing edge-case scenarios, and writing the glossary and decisions down the moment they crystallise. (Merely *reading* `CONTEXT.md` for vocabulary is not this skill — that's a one-line habit any skill can do. This skill is for when you're changing the model, not just consuming it.)
+
+## File structure
+
+Most repos have a single context:
+
+```
+/
+├── CONTEXT.md
+├── docs/
+│   └── adr/
+│       ├── 0001-event-sourced-orders.md
+│       └── 0002-postgres-for-write-model.md
+└── src/
+```
+
+If a `CONTEXT-MAP.md` exists at the root, the repo has multiple contexts. The map points to where each one lives:
+
+```
+/
+├── CONTEXT-MAP.md
+├── docs/
+│   └── adr/                          ← system-wide decisions
+├── src/
+│   ├── ordering/
+│   │   ├── CONTEXT.md
+│   │   └── docs/adr/                 ← context-specific decisions
+│   └── billing/
+│       ├── CONTEXT.md
+│       └── docs/adr/
+```
+
+Create files lazily — only when you have something to write. If no `CONTEXT.md` exists, create one when the first term is resolved. If no `docs/adr/` exists, create it when the first ADR is needed.
+
+## During the session
+
+### Challenge against the glossary
+
+When the user uses a term that conflicts with the existing language in `CONTEXT.md`, call it out immediately:
+
+> "Your glossary defines 'cancellation' as X, but you seem to mean Y — which is it?"
+
+### Sharpen fuzzy language
+
+When the user uses vague or overloaded terms, propose a precise canonical term:
+
+> "You're saying 'account' — do you mean the Customer or the User? Those are different things."
+
+### Discuss concrete scenarios
+
+When domain relationships are being discussed, stress-test them with specific scenarios. Invent scenarios that probe edge cases and force the user to be precise about the boundaries between concepts.
+
+### Cross-reference with code
+
+When the user states how something works, check whether the code agrees. If you find a contradiction, surface it:
+
+> "Your code cancels entire Orders, but you just said partial cancellation is possible — which is right?"
+
+### Update CONTEXT.md inline
+
+When a term is resolved, update `CONTEXT.md` right there. Don't batch these up — capture them as they happen. Use the format in [references/CONTEXT-FORMAT.md](./references/CONTEXT-FORMAT.md).
+
+`CONTEXT.md` should be totally devoid of implementation details. Do not treat `CONTEXT.md` as a spec, a scratch pad, or a repository for implementation decisions. It is a glossary and nothing else.
+
+### Offer ADRs sparingly
+
+Only offer to create an ADR when all three are true:
+
+1. **Hard to reverse** — the cost of changing your mind later is meaningful
+2. **Surprising without context** — a future reader will wonder "why did they do it this way?"
+3. **The result of a real trade-off** — there were genuine alternatives and you picked one for specific reasons
+
+If any of the three is missing, skip the ADR. Use the format in [references/ADR-FORMAT.md](./references/ADR-FORMAT.md).

package/skills/oracle-grill-me/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: oracle-grill-me
+description: >
+  Grill the user relentlessly about a plan, decision, or idea, maintaining the project's
+  domain model (CONTEXT.md, ADRs) as decisions crystallise. Use when the user wants to
+  stress-test their thinking, or uses any 'grill' trigger phrases.
+user-invocable: true
+---
+
+# Grill Me
+
+Interview me relentlessly about every aspect of this until we reach a shared understanding. Walk down each branch of the decision tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
+
+Ask the questions one at a time, waiting for feedback on each question before continuing. Asking multiple questions at once is bewildering.
+
+If a *fact* can be found by exploring the environment (filesystem, tools, etc.), look it up rather than asking me. The *decisions*, though, are mine — put each one to me and wait for my answer.
+
+Do not act on it until I confirm we have reached a shared understanding.
+
+Run this session using the `oracle-domain-modelling` skill.

