Skill Library Evaluation Standard v0.16 Evaluated 2026-09-05 Gate exit 0

agent-skills-toolkit

version 1.18.0  /  declared tier: advanced

Whole-library tier-compliance evaluation against the Advanced Skill Library Standard. Rendered from the one deterministic report object; the verdict is the gate's.

Checks passed
35/35
non-failing checks
Tier earned
Gold
Advanced
Blockers
0
none
Advisory warnings
0
none
Gate exit code
0
declared tier satisfied
Gold
Advanced
Verdict
Earns Gold
Declared Advanced; matches its declared tier.
No blockers: the declared tier is fully satisfied.
Bronze17 / 17
Silver8 / 8
Gold10 / 10
02

Executive summary

A derived, plain-language read of the deterministic result.

How to read this report

The colored matrix above is the whole verdict in one glance: every check is a chip, color-coded pass / fail / warn / not-applicable, grouped by tier. The tier is decided by a deterministic gate with a real exit code, not by opinion. Everything below expands that picture.

agent-skills-toolkit declares the Gold (Advanced) tier and earns Gold. Of the 35 checks in the spine, 35 do not fail (32 pass, 0 warn, 3 not applicable) and 0 fail. The deterministic gate exits 0.

No requirement blocks the declared tier; the library satisfies its claimed grade outright.

03

What was evaluated

The subject identity, then the component inventory.

Subject
agent-skills-toolkit
Version
1.18.0
Declared tier
Advanced (Gold)
Agent targets
claude, codex
Prefix
askit-
Grading profile
askit-library
ComponentTypeVersion
askit-backlogskill0.1.0
askit-build-agents-mdskill0.1.0
askit-build-chain-contractskill0.1.0
askit-build-commandskill0.1.0
askit-build-docsskill0.2.0
askit-build-hookskill0.1.0
askit-build-mcpskill0.1.0
askit-build-output-styleskill0.1.0
askit-build-samplesskill0.1.0
askit-build-settingsskill0.1.0
askit-build-skillskill0.1.3
askit-build-statuslineskill0.1.0
askit-build-subagentskill0.2.0
askit-build-workflowskill0.1.0
askit-capability-advisorskill0.1.0
askit-capability-gap-analysisskill0.1.0
askit-capability-whats-newskill0.1.0
askit-decisionskill0.1.0
askit-deprecateskill0.1.0
askit-evaluateskill0.1.3
askit-init-marketplaceskill0.2.0
askit-init-pluginskill0.1.0
askit-migrateskill0.1.0
askit-releaseskill0.1.0
askit-standards-watchskill0.1.0
askit-template-managerskill0.1.0
askit-skill-authorsubagent0.1.2
askit-evaluatorsubagent0.1.0
askit-explorersubagent0.1.0
askit-file-searchsubagent0.1.0
askit-file-opssubagent0.1.0
askit-reviewersubagent0.1.1
askit-quality-gradersubagent0.1.1
askit-evaluatecommand0.1.0
askit-build-skillcommand0.1.0
04

Methodology and scope

Three layers, kept separate so the verdict stays honest. Only the deterministic gate decides the tier.

Layer 1 - Conformance

Decides the tier. The portable Node gate runs every check with a real exit code, no model in the loop. Re-run node scripts/check.mjs . to reproduce it.

Layer 2 - Behavioral

Advisory only. A skill is run against its eval set; results are evidence and never decide a gate result.

Layer 3 - Review

Advisory only. A qualitative pass over scoping and design; it informs the insights, it does not move the badge.

Status legend

Pass requirement metFail blocks the tierWarn advisoryN/A vacuous pass

Confidence and limitations

Conformance findings are exact and reproducible: the same gate on the same commit yields the same result. Vacuous passes (U11, G6, G1) mean there was nothing to validate, not that a feature was exercised.

05

Tier compliance - evidence ledger

One row per requirement, all 35 itemized and grouped by tier. Every non-pass carries a why-it-matters note.

