writing-plans
Use when requirements are clear enough to plan and the work spans multiple steps, files, or verification stages
What this skill does
# Writing Plans ## Overview Turn requirements into an executable plan with concrete files, tests, and verification. A good plan removes guesswork without pretending the implementation is already done. **Core principle:** Every task should be specific enough that an engineer can execute it without inventing missing requirements. ## When to Use Use this skill when: - The task spans multiple files, phases, or checks - Requirements are stable enough to plan - The work benefits from a written execution order Do not use this skill when: - The change is small enough to track directly in `update_plan` - Requirements are still ambiguous - The user asked to implement immediately and the work is trivial ## Before Writing the Plan 1. Read the relevant code, docs, and existing specs. 2. Confirm the scope is one coherent unit of work. 3. Stop and clarify if the plan would depend on guessed requirements. If the request covers multiple independent changes, split it into separate plans or clearly separated task groups. ## Plan Format Save the plan where the user asked. If they did not specify a location, use: `docs/plans/YYYY-MM-DD-<topic>.md` Start with: ```markdown # <Topic> Implementation Plan **Goal:** <one sentence> **Scope:** <what this plan covers> **Non-goals:** <what this plan intentionally avoids> **Risks:** <key technical or rollout risks> ``` Then include: ### Files - Create: `path/to/new_file` - Modify: `path/to/existing_file` - Test: `path/to/test_file` ### Task N: <name> - Outcome: <what is true when this task is done> - Steps: - Write or update the failing test - Run the targeted check and confirm the expected failure - Implement the minimal change - Re-run targeted verification - Run broader regression checks if needed - Verification: - `exact command` - expected result - Dependencies: - `Task N-1` or `none` ## Planning Rules - Use exact file paths. - Prefer tasks that can be reviewed independently. - Encode test-first thinking when the task changes runtime behavior. - Include commands that can actually be run from the repo. - Keep steps concrete: "add parser for X in `foo.ts`", not "improve parsing". - Keep unrelated refactors out unless they are required to make the change safe. ## Execution Handoff If the plan will be executed in the same session: - Mirror the task list in `update_plan` - Keep one task `in_progress` - Revise the plan if implementation reveals real gaps If the plan has independent sidecar work: - Use `dispatching-parallel-agents` for bounded, non-overlapping subtasks ## Red Flags - Plans that rely on tool names from another harness - Tasks that touch the same files from multiple parallel workers - Missing verification steps - Hidden migrations, schema changes, or contract changes buried in generic wording - Placeholder language like "update as needed" or "handle edge cases"
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.