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 tikalk/adlc-team-skills --skill evals-specifygit clone --depth 1 https://github.com/tikalk/adlc-team-skillsWrote 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/tikalk/adlc-team-skills/evals-specify)<a href="https://agentmods.dev/skills/tikalk/adlc-team-skills/evals-specify"><img src="https://agentmods.dev/badge/skills/tikalk/adlc-team-skills/evals-specify/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/tikalk/adlc-team-skills/evals-specify"><img src="https://agentmods.dev/badge/skills/tikalk/adlc-team-skills/evals-specify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.00828 |
| Opus 5.5 | $0.00017 | $0.00331 |
| Sonnet 5.5 | $0.00009 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
evals-specify 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
evals-specify
What this skill does
Conducts bottom-up error analysis following EDD Principles III & IX (Error Analysis & Test Data as Code) to discover and document draft evaluation criteria from human observation of system failures.
Output:
- Draft Eval Records - Individual
EVAL-*.mdfiles in.adlc/drafts/evals/with open coding notes - Error Pattern Documentation - Bottom-up failure taxonomy from actual traces
- Pass/Fail Examples - Real examples that should pass/fail each criterion
- Auto-handoff to
/evals-clarifyfor axial coding and clustering
Key EDD Principles Applied:
- Principle III: Error Analysis & Pattern Discovery - Open coding → failure taxonomy
- Principle IX: Test Data as Code - Dataset planning and coverage analysis
- Principle II: Binary Pass/Fail - Maintain strict binary pass/fail conditions
- Principle V: Trajectory Observability - Track full multi-turn conversation traces
When to use
Note: Routine decision capture is handled by team-boot's continuous capture mechanism, which writes lightweight drafts directly to
.adlc/drafts/. This skill is for interactive deep-dive exploration — when you want guided trade-off analysis, multi-option comparison, or structured decision facilitation before documenting.
- Starting evaluation development: No existing criteria, need discovery from failure logs
- Production incident analysis: Recent failures require systematic analysis
- Quality assessment: Discovering and codifying boundary conditions from failures
When NOT to use
- No failure traces/specs: Generate synthetic traces first, or use
/evals-initto set up security baselines - Known criteria already exist: Use
/evals-clarifyto refine or/evals-implementto generate code
Process
User Input
$ARGUMENTS
Treat user input as specific failure areas or error patterns to analyze (e.g., "authentication bypass", "RAG irrelevant results").
--traces N— Number of traces to analyze (default: 20, min for theoretical saturation)--source SOURCE— Trace source location (e.g., logs, support tickets)
What ships with it
2 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 · +11 tokens per session ef08ec336fa2
- 1mo ago Changed · -1 tokens per session 35b4642dff65
- 1mo ago First seen · 71 lines · 33 tokens per session scan A eecbfe8fdf5c
evals-specify is a skill published in the GitHub repository tikalk/adlc-team-skills (143 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 828 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
respect-the-oracle
Use when working against a test suite, spec, or graded harness you do not own - especially inside an automated loop scored on how many tests pass - and tempted to change the tests, weaken assertions, hardcode expected outputs, special-case inputs, or overfit the visible examples to turn things green.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
unity-agent-workflows
Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first…
laravel-tdd
Test-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.