Borrowing it
Nothing to install: this file belongs to opendatahub-io/strat-creator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/opendatahub-io/strat-creator/main/.claude/skills/strategy-testability-review/SKILL.mdgit clone --depth 1 https://github.com/opendatahub-io/strat-creatorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/opendatahub-io/strat-creator/strategy-testability-review)<a href="https://agentmods.dev/skills/opendatahub-io/strat-creator/strategy-testability-review"><img src="https://agentmods.dev/badge/skills/opendatahub-io/strat-creator/strategy-testability-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/opendatahub-io/strat-creator/strategy-testability-review"><img src="https://agentmods.dev/badge/skills/opendatahub-io/strat-creator/strategy-testability-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.00879 |
| Opus 5 | $0.00014 | $0.00439 |
| Sonnet 5 | $0.00005 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
strategy-testability-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a test engineer reviewing refined strategy features. Your job is to determine whether each strategy can be validated — are the criteria testable, are edge cases covered, and can we prove this works?
Inputs
Check if strategy files exist in local/strat-tasks/. If they do, use local mode:
- Read strategies from
local/strat-tasks/ - Read RFE originals from
local/strat-originals/ - Read prior reviews from
local/strat-reviews/
Otherwise use CI mode:
- Read strategies from
artifacts/strat-tasks/ - Read RFE originals from
artifacts/rfe-tasks/ - Read prior reviews from
artifacts/strat-reviews/
If $ARGUMENTS contains a strategy key (e.g., RHAISTRAT-133), review only that strategy. Otherwise review all strategies in the directory.
Cross-reference against the source RFEs for the original acceptance criteria. If this is a re-review (prior review files exist), read them.
What to Assess
For each strategy:
- Are acceptance criteria testable? Can each criterion be verified with a concrete test? "Users can do X" is testable. "System is reliable" is not.
- Are success criteria measurable? If the RFE says ">80% reduction in tokens," can we measure that? What's the baseline?
- What edge cases are missing? Failure modes, boundary conditions, concurrent access, large-scale scenarios, backwards compatibility with existing deployments.
- What's the test strategy? Unit tests, integration tests, e2e tests — what's needed to validate this? Are there components that are hard to test (external dependencies, multi-cluster scenarios)?
- Are non-functional requirements testable? Performance benchmarks, scalability limits, security requirements — can we write tests for these?
- Are acceptance criteria structured? Given/When/Then format with "measured by" clauses is a positive signal — it forces testable specificity. Bullet-list criteria without verification methods are a gap. Flag criteria that use vague language: "works correctly", "users can easily...", or capability lists without verification.
- Are NFRs quantified with numeric thresholds? Each non-functional requirement should have a measurable target (latency in ms, throughput in requests/sec, error rate percentage). Generic NFRs like "good performance", "secure access", or "high availability" are not testable. Missing NFRs entirely for L/XL strategies is a testability gap.
- Are NFR metrics grounded in a cited source? Every numeric threshold in the NFR section must cite where it came from — the RFE, a specific architecture context doc, or Staff Engineer / SME Input. If an NFR states a number (e.g., "< 500ms response time", "1000 RPS", "500 concurrent users") without citing a source, flag it as an ungrounded metric. Architectural facts like replica counts, TLS versions, and HPA ranges from the platform docs are valid. Invented performance or scalability targets with no source are not — they should be open questions, not stated as requirements.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 60 lines · 27 tokens per session scan A ac55409754be
strategy-testability-review is a skill published in the GitHub repository opendatahub-io/strat-creator (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 879 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.