SkillAgentSearch skills...

ln-32-test-strategy-planner

Plans risk-based test portfolios and acceptance evidence; does not write or execute tests.

Install / Use

npx skills add levnikolaevich/claude-code-skills --skill ln-32-test-strategy-planner

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

82/100

Category

Legal

Supported Platforms

Universal

Our assessment of ln-32-test-strategy-planner

ln-32-test-strategy-planner scores 82/100 on our quality scale, 166th of 209 Legal skills we index.

Its SKILL.md is 14 KB long, well organised into 10 sections and no code examples: a thorough specification that gives an agent plenty to work with.

It has 566 GitHub stars, a meaningful sign that others use it.

Substance
30/30
Structure
13/20
Description
12/15
Adoption
12/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so ln-32-test-strategy-planner is actively maintained.
  • Our last check on 2026-11-08 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-15. Automated pattern scan on 2026-10-15. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

ln-32-test-strategy-planner compared with similar skills

All 4 of these similar skills score higher than ln-32-test-strategy-planner; compare them before choosing.

SkillScoreStarsUpdatedFormat
ln-32-test-strategy-planner (this skill)by levnikolaevich825662mo agoSKILL.md
taste-skillby Leonxlnx100117.6k9d agoCLAUDE.md
Claude-Code-Game-Studiosby Donchitos10039.9k8d agoCLAUDE.md
x402by browser-use100121.0k4d agoSKILL.md
algorithmic-artby anthropics100177.9k56d agoSKILL.md

Frequently asked questions

How do I install ln-32-test-strategy-planner?
Run npx skills add levnikolaevich/claude-code-skills --skill ln-32-test-strategy-planner. The install tabs above show the steps for each supported agent.
Which AI agents does ln-32-test-strategy-planner work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is ln-32-test-strategy-planner safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is ln-32-test-strategy-planner still maintained?
The repository was last updated about 2 months ago, so ln-32-test-strategy-planner is actively maintained.

name: ln-32-test-strategy-planner description: "Plans risk-based test portfolios and acceptance evidence; does not write or execute tests."

Test Strategy Planner

Goal: Design a read-only, risk-based test portfolio decision for the requested scope. Maximize confidence in important local behavior while preventing test growth that lacks a unique defect signal, and define how affected evidence is retained, changed, consolidated, retired, or deliberately omitted.

Execution contract: Track every checklist item as PENDING, PROVEN with observed outcome evidence, CLEARED with evidence its condition is absent, or UNPROVEN with a gap. Reading, delegation, tool failure, zero exit status, and self-reported success are not proof. Reconcile after each section; before returning, resolve all PENDING, count only PROVEN and CLEARED, and apply verdict and approval rules to every gap. Preserve intent, scope, mode, and existing authorization. Complete authorized work before required external approval; ask only consequential unresolved choices. If nobody can answer, report the exact question and apply the skill's gap verdict without waiting or guessing. Cite any blocking instruction and unresolved boundary; never invent approval gates. Scale depth to material risk; preserve mandatory checks, dependencies, and safety order while choosing verification methods. Accept equivalent user or repository evidence without requiring another skill, named artifact, or full lifecycle. Preserve source requirement and decision IDs. Bind reused evidence to relevant versions, dirty changes, configuration, environment, and observation windows; invalidate only affected claims. Choose the primary workflow by outcome and explicit selection. Consume neighboring contracts and valid evidence without duplicating ownership or restarting audits. Split distinct deliverables by scope, not mandatory skill invocation. Broad independent assessments use audit workflows; focused domain reviews remain read-only. On continuation, reconcile task, authorization, state, and gaps. Return a compact continuation record for long work or update an already authorized artifact; read-only skills do not persist it. Distinguish artifact readiness, verified behavior, and external-action authority. Before retrieval, define the evidence question; read selectively without skipping applicable instructions. Use tools for mechanical processing; summarize bounded results, errors, coverage, and source paths, keeping full output outside context. Before technical decisions, establish applicability and actual versions; verify version-dependent assumptions against official documentation or specifications. Search and read primary pages for current external recommendations; snippets are not evidence. Version-matched bundled documentation or valid prior evidence suffices. Record decision, version, source, and limitations. Mark unavailable evidence UNVERIFIED; block only essential dependent work. Prefer native mechanisms, justify added tools or abstractions with evidence, and reuse the existing rule owner.

