CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

github

Load to work or watch GitHub pull requests: threads, comments, reviews, CI logs, merges.

Quality

72%

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 ./skills/github/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 dense, highly actionable command reference with strong validation checkpoints and a sound overview-to-help/reference split, weakened mainly by two long, tangled prose sections that duplicate the --help contracts they cite and could be trimmed or moved to reference files.

Suggestions

Move the PR Merge Outcomes and Review reply check contract prose into reference files (e.g. references/merge-outcomes.md) or shrink them to exit-code/routing summaries, keeping the full contract in pr-merge --help as the body already advertises.

Add a copy-paste example for the VAR_SIGN multi-line GraphQL query with -F variables, and a worked pr-merge --check / queue-wait sequence covering the common merge case.

Break the merge-route paragraph into a short ordered list or decision table so the exit-75 → arm → queue-wait → re-check sequence is scannable instead of prose.

DimensionReasoningScore

Conciseness

The command table is extremely lean with no general-knowledge padding, but the ~450-word PR Merge Outcomes and Review reply check prose paragraphs restate contract detail that each section itself defers to "Full contract: pr-merge --help" / "check-review-replies --help", so the body "could be tightened" — anchor 3. Not 4 because the tightening opportunity is substantial, not minor; not 2 because nothing explains concepts Claude already knows and there is no padded filler.

3 / 5

Actionability

Concrete script paths, per-command flags, exit codes (0/75/1), and copy-paste snippets ("github.sh pr-threads 42", "env -u GH_TOKEN -u GITHUB_TOKEN gh pr list") cover most cases — anchor 4. Not 5 because a few guidance points stay abstract, e.g. "VAR_SIGN: use a multi-line GraphQL query with -F variables" gives no example query, and there is no worked pr-merge invocation.

4 / 5

Workflow Clarity

Multi-step flows carry explicit validation checkpoints: pr-merge --check readiness JSON, the repeat-until-merge-clears loop in "PR blocked with no visible conversations", exit-code routing (exit 75 → arm one exact head → queue-wait), and the "Never gate termination on gh pr view --json mergeable" guard with the state-reading alternative. Not 5 because the merge-route workflow, while fully specified, is a tangled prose paragraph rather than a clearly ordered sequence, making the steps harder to extract than anchor 5's "clear sequence".

4 / 5

Progressive Disclosure

Structure matches the bundle: an overview command table, detail deferred to per-command --help files (scripts/commands/ holds one script per table row), and one real, clearly-signaled reference (references/automatic-review.md, linked as markdown). Anchor 4 ("Good structure; most content is appropriately placed; references mostly clear"). Not 5 because the dense PR Merge Outcomes / reply-check contract prose is inlined in SKILL.md where the skill's own pattern would put it in a reference file or --help.

4 / 5

Total

15

/

20

Passed

Description

66%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.

A tight, domain-scoped description that names several concrete GitHub PR capabilities, but it lacks an explicit 'Use when...' trigger clause and the natural 'PR' synonym, capping completeness and trigger quality below the top anchors.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions PRs, pull requests, PR review threads or comments, CI failures on a PR, or merging."

Include the common synonyms "PR"/"PRs" alongside "pull requests" so the description matches how users naturally refer to them.

Consider naming one or two more capabilities (e.g. creating PRs, posting review replies) to close the coverage gap without adding length.

DimensionReasoningScore

Specificity

"work or watch GitHub pull requests: threads, comments, reviews, CI logs, merges" names the domain and lists several concrete objects, matching anchor 4 ("Lists several specific actions; minor gaps in coverage"). It is not 5 because "work or watch" are generic verbs and coverage omits PR creation, labels, and comment replies; not 3 because more than 1-2 concrete items are enumerated.

4 / 5

Completeness

The "what" is clear (operate on GitHub PR threads, comments, reviews, CI logs, merges), but there is no explicit "Use when..." clause; the trigger is only weakly implied by "Load to work or watch". Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3 — matching anchor 3 ("clear 'what' but 'when' is missing or only weakly implied").

3 / 5

Trigger Term Quality

Natural terms users would say are present: "GitHub pull requests", "reviews", "CI logs", "merges", "threads", "comments". Missing common synonyms like "PR"/"PRs" keeps it at anchor 4 ("Good keyword coverage; a few natural terms missing") rather than 5 ("including synonyms").

4 / 5

Distinctiveness Conflict Risk

"GitHub pull requests" with domain-specific objects (threads, CI logs, merges) carves a clear niche with minimal conflict risk, but "comments", "reviews", and "merges" could partially overlap with a generic code-review or git-merge skill — anchor 4 ("Mostly distinct; minor overlap risk with closely related skills").

4 / 5

Total

15

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

vanillagreencom/kendex

Path

skills/github/SKILL.md

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.