package/skills/spec-brainstorm/SKILL.md

@@ -2,8 +2,9 @@
 name: spec-brainstorm
 description: >
   Conversational design workshop for new features. Interviews the human one question
-  at a time, explores 2-3 approaches with trade-offs, then produces a focused spec.
-  Combines requirements discovery with codebase research and architecture design.
+  at a time, explores 2-3 approaches with trade-offs, and presents the design
+  section by section for approval before writing the spec. Combines requirements
+  discovery with codebase research and architecture design.
   Use when the user says "create a spec", "design this feature", "let's brainstorm",
   "what should we build", or at the start of any feature/refactor/complex-bug workflow.
 user-invocable: true
@@ -14,13 +15,14 @@ argument-hint: <topic or feature description>
 
 Conversational design workshop that produces a focused, reviewed spec.
 
-One question at a time. Multiple approaches explored. Ruthless scope control.
-No implementation until design is approved.
+One question at a time. Multiple approaches explored. Design approved in
+sections. Ruthless scope control. No implementation until design is approved.
 
 ## Artifact
 
 ```
-docs/specs/YYYY-MM-DD-<topic>-design.md  ← This skill's output
+docs/specs/YYYY-MM-DD-<feature>/
+└── design.md  ← This skill's output
 ```
 
 Requirements are inline — no separate requirements.json needed.
@@ -156,11 +158,14 @@ review before I continue with the design."
 
 ---
 
-## Step 4: Design — Explore Approaches
+## Step 4: Design
 
-Before settling on a design, present **2-3 approaches** with trade-offs.
+Design happens in three phases: explore approaches, present the design in sections,
+then write the spec file.
+
+### 4a. Explore approaches
 
-### Approach exploration
+Before settling on a design, present **2-3 approaches** with trade-offs.
 
 For each approach, address:
 
@@ -169,7 +174,7 @@ For each approach, address:
 3. **Cons** — What's painful, expensive, or risky
 4. **Complexity estimate** — Rough sense of implementation effort
 
-Then make a recommendation and explain why.
+Lead with your recommended option and explain why it wins.
 
 **Example:**
 
@@ -186,23 +191,60 @@ Then make a recommendation and explain why.
 > **Recommendation:** Approach B — the query flexibility matters more here than
 > implementation speed.
 
-### Design approval gate
+Get explicit approval on the chosen approach before presenting the design.
 
-Get explicit approval on the chosen approach before writing the full spec.
-
-**Tell the human:** "Which approach should we go with? Or should I explore a different
-direction?"
+**Tell the human:** "Which approach should we go with? Or should I explore a
+different direction?"
 
 **STOP. Wait for human to choose an approach.**
 
-### Write the spec
+### 4b. Present the design in sections
+
+Present the design in batches. Get approval after each batch before continuing.
+
+Sections already confirmed in earlier steps (Problem, Scope, Constraints, Context)
+are written into the spec from those confirmations — do not re-present them.
+
+**Batch A: User Stories** — the contract you're designing against. Formal stories
+with acceptance criteria and priorities. If rejected: revise. If the rejection
+reveals a scope misunderstanding, loop back to Discovery (Step 2).
+
+**Batch B: Architecture** — component design, domain modeling, and layer
+boundaries. Use `python-architecture` or `typescript-api-design` as relevant to
+your stack. Then present: component structure, domain model, where business
+logic lives, where IO lives. If rejected: revise. If the rejection undermines
+the chosen approach, offer to return to approach exploration (4a). If it
+reveals a fundamental gap, loop back to Research (Step 3). If the detail reveals
+the work is far more complex than estimated, say so and offer to revisit the
+approach.
+
+**Batch C: API Design + Data Model** — contracts derived from the approved
+architecture. Skip sections that don't apply, but say so explicitly ("No API
+changes — moving to Trade-offs"). Never skip silently. If rejected: revise. If
+the rejection implicates the architecture, go back to Batch B.
 