Tool Routing

| Need | Preferred tool | Use it when | Fallback | |---|---|---|---| | Requirements and repository rules | Native file reads plus Git | Establishing scope, current work, acceptance criteria, and supported commands | User-provided requirements with explicit limitations | | Existing test surface | File listing, search, manifests, runner configuration, and CI | Mapping test levels, fixtures, environments, and conventions | Repository tree and known test entrypoints | | Behavior and boundaries | Language server or host-native code intelligence | Tracing entrypoints, consumers, trust boundaries, persistence, queues, and external contracts | Narrow search followed by direct inspection | | Existing evidence | Existing test/CI reports and test/configuration reads | Current proof can change the strategy | Use static evidence with execution limits; do not execute tests during planning | | Current external failure modes | Official documentation, specifications, advisories, and primary field evidence | An external contract or real user failure can change scenarios or priority | Mark the claim UNVERIFIED; do not invent risk |

Keep the run read-only. Do not create tests, fixtures, snapshots, tasks, or documentation, and do not update the reviewed implementation.

Evidence Rules

  • Coverage is discovery evidence, not proof. Require an oracle that would fail for the named defect.

  • Prioritize by impact, plausible failure, uniqueness, detectability, and recovery cost; do not convert those judgments into universal numeric thresholds.

  • Existing tests reduce a gap only when their setup and assertions prove the same behavior and failure mode.

  • Keep portfolio action separate from execution status. Use KEEP, ADD, UPDATE, MERGE, DELETE, or NO_TEST for the decision and PASS, FAIL, BLOCKED, or UNPROVEN only for evidence state.

  • NO_TEST is an explicit risk decision, not missing work. Name the existing proof, alternative control, or accepted residual risk.

  • A persistent test register is optional. Prefer repository-native test names, paths, tags, CI configuration, and task output unless scale or governance requires another maintained artifact.

  • External research is actionable only when it adds a concrete failure mode, boundary, or oracle to this plan.

Checklist

1. Establish Scope and Evidence

  • [ ] Resolve the feature, requirements, acceptance criteria, actors, explicit non-goals, and protected human or system outcomes; separate the requested mechanism from the result it must enable and return BLOCKED if there is no concrete behavior to plan for.
  • [ ] Read applicable repository instructions and inspect Git state so current work and unrelated changes are not mistaken for established behavior.
  • [ ] Detect languages, frameworks, runners, test directories, fixtures, factories, environments, CI gates, coverage, contract tests, and manual test surfaces for the affected behavior and its verification dependencies. Expand discovery only when another surface can change coverage, risk, test level, or feasibility.
  • [ ] Map existing evidence and every test affected by the requested behavior to each requirement; record coverage as complete, partial, missing, or unavailable based on the actual oracle, alongside the execution state defined in Evidence Rules; names and proximity are not proof.
  • [ ] Inspect manual, exploratory, incident, and production evidence when it reveals behavior that automated suites do not cover.
  • [ ] Identify environment, data, credentials, services, devices, browsers, and destructive-state constraints before proposing scenarios.
  • [ ] Record assumptions and unknowns that can change test level, priority, or feasibility, and ask one concise question only when different interpretations materially change the strategy.

