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

72

Quality

88%

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

77%

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

A high-signal, executable multi-phase verification workflow with excellent actionability and workflow clarity, including robust validation and cleanup. Its weaknesses are modest verbosity from duplicated cleanup/limitation rationale and a lack of progressive disclosure into bundled reference files.

Suggestions

Remove the duplicate cleanup/trap rationale in Phase 8 (the EXIT trap installed in Phase 3 already covers it) and consolidate the 'Cannot verify fix (skill limitation)' note into one location instead of repeating it in the Non-negotiables section.

Move the lengthy MCP protocol handshake (Phase 4 curl sequence) and/or the report template (Phase 7) into a references/ file and link to it from the main body, so SKILL.md stays a concise overview.

Tighten inline comments to the non-obvious decision only — e.g., keep 'why detached HEAD avoids clobbering a maintainer's pr-$PR branch' but trim the restating of what the subsequent commands already show.

DimensionReasoningScore

Conciseness

The body is dense and executable with no concept-overexplaining, but the cleanup/trap rationale is restated in both Phase 3 and Phase 8 and the 'Cannot verify fix (skill limitation)' reasoning is repeated in the Non-negotiables, so it could be tightened.

2 / 3

Actionability

Provides fully executable gh/jq/git/uv/curl/diff commands with real flags, port probing, and session handling — copy-paste ready rather than pseudocode, matching the top anchor.

3 / 3

Workflow Clarity

Eight phases are clearly sequenced with explicit validation guards (file-existence checks, git-clean check, fetch guard, startup wait loop with crash detection, session-id check) plus an EXIT/INT/TERM cleanup trap and a Non-negotiables checklist, satisfying the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

Content is well-organized into navigable phases, but it is a monolithic single SKILL.md with no bundle reference files, and for a complex ~200-line skill the protocol handshake, report template, and audit criteria are inline rather than split into one-level-deep references.

2 / 3

Total

10

/

12

Passed

Description

100%

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 third-person, concrete, and explicitly pairs capabilities with natural 'Use when...' triggers tied to a specific verification workflow. It is distinguishable and free of vague fluff, scoring at the top of every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — check out the PR, restart the MCP server, re-run the same tool call, diff the outputs, and audit locale-independence/DOM-stability/scope — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both 'what' (checkout, re-run, diff, audit) and 'when' via a 'Use when the user says...' clause with explicit triggers, satisfying the top anchor.

3 / 3

Trigger Term Quality

Includes natural phrasings a user would actually say ('verify PR #N', 'does this PR fix #M', 'check #N locally', 'test the fix in #N'), giving good coverage of trigger variations.

3 / 3

Distinctiveness Conflict Risk

A clear niche tied to the /2-repro-issue baseline, LinkedIn MCP server, and CLAUDE.md scraping rules with distinct triggers, making conflict with other skills unlikely.

3 / 3

Total

12

/

12

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.