-Once an approach is chosen, write the full spec document.
+**Batch D: Trade-offs + Open Questions** — alternatives considered, why this
+approach wins, known limitations, anything unresolved. Usually revisable inline.
 
-Use the Skill tool to invoke **oracle-architect** for component design, domain modeling,
-and layer boundaries.
+Each batch ends with:
 
-### What the spec should contain
+**Tell the human:** "Does this look right?"
+
+**STOP. Wait for approval before continuing.**
+
+If you loop twice on the same batch, stop and ask:
+
+> "We've looped on [batch] twice. Should we reconsider the approach?"
+
+**Terminology discipline:** while drafting batches, challenge terms against
+`CONTEXT.md` and update it inline as terms resolve, using the **oracle-domain-modelling**
+skill. If domain confusion runs deep, suggest pausing for **oracle-grill-me** before continuing.
+
+### 4c. Write the spec
+
+Once all batches are approved, write the full spec document.
+
+#### What the spec should contain
 
 ```markdown
 # Feature Name
@@ -256,70 +298,48 @@ and layer boundaries.
 Scale each section to complexity — a few sentences if straightforward, detailed if
 nuanced.
 
-### Reference implementations
-
-If human provides reference code — from open source, from elsewhere in codebase — use it
-as a concrete guide. Working from a reference produces dramatically better designs.
+#### Reference implementations
 
----
-
-## Step 5: Self-Review
-
-Before presenting the spec to the human, run this checklist silently:
-
-### 1. Placeholder scan
-
-Are there any TBD, TODO, FIXME, or incomplete sections? Every section should have real
-content or be removed.
-
-### 2. Internal consistency
-
-Do sections contradict each other? If the Architecture section says "stateless" but the
-Data Model includes session state, resolve the conflict before presenting.
-
-### 3. Scope check
-
-Is this focused enough for a single implementation plan? If the spec covers more than
-one independent subsystem, it should have been decomposed in Step 2. If it's still too
-broad, flag it now.
+If the human provides reference code — from open source, from elsewhere in the
+codebase — use it as a concrete guide. Working from a reference produces
+dramatically better designs.
 
-### 4. Ambiguity check
+#### Self-review
 
-Could any requirement be interpreted two ways? If so, pick one interpretation, state it
-explicitly, and let the human correct you.
+After writing the file, check it with fresh eyes:
 
-Fix any issues found. Then present.
+1. **Placeholder scan** — Any TBD, TODO, FIXME, or incomplete sections? Every
+   section should have real content or be removed.
+2. **Internal consistency** — Do sections contradict each other? If the
+   Architecture section says "stateless" but the Data Model includes session
+   state, resolve the conflict.
+3. **Scope check** — Is this focused enough for a single implementation plan?
+   If the spec covers more than one independent subsystem, it should have been
+   decomposed in Step 2. If it's still too broad, flag it now.
+4. **Ambiguity check** — Could any requirement be interpreted two ways? If so,
+   pick one interpretation, state it explicitly, and let the human correct you.
 
-**Tell the human:** "The spec is complete. Ready for your review."
-
-**STOP. Wait for human review.**
+**Substance rule:** if a fix changes the substance of an approved section,
+re-present that section for approval. Wording and consistency fixes go inline —
+note them at handoff.
 
 ---
 
-## Step 6: Annotation
-
-Human may annotate the spec directly — adding corrections, rejections, domain knowledge,
-or "remove this section entirely."
-
-When they say "I added notes":
+## Step 5: Handoff
 
-1. Re-read the full document
-2. Address every note
-3. Update the spec
-4. Run the self-review checklist again (Step 5)
-5. **Do not move to planning**
+**Tell the human:**
 
-This may repeat 1-6 times. Spec is not approved until human explicitly says so.
+> "Spec written to `docs/specs/<path>`. Every section was approved during our
+> conversation — review it if you'd like, or we can go straight to the
+> implementation plan. Ready for spec-plan?"
 
----
-
-## Handoff
+If the human requests changes — in conversation or by annotating the file —
+address every note, update the spec, and re-run the self-review. If a change
+alters the substance of an approved section, re-present that section for
+approval before continuing.
 
-When the spec is approved, the next step is **spec-plan**.
-
-> "Spec is approved. Ready to write the implementation plan?"
+The next step is **spec-plan**. Do not start planning without the human's
+go-ahead. Do not write code.
 
 If planning reveals design flaws, loop back to research. See **spec-orchestrator**
 for iteration patterns.
-
-Do not start planning without explicit approval. Do not write code.

package/skills/spec-finish/SKILL.md

@@ -2,8 +2,9 @@
 name: spec-finish
 description: >
   Post-implementation completion workflow. Use after spec-implement completes to validate,
-  review, create stacked commits, and prepare for PR. Triggers when implementation is done,
-  when the user says "finish", "done", "complete", or after implementation tasks are finished.
+  review, create stacked commits, and open a PR via code-pull-request. Triggers when
+  implementation is done, when the user says "finish", "done", "complete", or after
+  implementation tasks are finished.
 user-invocable: true
 ---
 
@@ -99,29 +100,26 @@ Use the Skill tool to invoke code-review skill for comprehensive code review.
 
 ## Step 4: Update Documentation
 
-Optional - use code-docs skill if needed.
-
 ### Check for Updates
 - README changes needed?
 - API documentation updated?
 - Changelog updated?
 
 ### If documentation needed
-- Load code-docs
 - Update relevant docs
 - Commit with docs
 
 ---
 
-## Step 5: Prepare for PR
+## Step 5: Open the PR
+
+Steps 1-4 (validate, review, stack commits, update docs) must all be complete
+before proceeding. **If code-review found blocking issues, stop — return to
+spec-implement to fix them. Do not proceed to Step 5b.**
 
-### Verify
-- All tests passing
-- All reviews complete
-- Documentation updated
-- Commits stacked properly
+### Step 5a: Present Completion Summary
 
-### Summary for Human
+Before creating the PR, present a summary to the human:
 
