CtrlK
BlogDocsLog inGet started
Tessl Logo

2-repro-issue

Reproduce #N, investigate #N, try #N locally, or verify the bug in #N.

60

Quality

71%

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 ./.agents/skills/2-repro-issue/SKILL.md
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.

The body is a tightly written, highly executable reproduction recipe with strong validation checkpoints, feedback loops, and a checklist; its only weak spot is a long inline protocol block that could be split into a script.

DimensionReasoningScore

Conciseness

The body is dense and mostly lean — executable commands with terse, earned instructions and no padding about basic concepts — but a few caveat sentences (account variants, UI language) could be trimmed slightly.

4 / 5

Actionability

Fully executable, copy-paste-ready bash throughout (gh issue view, uv run, MCP initialize/tools/call curl, jq meta, port loop, cleanup) with clearly marked placeholders, covering the common repro cases.

5 / 5

Workflow Clarity

A clear 4-step sequence with explicit validation checkpoints (dirty-workspace check, port-bind wait, protocol-error checks, 'ask before login') plus feedback loops and a 'Non-negotiables' checklist; the destructive/batch cap does not apply because validation is extensive.

5 / 5

Progressive Disclosure

Well-organized into clearly headed sections (1-4 plus Non-negotiables) with one-level, self-contained navigation and no nested references, though the long inline MCP protocol block is bulk that a script file could offload.

4 / 5

Total

18

/

20

Passed

Description

55%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 states concrete actions but relies on an unnatural '#N' placeholder and omits both the domain and an explicit trigger clause, capping completeness and leaving overlap risk with sibling skills.

Suggestions

Replace the '#N' placeholder with natural trigger phrasing and add an explicit 'Use when...' clause (e.g., 'Use when reproducing, investigating, or verifying a reported LinkedIn-MCP GitHub issue').

Name the domain (LinkedIn-MCP issues / GitHub issue) so the description is distinguishable from sibling skills like /3-verify-pr-fix and triggers on the right requests.

Add common natural synonyms users actually say ('reproduce a bug', 'investigate issue #123', 'verify a reported issue') to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Reproduce', 'investigate', 'try #N locally', 'verify the bug in #N' — which is more than the 1-2 of a score-3 anchor, but coverage is narrow (only issue reproduction/verification) so it falls short of comprehensive.

4 / 5

Completeness

The 'what' is clear (reproduce/investigate/verify a bug in an issue) but there is no explicit 'Use when...' trigger clause, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Has relevant keywords ('reproduce', 'investigate', 'verify the bug') but the literal '#N' placeholder is not a phrase any user says, and the actual domain (GitHub/LinkedIn-MCP issue) is missing, leaving common variations uncovered.

3 / 5

Distinctiveness Conflict Risk

The reproduction/investigation actions are somewhat specific, but the bare '#N' placeholder and absent domain mean it could overlap with the sibling skill '/3-verify-pr-fix' referenced in the body.

3 / 5

Total

13

/

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.