BronzeTier satisfied.17 / 17
U1library-jsonPass

Requirement satisfied; no finding raised. checks/library-json.mjs

U2anatomyPass

Requirement satisfied; no finding raised. checks/anatomy.mjs

U3frontmatter-validPass

Requirement satisfied; no finding raised. checks/frontmatter-valid.mjs

U4name-matches-dirPass

Requirement satisfied; no finding raised. checks/name-matches-dir.mjs

U5description-scorePass

Requirement satisfied; no finding raised. checks/description-score.mjs

U6reference-linksPass

Requirement satisfied; no finding raised. checks/reference-links.mjs

U7instruction-budgetPass

Requirement satisfied; no finding raised. checks/instruction-budget.mjs

U8manifest-driftPass

Requirement satisfied; no finding raised. checks/manifest-drift.mjs

U9version-matchPass

Requirement satisfied; no finding raised. checks/version-match.mjs

U12mermaid-validPass

Requirement satisfied; no finding raised. checks/mermaid-valid.mjs

U11mcp-validN/A

Nothing to validate for this subject (vacuous pass). checks/mcp-valid.mjs

U13skill-registrationPass

Requirement satisfied; no finding raised. checks/skill-registration.mjs

U14agent-restricted-fieldsPass

Requirement satisfied; no finding raised. checks/agent-restricted-fields.mjs

U15agents-dir-registerablePass

Requirement satisfied; no finding raised. checks/agents-dir-registerable.mjs

U16metadata-placementPass

Requirement satisfied; no finding raised. checks/metadata-placement.mjs

U17catalogue-manifest-shapePass

Requirement satisfied; no finding raised. checks/catalogue-manifest-shape.mjs

U18command-size-capPass

Requirement satisfied; no finding raised. checks/command-size-cap.mjs

SilverTier satisfied.8 / 8
S1agent-targetsPass

Requirement satisfied; no finding raised. checks/agent-targets.mjs

S2prefixPass

Requirement satisfied; no finding raised. checks/prefix.mjs

S3components-indexPass

Requirement satisfied; no finding raised. checks/components-index.mjs

S8components-mirrorPass

Requirement satisfied; no finding raised. checks/components-mirror.mjs

S4chain-contractPass

Requirement satisfied; no finding raised. checks/chain-contract.mjs

S7command-contractPass

Requirement satisfied; no finding raised. checks/command-contract.mjs

S5workflow-skillsPass

Requirement satisfied; no finding raised. checks/workflow-skills.mjs

S6per-target-presencePass

Requirement satisfied; no finding raised. checks/per-target-presence.mjs

GoldTier satisfied.10 / 10
G3library-regressionPass

Requirement satisfied; no finding raised. checks/library-regression.mjs

G6deprecationN/A

Nothing to validate for this subject (vacuous pass). checks/deprecation.mjs

G1hook-documentationN/A

Nothing to validate for this subject (vacuous pass). checks/hook-documentation.mjs

G2self-hostingPass

Requirement satisfied; no finding raised. checks/self-hosting.mjs

G5release-notesPass

Requirement satisfied; no finding raised. checks/release-notes.mjs

G4index-driftPass

Requirement satisfied; no finding raised. checks/index-drift.mjs

G7docs-frontmatterPass

Requirement satisfied; no finding raised. checks/docs-frontmatter.mjs

G8folder-readmePass

Requirement satisfied; no finding raised. checks/folder-readme.mjs

G9source-docPass

Requirement satisfied; no finding raised. checks/source-doc.mjs

G10docs-presencePass

Requirement satisfied; no finding raised. checks/docs-presence.mjs

06

The climb / burndown

No blockers; the declared tier is satisfied.

No blockers: the declared tier is satisfied. There is nothing to climb.

07

Improvement path

One card per gap: the issue, priority and effort, and a copy-paste prompt that drives the matching askit builder and re-runs the gate.

