Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jeremylongworth-source/AgentSkills --skill skill-evaluation-iterationgit clone --depth 1 https://github.com/jeremylongworth-source/AgentSkillsWrote 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/jeremylongworth-source/agentskills/skill-evaluation-iteration)<a href="https://agentmods.dev/skills/jeremylongworth-source/agentskills/skill-evaluation-iteration"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/skill-evaluation-iteration/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/jeremylongworth-source/agentskills/skill-evaluation-iteration"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/skill-evaluation-iteration.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 | $0.00064 | $0.00598 |
| Opus 5.5 | $0.00026 | $0.00239 |
| Sonnet 5.5 | $0.00013 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
skill-evaluation-iteration 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 1mo 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.
Skill Evaluation Iteration
Core Workflow
- Define the target behavior and realistic user scenarios before editing the skill.
- Run or simulate a baseline without the skill when practical.
- Run or simulate the same scenario with the skill.
- Compare outputs by decision quality, missing steps, correctness, concision, safety, tool use, validation, and deliverable usefulness.
- Patch the skill to close observed gaps. Keep changes small and domain-specific.
- Validate the skill folder with the official validator.
- Repeat only when the new test reveals a material gap.
For model-specific evaluations, record the exact model, reasoning setting, host, active instructions, available tools, and source inputs. Hold those constant when comparing skill versions. Label source reviews and simulations separately from live runs; only claim improvements supported by recorded outputs. Include a negative case for unnecessary questions or skill use.
Output Contract
For skillset improvement work, return:
- Scenarios evaluated
- Rubric used
- Gaps found
- Skills changed
- Validation run
- Remaining risks or deferred improvements
Patch Decision Rule
Patch a skill only when the test reveals a concrete trigger, workflow, output, validation, freshness, or routing gap. Do not edit skills just to make them longer.
Evaluation Criteria
- Trigger accuracy: skill activates for the right requests and avoids unrelated ones.
- Metadata sync:
agents/openai.yamlstill reflects the currentSKILL.mdpurpose, especially after major edits. - Scope and discovery: the skill is installed in the narrowest useful scope with a precise description; global instructions do not accumulate skill-routing lists.
- Context efficiency: SKILL.md is concise and references are loaded only when needed.
- Procedural value: skill changes the agent's workflow, not just wording.
- Quality bar: output includes acceptance criteria, validation, and domain-specific checks.
- Robustness: skill handles edge cases, constraints, and missing context.
- Maintainability: skill avoids stale facts unless it includes a freshness rule.
- Hygiene: generated scaffold placeholders, TODOs, stale examples, and irrelevant boilerplate are removed.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +6 lines 7293d718b1f0
- 1mo ago First seen · 54 lines · 64 tokens per session scan A d649a2c06d63
skill-evaluation-iteration is a skill published in the GitHub repository jeremylongworth-source/AgentSkills (1 stars, last pushed 17d ago), licensed MIT. It adds 64 tokens to every session and 598 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
tester
Run end-to-end web quality audits with Playwright and Lighthouse using existing project scripts first. Use when the user says /tester, e2e test, smoke test, Playwright audit, Lighthouse audit, performance audit, accessibility audit, dark mode audit, mobile audit, or asks for 100/100 Lighthouse improvement guidance.
data-validation-contracts
Use when data crosses a boundary into your code (file, API, warehouse table, upload, model input or output), when a join or cleaning step can change row counts, or when adding pandera, Great Expectations, Pydantic or dbt checks.
flutter-testing
Use when testing Flutter code - unit tests for logic, widget tests for UI behavior, golden tests for appearance, the multi-size/text-scale/dark matrix, accessibility guidelines, test-first.
retest-after-revision
Use when the task came back to QA after needrevision - what to re-run, what may carry over, and how to keep old passes from approving new code.
dotnet-testing-advanced-tunit-advanced
A guide for advanced TUnit testing in .NET. TUnit is a testing framework; the guide covers tests driven by data, dependency injection, integration tests, retries, time limits, and filtering.
dotnet-testing-private-internal-testing
A guide to testing private and internal members in .NET, including design changes, friend-assembly access, and reflection. Private members are available only inside their class; internal members are limited to the same project.