CtrlK
BlogDocsLog inGet started
Tessl Logo

fuzzlyn-triage

Triage Fuzzlyn CI runs.

53

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/fuzzlyn-triage/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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.

The body is a concrete, well-sequenced triage procedure with real commands and strong ordering controls. Its main weakness is the lack of validation/verification checkpoints before destructive file deletions in a batch workflow, which caps workflow clarity.

Suggestions

Add verification before destructive steps, e.g. confirm zip extraction succeeded and count matches before deleting the .zip files, and confirm repro.mc reproduces the failure before deleting the other .mc files.

Clarify where to find the "reduced examples" and .mc files (which artifact/directory path) so the early steps are fully actionable.

Add an explicit error-recovery feedback loop when superpmi does not reproduce the assertion failure (what to do / when to move on).

DimensionReasoningScore

Conciseness

The body is mostly lean with concrete commands and little concept over-explanation; a few illustrative examples (seed 123456789, clrjit_unix_x64_x64.dll) could be trimmed but generally earn their place, fitting the efficient-with-minor-trim anchor.

4 / 5

Actionability

It provides specific executable commands (runfo get-helix-payload, superpmi.exe, mcs.exe) with real flags, matching mostly-executable guidance; placeholder paths and a couple of vague directives ("Look at the reduced examples that are available") keep it just below fully copy-paste ready.

4 / 5

Workflow Clarity

Sequencing is excellent ("must be completed in order", "Do NOT parallelize", per-example gating), but the workflow performs destructive and batch operations (deleting .zip files after extraction, deleting other .mc files) without verification before deletion, so the destructive/batch validation cap holds it at 3.

3 / 5

Progressive Disclosure

The content is well-organized into clearly headed numbered sections and is self-contained with no external references needed; it sits just below the 5 anchor which expects well-signaled one-level-deep references, but the structure is clean and navigable.

4 / 5

Total

15

/

20

Passed

Description

48%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.

The description is appropriately third-person and points to a distinct niche, but it is too terse: it states a single action with no "Use when" trigger guidance and no synonyms. It reads more like a label than a complete skill description.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when the user asks to triage or investigate a failing Fuzzlyn CI run."

Expand the action list beyond "triage" to concrete capabilities (download artifacts, reproduce JIT assertion failures, analyze jitdumps, draft GitHub issues).

Include natural trigger synonyms and the tool name variations a user might say (e.g. "Fuzzlyn", "Fuzzlyn CI", "JIT assertion failures").

DimensionReasoningScore

Specificity

The description names the domain ("Fuzzlyn CI runs") and a single minimal action ("Triage"), matching the anchor that names the domain with minimal actions like "Processes PDF files"; it does not list multiple concrete actions needed for a 3.

2 / 5

Completeness

It gives a clear "what" (triage Fuzzlyn CI runs) but no "Use when..." clause or explicit trigger guidance, so per the missing-trigger cap it cannot exceed 3.

3 / 5

Trigger Term Quality

It includes relevant natural terms a user would say ("Fuzzlyn", "CI runs", "triage") but offers no synonyms or variations, fitting the anchor for some relevant keywords missing common variations.

3 / 5

Distinctiveness Conflict Risk

"Fuzzlyn CI runs" pins a clear niche with minimal conflict risk, but the terse form and generic "triage" action leave minor overlap with other triage skills, landing just below the fully-distinct 5 anchor.

4 / 5

Total

12

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
dotnet/runtime
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.