# Askit Evaluate > Evaluates a skill or plugin against the Advanced Skill Library Standard across three modes, producing deterministic conformance findings and a tier, an opt-in behavioral pass, and a qualitative review. Use when you want to audit conformance, judge whether a skill behaves and triggers correctly, get a qualitative review, or see what blocks the next tier. - **Type:** Skill - **Install:** `agentstack add skill-product-on-purpose-agent-skills-toolkit-askit-evaluate` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [product-on-purpose](https://agentstack.voostack.com/s/product-on-purpose) - **Installs:** 0 - **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills) - **Latest version:** 0.1.0 - **License:** Apache-2.0 - **Upstream author:** [product-on-purpose](https://github.com/product-on-purpose) - **Source:** https://github.com/product-on-purpose/agent-skills-toolkit/tree/main/skills/askit-evaluate - **Website:** https://product-on-purpose.github.io/agent-skills-toolkit ## Install ```sh agentstack add skill-product-on-purpose-agent-skills-toolkit-askit-evaluate ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # askit-evaluate ## Purpose Assess a known, local component or plugin against `STANDARD.md`. Three modes. `conformance` (the default) runs the deterministic portable scripts and returns a per-rule report (pass / warn / error), the satisfied tier, and concrete remediation. `behavioral` runs a skill against its eval-set and judges whether it triggers and behaves as expected, delegating to `askit-quality-grader`. `review` forms a qualitative judgment (correctness, altitude, naming, whether a component is warranted), delegating to `askit-reviewer`. Only `conformance` is deterministic and gate-safe; `behavioral` and `review` are opt-in LLM-judged passes that produce evidence, never a CI gate result (Design Principle 3, ADR 0023). ## When to use When the user asks to evaluate, audit, or check a skill or plugin, asks "what tier is this" or "what is blocking the next tier" (conformance), asks whether a skill actually triggers and behaves correctly (behavioral), or wants a qualitative review (review). ## conformance mode (default, deterministic) 1. Determine the target path (a plugin root with `library.json`, or a single skill directory with `SKILL.md`). 2. Run: `node scripts/evaluate.mjs --json`. 3. Present the findings grouped by rule, the tier (for a plugin), and the remediation. Lead with errors, then warnings. 4. For a shareable, designed report, render the same object: `node scripts/evaluate.mjs --format=html --out report.html` (a self-contained page for a non-engineer) or `--format=md` (the Markdown twin for PR review and agents). It renders the same deterministic object the terminal shows, adds no judgment, and does not change the verdict. See [references/report-format.md](references/report-format.md). 5. If there are warnings or errors, point the user at `askit-build-skill` in `improve` mode to fix them. ## behavioral mode (opt-in, LLM-judged) 1. Locate the target's eval-set under `evals/` (triggering `{query, should_trigger}` cases and `{given, expect}` behavior cases). The `evals/` convention is forward-looking: most real targets do not ship one. If it is absent, the grader DERIVES a case set instead - should-fire queries and adversarial near-misses from the target's description (read sibling skills' descriptions to make the no-fire cases genuinely competitive), plus behavior cases from the documented workflow - judges by static analysis of the artifact, and says so in the evidence. 2. Delegate to `askit-quality-grader`: it runs the skill against the cases (on-disk or derived) and judges fire / no-fire and output quality. 3. Report the verdict per case with evidence. This is evidence, not a gate result; it never fails CI. ## review mode (opt-in, qualitative) 1. Delegate to `askit-reviewer`: it reviews the component or change for correctness, altitude, naming, and whether it is warranted. 2. Report findings by severity with remediation. Like behavioral, this is advisory, not a gate result. ## Scope The conformance core is deterministic and is what CI runs (Design Principle 3). Behavioral and review are opt-in LLM-judged layers beside the gate: the Standard defers the full eval engine to roadmap, and G3 requires only the deterministic baseline (ADR 0023). See [references/report-format.md](references/report-format.md) for the report shape. The delegations are permitted in `agents/_chain-permitted.yaml` (`askit-evaluate` may invoke `askit-evaluator` for conformance, `askit-quality-grader` for behavioral, and `askit-reviewer` for review). ## Source & license This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [product-on-purpose](https://github.com/product-on-purpose) - **Source:** [product-on-purpose/agent-skills-toolkit](https://github.com/product-on-purpose/agent-skills-toolkit) - **License:** Apache-2.0 - **Homepage:** https://product-on-purpose.github.io/agent-skills-toolkit Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/skill-product-on-purpose-agent-skills-toolkit-askit-evaluate - Seller: https://agentstack.voostack.com/s/product-on-purpose - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.