No action required; nothing failed or warned.

08

Insights

None for a deterministic conformance report.

No insights in a conformance report

Insights are produced by the advisory review layer (askit-reviewer), which a deterministic conformance report does not run. Run review mode to populate this section; a conformance report does not fabricate qualitative notes.

09

Evidence and sources

Citations grounding the findings: the check module, Standard clause, or subject file.

  • CHECKscripts/check.mjs - the portable deterministic gate (node scripts/check.mjs .); its exit code drives the verdict.
  • CLAUSEStandard v0.16 - the 35-check spine and the Bronze / Silver / Gold tier definitions.
  • FILElibrary.json - the subject identity (name, version, tier, agent-targets, prefix).
10

Report metadata

Provenance for this evaluation, plus the legend.

Subjectagent-skills-toolkit v1.18.0
Standard versionv0.16
Spine35 checks
Declared tieradvanced
Grade earnedGold (Advanced)
Grading profileaskit-library
Verdict modelocal
Evaluatoraskit-evaluate (renderer)
Gate exit code0
Evaluated2026-09-05
Checks32 PASS / 0 FAIL / 0 WARN / 3 N/A

Status legend

Pass requirement metFail blocks the tierWarn advisoryN/A vacuous pass

Generated by the askit-evaluate report renderer. The conformance layer is deterministic and reproducible; re-run node scripts/check.mjs . to reproduce every finding. This report adds no judgment and does not change the verdict.

11

Per-check glossary

What each of the 35 checks verifies, in one line - a plain-language reference for every row above.

