CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deep-inspect

Use when a dotnet-inspect change needs expensive evidence outside normal PR CI, or when preparing release certification; coordinate Deep Inspect lanes (full slow tests, cross-platform certification, IL round-trip sweep, corpus sensors, package discovery, validity scans, and analysis census).

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-built operational skill: every command is copy-paste executable, the lane table makes dispatch decisions immediate, and result interpretation rules are explicit and unambiguous. The main weaknesses are mild redundancy in the certification-policy prose and inlined detail that a reference file could absorb.

Suggestions

Deduplicate the certification/publish-consumption policy, which is stated in both the intro and the 'Local equivalents' section — state it once and cross-reference.

Move the package-sweep schedule and promotion policy into a short reference file (or the lane table) so the overview stays lean.

Replace the fragile '../../../docs/release-workflow.md' relative link with a stable repo-relative path or a brief inline summary of the failure-acceptance path.

DimensionReasoningScore

Conciseness

The body is dense with repo-specific policy and commands Claude could not know, with no filler explaining general concepts — but the certification/publish-consumption policy is restated ('Publish consumes the latest completed certification evidence...' vs 'A green daily or manually dispatched certification requires...') and several long winding sentences could be tightened. Not 5 due to this redundancy; not 3 because nearly all content is non-obvious operational knowledge, not padding.

4 / 5

Actionability

Fully executable throughout: copy-paste 'gh workflow run deep-inspect.yml -f lane=<lane>' for every lane, 'gh run list/view/download' for inspection, and complete local-equivalent dotnet commands with exact project paths and flags. Not 4 because the commands cover the common cases completely with no gaps.

5 / 5

Workflow Clarity

The flow (dispatch a lane → inspect runs/artifacts → interpret per the Reading results rules) is clearly sequenced by section, and validation checkpoints are explicit ('A green... certification requires the test, platform-test, and decompiler-corpus jobs at one exact SHA'; 'Non-success outcomes remain red and require explicit human acceptance after review'). Not 5 because error-recovery guidance routes to an external release-workflow doc rather than including the feedback loop inline; not 3 because verification requirements and failure handling are stated, not absent.

4 / 5

Progressive Disclosure

No bundle files exist, and the single-file body is well organized into Lanes / manual dispatch / local equivalents / Reading results with a scannable lane table. Not 5 because some lane-specific operational detail (e.g. package-sweep scheduling and promotion policy) is inlined where a reference file would keep the overview lean, and one reference is a buried relative link ('../../../docs/release-workflow.md#ship-only-override') whose path is awkward outside the repo layout; not 3 because structure and navigation are otherwise good.

4 / 5

Total

17

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it pairs an explicit 'Use when' trigger clause with a comprehensive, concrete enumeration of the lanes it coordinates, all in third person. The only gap is modest synonym coverage for trigger terms that appear in the body but not the description.

DimensionReasoningScore

Specificity

The description enumerates concrete capabilities — 'coordinate Deep Inspect lanes (full slow tests, cross-platform certification, IL round-trip sweep, corpus sensors, package discovery, validity scans, and analysis census)' — giving comprehensive, specific coverage of what the skill does. Not score 4 because coverage is comprehensive rather than having minor gaps; not below because no part is vague.

5 / 5

Completeness

Explicitly answers both: 'Use when a dotnet-inspect change needs expensive evidence outside normal PR CI, or when preparing release certification' (when, with concrete triggers) and 'coordinate Deep Inspect lanes (...)' (what). Matches the top anchor with concrete trigger phrases, so not 4.

5 / 5

Trigger Term Quality

Natural maintainer phrases like 'expensive evidence outside normal PR CI', 'release certification', 'full slow tests', and 'cross-platform certification' would plausibly be said when this skill is needed. Not 5 because there are no synonyms or variations for key terms (e.g. 'nightly', 'package sweep', 'corpus ratchet' appear only in the body); not 3 because the included keywords are relevant and mostly the ones users would say.

4 / 5

Distinctiveness Conflict Risk

A clear niche (dotnet-inspect Deep Inspect CI/certification lanes) with distinct, domain-specific triggers; minimal risk of firing for an unrelated skill. Not 4 because the triggers are uniquely tied to this repo's workflow rather than overlapping with closely related skills.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository

richlander/dotnet-inspect

Path

.github/skills/deep-inspect/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.