 ```
 ## Completion Summary
@@ -130,13 +128,21 @@ Optional - use code-docs skill if needed.
 **Tests:** [passed/failed]
 **Type Check:** [passed/failed]
 **Lint:** [passed/failed]
+**Review:** [passed/issues found]
 **Commits:** [N commits in stack]
 **Ready for PR:** [yes/no]
 ```
 
+### Step 5b: Invoke code-pull-request
+
+Only when the summary shows **Ready for PR: yes**, invoke the
+[code-pull-request](../code-pull-request/SKILL.md) skill to create the PR. It
+detects the platform (GitHub/GitLab), checks for an existing PR, finds a
+template, generates the body from commits, and opens the PR via `gh` or `glab`.
+
 ### Handoff
 
-> "Implementation complete. [N] commits stacked. Ready for [submit/open PR]."
+> "Implementation complete. [N] commits stacked. Opening PR now."
 
 ---
 
@@ -145,7 +151,7 @@ Optional - use code-docs skill if needed.
 This skill orchestrates other skills:
 
 - Invokes code-review for quality check
-- Invokes code-docs if documentation needs updates
+- Invokes code-pull-request as the final step to open the PR
 
 ---
 

package/skills/spec-implement/SKILL.md

@@ -108,8 +108,9 @@ Update the todo status to in_progress.
 Read the task's **inputs** first — understand what context you need.
 Then read the **description** — know what to build and the constraints.
 
-Invoke **oracle-testing** for test design. Write tests that cover the validation
-criteria before writing implementation.
+Write tests that cover the validation criteria before writing implementation.
+Invoke `typescript-testing` or `python-testing` (whichever matches the project)
+for test design patterns when needed.
 
 ```
 1. Read task inputs and description