CtrlK
BlogDocsLog inGet started
Tessl Logo

ov-debug-matcher-pass

Debug why an OpenVINO MatcherPass transformation is not firing. Use this skill immediately when a user says a transformation is "not applied", a "pass has no effect", a "matcher never triggers", a pattern "doesn't match", a "callback never fires", "WrapType predicate is too strict", a subgraph "not fused" despite the pass being registered, or they see "END: PATTERN DIDN'T MATCH" in matcher logs. Also trigger when a MatcherPass works on one model but silently skips another, when the user wants to add a reproducer test for a transformation that should fire but doesn't, or when they suspect an opset version mismatch preventing a match. Do NOT trigger for: writing a new MatcherPass from scratch, debugging a pass that fires but produces wrong numerical results, crashes in pass registration, or general questions about what MatcherPass is.

73

Quality

91%

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

88%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 highly actionable, well-sequenced debugging workflow with strong validation feedback loops and executable commands throughout. The main weaknesses are mild redundancy across the root-cause tables (3c, 3d, Step 6) and limited use of progressive disclosure beyond the single example-report reference.

Suggestions

Consolidate the root-cause material: the 3c log-phrase table, the 3d common-causes list, and the Step 6 resolution table overlap heavily — consider a single cause→log-phrase→resolution table or move the catalog to a reference file.

Move the Step 6 resolution-strategy table (and possibly the 3d root-cause catalog) into a references file linked from the main body to reduce inline length and improve progressive disclosure.

Trim or fold the 'Common test locations' and CMake target-discovery grep examples in Step 4/5 into a single 'locating tests' reference, since they are lookup material rather than core workflow steps.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence (no basic explanation of what OpenVINO or a matcher is), but root-cause material is covered three times — the 3c log-phrase table, the 3d common-causes list, and the Step 6 resolution table — which could be consolidated.

4 / 5

Actionability

Fully executable guidance throughout: concrete grep/cmake/env-var bash commands, a runnable Python tally snippet, a copy-paste C++ TEST_F template, and exact gtest_filter invocations covering the common cases.

5 / 5

Workflow Clarity

Clear Step 0–6 sequence with explicit validation checkpoints (Step 2a tally, wait-for-completion guard, Step 5 cross-check of matcher logs) and a feedback loop ('If the logs diverge ... revise the test graph ... and repeat'), plus an early-exit condition.

5 / 5

Progressive Disclosure

Good structure with a clearly signaled one-level-deep reference (references/example-diagnosis-report.md) verified to exist, but the body itself is a long inline workflow and only the filled example is offloaded, so disclosure is not fully leveraged.

4 / 5

Total

18

/

20

Passed

Description

95%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, trigger-rich description that clearly states what the skill does and when to use it, using third-person imperative voice and including rare literal log phrases as triggers. The only minor gap is that the concrete action list is narrow (debug + reproducer) rather than a broad set of operations.

DimensionReasoningScore

Specificity

Names the domain ('OpenVINO MatcherPass transformation') and concrete actions ('Debug why ... is not firing', 'add a reproducer test'), but coverage is effectively two actions rather than a broad list, leaving minor gaps relative to the comprehensive anchor.

4 / 5

Completeness

Explicitly answers both 'what' (debug why a MatcherPass does not fire; add a reproducer test) and 'when' ('Use this skill immediately when ...' with many concrete triggers, plus negative triggers 'Do NOT trigger for ...').

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases a user would actually say — 'not applied', 'pass has no effect', 'matcher never triggers', 'doesn't match', 'callback never fires', 'not fused', plus the literal log string 'END: PATTERN DIDN'T MATCH' and 'opset version mismatch'.

5 / 5

Distinctiveness Conflict Risk

Highly specific niche (OpenVINO MatcherPass non-firing debugging) with both positive and negative trigger guidance, making conflict with other skills minimal.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 suspicious

Warning

Total

15

/

16

Passed

Repository
openvinotoolkit/openvino
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.