2. Build the Risk Map

  • [ ] Trace critical flows from actor trigger through entrypoint, runtime wiring, state change, and durable or user-visible outcome.
  • [ ] Identify uniquely important local behavior involving money, authentication, authorization, ownership, data integrity, destructive actions, migrations, public contracts, or irreversible workflows.
  • [ ] Enumerate plausible defect classes: incorrect success, rejected valid input, accepted invalid input, boundary error, partial failure, duplicate delivery, ordering, timeout, retry, cancellation, race, rollback, recovery, and compatibility drift; state what protected outcome is lost or what concrete harm follows.
  • [ ] Separate product risks from implementation details and behavior already guaranteed by a dependency; exclude technically representable states that protect no unique local outcome or decision.
  • [ ] Identify privacy-sensitive or regulated test data and require synthetic, minimized, or explicitly approved fixtures.
  • [ ] Use current external evidence only when version-sensitive contracts, recurring user failures, abuse patterns, or interoperability risks can change the map.
  • [ ] Rank risks qualitatively and explain ties or uncertainty; do not manufacture precision from missing frequency or impact data.

3. Decide Portfolio Actions, Levels, and Oracles

  • [ ] Assign every material risk and affected test exactly one provisional action: KEEP when trusted unique proof remains valid; ADD for an unproved material risk; UPDATE when valuable intent remains but basis, boundary, setup, or oracle changed; MERGE for safely consolidatable proof; DELETE for obsolete, duplicate, trivial, or untrustworthy proof; or NO_TEST when another control or accepted risk is sufficient.

  • [ ] For DELETE or MERGE, prove that the test basis is obsolete or identify replacement evidence that preserves every still-required material behavior, failure mode, oracle, and useful failure localization; never retain obsolete proof merely because it already exists.

  • [ ] Test value and boundary: Require every test to detect a concrete defect in this product's business logic and name the protected business outcome. Prefer E2E through user or external-system boundaries; use integration or unit tests only for business scenarios difficult to exercise reliably through E2E. Reject platform, trivial-wiring, implementation-detail, and duplicate proof with no distinct business failure signal.

  • [ ] Define the minimum sufficient independent oracle, combining observations when the contract requires them: returned contract, durable state, emitted event, rendered behavior, external effect, invariant, or deterministic artifact.

  • [ ] Check that mocks and fakes do not bypass the boundary or failure semantics the scenario claims to prove.

  • [ ] UI test locators: Use stable project-native semantic locators (roles, accessible names, labels) or explicit IDs/test hooks according to the observable contract and locale strategy. Avoid styling, position, timing, and incidental structure. Treat exact-copy assertions separately when copy is a requirement; do not require product edits solely to add hooks when a robust semantic locator exists.

  • [ ] Include positive, invalid, boundary, authorization, error, recovery, concurrency, and compatibility cases only where the risk map makes them material.

  • [ ] Specify non-default configuration, time, locale, randomness, ordering, or data scale when defaults could conceal hard-coded behavior.

  • [ ] Add browser, device, operating-system, runtime, or version cells only when the supported contract or a known risk makes them decision-relevant.

  • [ ] Prefer deterministic setup and bounded data; identify where real dependencies, emulators, disposable environments, or production-like topology are necessary.

  • [ ] Define the repository gate or diagnostic role, entry prerequisites, and evidence-based completion criteria for each portfolio action; do not use test count or raw coverage as completion.

4. Produce a Prioritized Test Matrix

  • [ ] For every decision, name the test basis, protected outcome, risk, existing evidence or affected test, portfolio action, level, setup, oracle, expected evidence, environment, gate, and result state when known.
  • [ ] Define a review or retirement trigger for evidence whose value depends on a contract, migration, compatibility window, workaround, incident, dependency, or temporary risk; do not invent dates without an owned reason.
  • [ ] Order scenarios so safety-critical and high-information checks run before expensive breadth, while preserving prerequisite and state dependencies.
  • [ ] Identify which scenarios can run in parallel and which share mutable state, rate limits, accounts, devices, or environment setup.
  • [ ] Classify gates by failure consequence and required detection time; place slow diagnostic checks outside routine gates only when another control covers release-critical risk.
  • [ ] State exclusions explicitly, including scenarios with no unique

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars566
CategoryLegal
Updated2mo ago
Forks84

Languages

PowerShell

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions