CtrlK
BlogDocsLog inGet started
Tessl Logo

3-verify-pr-fix

Check out a candidate PR locally, restart the MCP server on the PR branch, re-run the exact same MCP tool call that failed in /2-repro-issue, diff the outputs, and audit the fix for locale-independence, DOM-stability, and scope per CLAUDE.md scraping rules. Use when the user says "verify PR

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

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 thorough, executable verification workflow with strong validation checkpoints and clear sequencing. The main weakness is mild verbosity and a monolithic single-file structure that could offload a few sections to references.

Suggestions

Trim rationale commentary in Phase 3/4 to the essential 'why' — e.g. condense the multi-line detached-HEAD and trap explanations so each guard reads in one line.

Move the Phase 6 hard-flag audit rules and/or the Phase 7 report template into a referenced file (e.g. references/audit-flags.md) so the main flow stays scannable.

Hoist the verdict-classification taxonomy (Phase 5) into a short table to reduce prose and make the five outcomes scannable at a glance.

DimensionReasoningScore

Conciseness

The body is dense and mostly actionable with justified, domain-specific rationale (e.g. the cleanup-trap and port-probe explanations), but a few commentary blocks could be trimmed without losing clarity. Not a 5 because some explanatory asides exceed what Claude needs.

4 / 5

Actionability

Every phase ships copy-paste-ready, executable bash (PR parsing, guarded fetch, detached checkout, port probing, MCP initialize/tools/call curls, diff), covering the common verification path end to end.

5 / 5

Workflow Clarity

Eight clearly sequenced phases with explicit validation checkpoints (non-empty baseline files, server-bound wait loop, server-died detection, merge-base diff), error-recovery feedback loops, and a cleanup trap for the destructive checkout/restart.

5 / 5

Progressive Disclosure

No bundle files exist; the single ~190-line file is well-organized into eight phase headers with no nested references, but it exceeds the 50-line simple-skill exception and a couple of sections (the Phase 6 audit ruleset, Phase 7 report template) could plausibly be split into one-level-deep references.

4 / 5

Total

18

/

20

Passed

Description

100%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 concrete, trigger-rich, and clearly distinguishes the skill's niche; it answers both what it does and when to invoke it. No vagueness or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Check out a candidate PR locally', 'restart the MCP server on the PR branch', 're-run the exact same MCP tool call', 'diff the outputs', and 'audit the fix for locale-independence, DOM-stability, and scope' — giving comprehensive coverage with no vague filler.

5 / 5

Completeness

Clearly answers both what (checkout, restart, replay, diff, audit) and when via an explicit 'Use when the user says…' clause with concrete trigger phrases.

5 / 5

Trigger Term Quality

Provides several natural user phrases — 'verify PR #N', 'does this PR fix #M', 'check #N locally', 'test the fix in #N' — covering the common variations a user would actually say.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (verifying a candidate PR against a /2-repro-issue on-main baseline for a LinkedIn MCP server) with distinct triggers and minimal overlap with other skills.

5 / 5

Total

20

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
stickerdaniel/linkedin-mcp-server
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.