CheckTierWhat it verifies
U1 library-jsonBronzeWithout a valid library.json a tool cannot identify the library, its version, or the Standard it pins, so nothing downstream can grade, install, or emit it.
U2 anatomyBronzeThe agentskills.io anatomy (a root AGENTS.md and the standard component folders) is how any agent discovers what the library contains; a broken anatomy makes the library unreadable to the tools meant to load it.
U3 frontmatter-validBronzeA component whose frontmatter does not parse, or lacks a name or description, cannot be loaded or selected by an agent; the parse is the contract between the file and the runtime.
U4 name-matches-dirBronzeWhen a component's declared name does not match its directory, references and manifests point at the wrong place; a kebab-case directory that equals the name keeps lookups unambiguous across agents.
U5 description-scoreBronzeA description below the clarity bar makes a skill hard for an agent to select for the right job; it may fail to fire when it should, or fire when it should not.
U6 reference-linksBronzeA reference link that does not resolve sends the agent to a missing file mid-task, breaking progressive disclosure exactly when the detail is needed.
U7 instruction-budgetBronzeA body over the instruction budget risks the model dropping its later steps, so the exact step that differentiates the skill can be the one lost at runtime.
U8 manifest-driftBronzeWhen a native manifest disagrees with library.json, the agent loads something other than what the library declares; generated (not hand-edited) manifests are what keep the two in lockstep.
S1 agent-targetsSilverWithout a declared agent-targets list the library does not say which agents it converges across, so the Convergent guarantees (matching manifests, per-target presence) have nothing to check against.
S2 prefixSilverA consistent prefix is how a multi-skill library avoids name collisions on a shared agent and signals which components belong to it; an unprefixed component is ambiguous once installed beside others.
S3 components-indexSilverWhen the components index does not list what is on disk, tools that read the index (install, emit, grade) miss real components or reference ones that do not exist.
S8 components-mirrorSilverA one-way index lets the index and disk drift apart silently; mirroring in both directions catches both an orphan on disk and a phantom in the index.
S4 chain-contractSilverAn orphan or phantom chain edge means a declared delegation points at nothing, or a real delegation is undeclared; the chain contract is what makes cross-component handoffs honest and reviewable.
S7 command-contractSilverA command that maps to zero or many skills is ambiguous at invocation; one command to exactly one skill keeps the slash entry point predictable.
S5 workflow-skillsSilverA workflow step that references a skill which does not exist breaks the run at that step; validating the references keeps a multi-step workflow executable end to end.
S6 per-target-presenceSilverIf a declared agent target is missing its native manifest, the library claims to converge on an agent it cannot actually load onto; per-target presence makes the cross-agent claim real.
U9 version-matchBronzeWhen a component version disagrees with library.json, release tooling and consumers cannot tell which version they actually have; the versions must agree to make a release honest.
U12 mermaid-validBronzeA mermaid diagram that does not parse renders as a broken block in the docs and the docs site, so a diagram meant to explain the library instead signals it is unmaintained.
U11 mcp-validBronzeAn MCP server definition that is malformed or carries an inline secret either fails to connect or leaks a credential into the repository; validating it keeps the integration safe and loadable.
U13 skill-registrationBronzeA skill on disk that the manifest does not register ships but is invisible to installers; the catalog must list everything the library delivers, and a registered skill with no directory cannot be delivered at all.
U14 agent-restricted-fieldsBronzeClaude Code refuses hooks, mcpServers and permissionMode on a plugin-shipped agent for security reasons, so an agent declaring one has configured something the runtime will not honour - and nothing tells the author, which is the whole hazard.
U15 agents-dir-registerableBronzeClaude Code scans agents/ for *.md and registers every file it finds, so a file the plugin excludes from its own registration is still a live subagent - with whatever name and frontmatter it happens to carry - and it escapes every check that reads the registration list.
U16 metadata-placementBronzeThe Standard places version, tier, status and the other governance keys under `metadata`; declared at the top level they are read by nothing, so an author who wrote a version has not recorded one and receives no signal either way.
U17 catalogue-manifest-shapeBronzeA .claude-plugin/marketplace.json that cannot be parsed, carries no plugins array, or mixes skill-source and plugin-source entries is read by no scope or by only one of two - so entries the author declared are catalogued by nothing, with no signal either way.
U18 command-size-capBronzeCodex migrates a plugin's commands into skills and SKIPS any whose rendered skill exceeds its size cap - no skill is written and no error is raised, so an oversized command simply does not exist on Codex while the repository still shows it.
G3 library-regressionGoldChain edges are where delegation breaks quietly; a regression eval per edge turns the chain contract from a declaration into a tested guarantee that a refactor cannot sever unnoticed.
G6 deprecationGoldA component removed or replaced without following the deprecation policy breaks consumers who depended on it; an explicit deprecation gives them a status, a reason, and a migration path.
G1 hook-documentationGoldAn undocumented hook changes the agent's behavior invisibly; documenting each hook is what lets a reviewer and a consumer see what fires and why before they install it.
G2 self-hostingGoldWithout CI running the gate, conformance is a claim, not a proof. Any change can silently regress the library, and a consumer cannot point to a green badge that says the standard held on the latest commit.
G5 release-notesGoldA changelog is for maintainers; release notes are for users. Without a curated RELEASE-NOTES.md, adopters have no human-readable summary of what changed and why they should upgrade.
G4 index-driftGoldA stale INDEX.md misrepresents the library to anyone reading the catalog; generating it and drift-checking in CI keeps the published index honest on every commit.
G7 docs-frontmatterGoldThe audience/level/doc-role frontmatter taxonomy is what lets the docs site route a reader to the right page; without it the generated site cannot organize the library's documentation.
G8 folder-readmeGoldA meaningful folder with no README leaves a reader guessing what it holds; a short folder guide is the cheapest orientation a contributor or consumer gets.
G9 source-docGoldA script with no what-it-is / what-it-does / why docblock forces a maintainer to reverse-engineer its purpose; the four-field header keeps the toolkit's own machinery legible.
G10 docs-presenceGoldA library without the Diataxis quadrants (tutorials, how-to, reference, explanation) leaves whole classes of reader unserved; their presence is what makes the documentation complete rather than incidental.