CtrlK
BlogDocsLog inGet started
Tessl Logo

monitor-pr

Monitor one or more GitHub PRs and maintain a live status table showing title, link, check status, resolved/total comments, and reviewer approval. Shows a Windows dialog when a PR is ready to merge. Input: a comma-separated list of PR numbers, "mine", or "all".

58

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/monitor-pr/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 skill body is highly actionable with concrete commands and a clearly sequenced polling workflow including validation. It is somewhat verbose due to repeated emphasis on the polling mandate and inline detail that could be split into references.

Suggestions

Reduce repetition of the polling mandate (it appears in Step 4, the stop-conditions block, and Guidelines) to a single authoritative statement with brief cross-references.

Extract the detailed ADO timeline/log-fetch procedure and the Checks ETA computation into a separate reference file (e.g. references/ci-logs.md and references/eta.md), keeping only the key command in SKILL.md.

Add an explicit error-recovery feedback loop for failed `gh`/API calls during polling (retry/backoff behavior) to round out workflow_clarity.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence, but it is long and contains some restatement (the polling mandate is repeated three times) and over-specified procedure that could be tightened.

3 / 5

Actionability

Fully executable guidance throughout — concrete `gh` commands, a complete GraphQL query with jq filter, curl calls for ADO, and a ready-to-run PowerShell dialog command cover the common cases.

5 / 5

Workflow Clarity

Steps 1–4 are clearly sequenced with a validation checkpoint (re-fetching fresh data each poll) and explicit stop conditions; the destructive empty-commit retrigger has a 'never force push' guard, though the loop lacks an explicit error-recovery feedback loop.

4 / 5

Progressive Disclosure

No bundle files exist; the content is organized into well-labeled sections (Input, Prerequisites, Steps 1–4, Checks ETA, Retriggering, Guidelines) with clear headers, though some inline procedure detail (ADO timeline fetch, ETA computation) could live in a separate reference file.

4 / 5

Total

16

/

20

Passed

Description

62%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 clearly states what the skill does with concrete actions, but omits an explicit 'when to use' trigger clause, which caps completeness. Trigger-term coverage is good but missing common synonyms.

Suggestions

Add an explicit 'Use when ...' clause naming the situations that should trigger this skill (e.g. 'Use when the user asks to monitor PRs, watch PR status, or get notified when a PR is ready to merge').

Include common synonyms/trigger terms such as 'pull request', 'CI checks', and 'watch' alongside 'PR' to improve trigger-term coverage.

Tighten the input format into a single sentence so the description reads as a concise overview rather than a spec.

DimensionReasoningScore

Specificity

Names the domain (GitHub PR monitoring) and several concrete actions — maintain a live status table, show title/link/check status/resolved comments/reviewer approval, and show a Windows dialog — with minor gaps in coverage.

4 / 5

Completeness

There is a clear 'what' (monitor PRs, maintain a status table, alert when ready to merge) but no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Includes natural terms like 'GitHub PRs', 'PR is ready to merge', 'check status', and 'reviewer approval', but lacks common synonyms like 'pull request', 'CI', or 'checks passing'.

4 / 5

Distinctiveness Conflict Risk

The niche (live PR status polling with Windows merge dialog) is fairly distinct and unlikely to trigger for unrelated skills, with only minor overlap risk against general GitHub/PR-review skills.

4 / 5

Total

15

/

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
BabylonJS/Babylon.js
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.