CtrlK
BlogDocsLog inGet started
Tessl Logo

pr-failure-scan

Analyze a dotnet/runtime PR's CI failures, skip failures already known to Build Analysis, find matching Known Build Errors, and create or draft new KBEs for the remaining failures. Supports dry-run output to local markdown files instead of creating GitHub issues.

65

Quality

78%

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/pr-failure-scan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 well-sequenced, validation-rich workflow for a destructive operation, with concrete guidance and one clear external reference; its main weakness is moderate verbosity in the draft template and signature-preference sections.

Suggestions

Add an executable gh command for fetching the PR's completed check runs (e.g. a sample `gh api repos/dotnet/runtime/commits/<sha>/check-runs` call) rather than describing the fetch conceptually.

Move the multi-section draft-file template into the shared create-kbe.instructions.md file (or a bundled reference) and link to it, trimming the inline SKILL.md body.

Tighten the 'Dry-run drafting guidance' signature-preference bullets into a shorter rule set to reduce token overhead.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's knowledge of CI/AzDO/Helix concepts, but the inline draft template and the signature-preference prose could be tightened; a few padded elaborations keep it below the 4 anchor.

3 / 5

Actionability

Provides concrete API references, explicit parse instructions, and a copy-ready draft-file template, but check-run and Build Analysis fetching are described conceptually rather than as executable gh commands.

4 / 5

Workflow Clarity

A clearly numbered Step 0–6 sequence with explicit validation checkpoints (Step 1 permission gate, per-issue confirmation in live mode, decline-to-stop loops) appropriate for the destructive issue-creation operation.

5 / 5

Progressive Disclosure

Good section structure with a single well-signaled one-level-deep reference to create-kbe.instructions.md; minor inlining of the draft template and label guidance keeps it just short of the 5 anchor.

4 / 5

Total

16

/

20

Passed

Description

82%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 specific, distinctive, and rich in natural domain trigger terms, but it omits an explicit 'Use when…' usage clause, which caps its completeness score.

Suggestions

Add an explicit 'Use when…' clause, e.g. 'Use when triaging CI failures on a dotnet/runtime PR or when the user asks to create or draft KBEs from a PR's failed checks.'

Mention the bare PR-number/URL invocation form as a trigger so users searching by invocation ('/pr-failure-scan') match the description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — analyze CI failures, skip Build Analysis knowns, find matching Known Build Errors, create/draft new KBEs, and dry-run to markdown — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Clearly states what the skill does but provides no explicit 'Use when…' trigger clause; per the rubric guideline, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Covers the natural domain terms a user would say ('CI failures', 'Known Build Errors', 'KBEs', 'GitHub issues', 'dry-run', 'markdown files', 'dotnet/runtime PR') plus the KBE abbreviation/synonym alongside its expansion.

5 / 5

Distinctiveness Conflict Risk

Highly specific niche (dotnet/runtime PR CI failures, KBEs, Build Analysis) and explicitly contrasts itself with the scheduled CI failure scan workflow, minimizing conflict risk; uses consistent third-person voice.

5 / 5

Total

18

/

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.